modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-27 18:27:39
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 500
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-27 18:23:41
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Astarossa/Victor_Tsoi | Astarossa | 2024-05-22T01:38:45Z | 2 | 0 | transformers | [
"transformers",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-20T13:16:34Z | ---
license: apache-2.0
---
|
DUAL-GPO-2/phi-2-irepo-chatml-v3-i2 | DUAL-GPO-2 | 2024-05-22T01:32:38Z | 2 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"phi",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"custom_code",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1",
"base_model:adapter:DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1",
"region:us"
] | null | 2024-05-21T23:18:35Z | ---
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
base_model: DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: phi-2-irepo-chatml-v3-i2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# phi-2-irepo-chatml-v3-i2
This model is a fine-tuned version of [DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1](https://huggingface.co/DUAL-GPO/phi-2-irepo-chatml-merged-v1-i1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2 |
Cyberlounge/LGTM-1-kururu-2b | Cyberlounge | 2024-05-22T01:31:22Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T11:09:23Z | ---
license: apache-2.0
---
|
Meggido/L3-8B-Stheno-v3.1-6.5bpw-h8-exl2 | Meggido | 2024-05-22T01:20:45Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T01:14:55Z | ---
language:
- en
license: cc-by-nc-4.0
---
# ⚡ExLlamaV2 quant of : [L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1)
> [!note]
> ➡️ **Exl2 version :** [0.0.21](https://github.com/turboderp/exllamav2/releases/tag/v0.0.21)<br/>
> ➡️ **Cal. dataset :** Default.<br/>
> 📄 <a href="https://huggingface.co/Meggido/L3-8B-Stheno-v3.1-6.5bpw-h8-exl2/resolve/main/measurement.json" download>Measurement.json</a> file.
<img src="https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg" style="width: 80%; min-width: 400px; display: block; margin: auto;">
**Model: Llama-3-8B-Stheno-v3.1**
This has been an experimental model I've been working on for a bit. Llama-3 was kind of difficult to work with.
<br>I also had been hired to create a model for an Organisation, and I used the lessons I learnt from fine-tuning that one for this specific model. Unable to share that one though, unfortunately.
<br>Made from outputs generated by Claude-3-Opus along with Human-Generated Data.
Stheno-v3.1
\- A model made for 1-on-1 Roleplay ideally, but one that is able to handle scenarios, RPGs and storywriting fine.
<br>\- Uncensored during actual roleplay scenarios. # I do not care for zero-shot prompting like what some people do. It is uncensored enough in actual usecases.
<br>\- I quite like the prose and style for this model.
#### Testing Notes
<br>\- Known as L3-RP-v2.1 on Chaiverse, it did decently there [>1200 Elo]
<br>\- Handles character personalities well. Great for 1 on 1 Roleplay sessions.
<br>\- May need further token context & few-shot examples if using it as a Narrator / RPG Roleplaying session. It is able to handle them though.
<br>\- A model leaning towards NSFW, mention explicitly in prompts if you want to steer away. [Avoid Negative Reinforcement]
<br>\- Occasionally spits out leaking XML and nonsense. A regen / swipe instantly fixes that.
<br>\- Unique / Varied Answers when Regenerating answers. Pretty cool?
<br>\- Works best with *some* token context in the character card itself. A chef needs ingredients to cook, no?
***
**Recommended Samplers:**
```
Temperature - 1.12 to 1.32
Min-P - 0.075
Top-K - 40
Repetition Penalty - 1.1
```
**Stopping Strings:**
```
\n{{User}} # Or Equivalent, depending on Frontend
<|eot_id|>
<|end_of_text|>
\n< # If there is leakage of XML tags in response. May happen Occasionally, Regenerate Answer as Needed. Happens rarely.
```
**Prompting Template - Llama-3-Instruct**
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>
```
**Basic Roleplay System Prompt**
```
You are an expert actor that can fully immerse yourself into any role given. You do not break character for any reason, even if someone tries addressing you as an AI or language model.
Currently your role is {{char}}, which is described in detail below. As {{char}}, continue the exchange with {{user}}.
```
***
Support me here if you're interested. [Ko-Fi](https://ko-fi.com/sao10k)
If not, that's fine too. Feedback would be nice.
```
Art by wada_kazu / わだかず (pixiv page private?)
```
*** |
RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf | RichardErkhov | 2024-05-22T01:20:42Z | 105 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T19:31:59Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
LLaMA2-13B-Estopia - GGUF
- Model creator: https://huggingface.co/KoboldAI/
- Original model: https://huggingface.co/KoboldAI/LLaMA2-13B-Estopia/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [LLaMA2-13B-Estopia.Q2_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q2_K.gguf) | Q2_K | 4.52GB |
| [LLaMA2-13B-Estopia.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ3_XS.gguf) | IQ3_XS | 4.99GB |
| [LLaMA2-13B-Estopia.IQ3_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ3_S.gguf) | IQ3_S | 5.27GB |
| [LLaMA2-13B-Estopia.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K_S.gguf) | Q3_K_S | 5.27GB |
| [LLaMA2-13B-Estopia.IQ3_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ3_M.gguf) | IQ3_M | 5.57GB |
| [LLaMA2-13B-Estopia.Q3_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K.gguf) | Q3_K | 5.9GB |
| [LLaMA2-13B-Estopia.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K_M.gguf) | Q3_K_M | 5.9GB |
| [LLaMA2-13B-Estopia.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q3_K_L.gguf) | Q3_K_L | 6.45GB |
| [LLaMA2-13B-Estopia.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ4_XS.gguf) | IQ4_XS | 6.54GB |
| [LLaMA2-13B-Estopia.Q4_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_0.gguf) | Q4_0 | 6.86GB |
| [LLaMA2-13B-Estopia.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.IQ4_NL.gguf) | IQ4_NL | 6.9GB |
| [LLaMA2-13B-Estopia.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_K_S.gguf) | Q4_K_S | 6.91GB |
| [LLaMA2-13B-Estopia.Q4_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_K.gguf) | Q4_K | 7.33GB |
| [LLaMA2-13B-Estopia.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_K_M.gguf) | Q4_K_M | 7.33GB |
| [LLaMA2-13B-Estopia.Q4_1.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q4_1.gguf) | Q4_1 | 7.61GB |
| [LLaMA2-13B-Estopia.Q5_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_0.gguf) | Q5_0 | 8.36GB |
| [LLaMA2-13B-Estopia.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_K_S.gguf) | Q5_K_S | 8.36GB |
| [LLaMA2-13B-Estopia.Q5_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_K.gguf) | Q5_K | 8.6GB |
| [LLaMA2-13B-Estopia.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_K_M.gguf) | Q5_K_M | 8.6GB |
| [LLaMA2-13B-Estopia.Q5_1.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q5_1.gguf) | Q5_1 | 9.1GB |
| [LLaMA2-13B-Estopia.Q6_K.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q6_K.gguf) | Q6_K | 9.95GB |
| [LLaMA2-13B-Estopia.Q8_0.gguf](https://huggingface.co/RichardErkhov/KoboldAI_-_LLaMA2-13B-Estopia-gguf/blob/main/LLaMA2-13B-Estopia.Q8_0.gguf) | Q8_0 | 12.88GB |
Original model description:
---
base_model:
- TheBloke/Llama-2-13B-fp16
tags:
- mergekit
- merge
license: cc-by-nc-4.0
---
# Introduction
- Estopia is a model focused on improving the dialogue and prose returned when using the instruct format. As a side benefit, character cards and similar seem to have also improved, remembering details well in many cases.
- It focuses on "guided narratives" - using instructions to guide or explore fictional stories, where you act as a guide for the AI to narrate and fill in the details.
- It has primarily been tested around prose, using instructions to guide narrative, detail retention and "neutrality" - in particular with regards to plot armour. Unless you define different rules for your adventure / narrative with instructions, it should be realistic in the responses provided.
- It has been tested using different modes, such as instruct, chat, adventure and story modes - and should be able to do them all to a degree, with it's strengths being instruct and adventure, with story being a close second.
# Usage
- The Estopia model has been tested primarily using the Alpaca format, but with the range of models included likely has some understanding of others. Some examples of tested formats are below:
- ```\n### Instruction:\nWhat colour is the sky?\n### Response:\nThe sky is...```
- ```<Story text>\n***\nWrite a summary of the text above\n***\nThe story starts by...```
- Using the Kobold Lite AI adventure mode
- ```User:Hello there!\nAssistant:Good morning...\n```
- For settings, the following are recommended for general use:
- Temperature: 0.8-1.2
- Min P: 0.05-0.1
- Max P: 0.92, or 1 if using a Min P greater than 0
- Top K: 0
- Response length: Higher than your usual amount most likely - for example a common value selected is 512.
- Note: Response lengths are not guaranteed to always be this length. On occasion, responses may be shorter if they convey the response entirely, other times they could be upwards of this value. It depends mostly on the character card, instructions, etc.
- Rep Pen: 1.1
- Rep Pen Range: 2 or 3x your response length
- Stopping tokens (Not needed, but can help if the AI is writing too much):
- ```##||$||---||$||ASSISTANT:||$||[End||$||</s>``` - A single string for Kobold Lite combining the ones below
- ```##```
- ```---```
- ```ASSISTANT:```
- ```[End```
- ```</s>```
- The settings above should provide a generally good experience balancing instruction following and creativity. Generally the higher you set the temperature, the greater the creativity and higher chance of logical errors when providing responses from the AI.
# Recipe
This model was made in three stages, along with many experimental stages which will be skipped for brevity. The first was internally referred to as EstopiaV9, which has a high degree of instruction following and creativity in responses, though they were generally shorter and a little more restricted in the scope of outputs, but conveyed nuance better.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.10
- model: Undi95/Emerhyst-13B
parameters:
weight: 0.05
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.05
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The second part of the merge was known as EstopiaV13. This produced responses which were long, but tended to write beyond good stopping points for further instructions to be added as it leant heavily on novel style prose. It did however benefit from a greater degree of neutrality as described above, and retained many of the detail tracking abilities of V9.
```yaml
merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
- model: TheBloke/Llama-2-13B-fp16
- model: Undi95/UtopiaXL-13B
parameters:
weight: 1.0
- model: Doctor-Shotgun/cat-v1.0-13b
parameters:
weight: 0.01
- model: chargoddard/rpguild-chatml-13b
parameters:
weight: 0.02
- model: PygmalionAI/mythalion-13b
parameters:
weight: 0.08
- model: CalderaAI/13B-Thorns-l2
parameters:
weight: 0.02
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.20
dtype: float16
```
The third step was a merge between the two to retain the benefits of both as much as possible. This was performed using the dare merging technique.
```yaml
# task-arithmetic style
models:
- model: EstopiaV9
parameters:
weight: 1
density: 1
- model: EstopiaV13
parameters:
weight: 0.05
density: 0.30
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
parameters:
int8_mask: true
dtype: bfloat16
```
# Model selection
- Undi95/UtopiaXL-13B
- Solid all around base for models, with the ability to write longer responses and generally good retension to detail.
- Doctor-Shotgun/cat-v1.0-13b
- A medical focused model which is added to focus a little more on the human responses, such as for psycology.
- PygmalionAI/mythalion-13b
- A roleplay and instruct focused model, which improves attentiveness to character card details and the variety of responses
- Undi95/Emerhyst-13B
- A roleplay but also longer form response model. It can be quite variable, but helps add to the depth and possible options the AI can respond with during narratives.
- CalderaAI/13B-Thorns-l2
- A neutral and very attentive model. It is good at chat and following instructions, which help benefit these modes.
- KoboldAI/LLaMA2-13B-Tiefighter
- A solid all around model, focusing on story writing and adventure modes. It provides all around benefits to creativity and the prose in models, along with adventure mode support.
- chargoddard/rpguild-chatml-13b
- A roleplay model, which introduces new data and also improves the detail retention in longer narratives.
# Notes
- With the differing models inside, this model will not have perfect end of sequence tokens which is a problem many merges can share. While attempts have been made to minimise this, you may occasionally get oddly behaving tokens - this should be possible to resolve with a quick manual edit once and the model should pick up on it.
- Chat is one of the least tested areas for this model. It works fairly well, but it can be quite character card dependant.
- This is a narrative and prose focused model. As a result, it can and will talk for you if guided to do so (such as asking it to act as a co-author or narrator) within instructions or other contexts. This can be mitigated mostly by adding instructions to limit this, or using chat mode instead.
# Future areas
- Llava
- Some success has been had with merging the llava lora on this. While no in depth testing has been performed, more narrative responses based on the images could be obtained - though there were drawbacks in the form of degraded performance in other areas, and hallucinations due to the fictional focus of this model.
- Stheno
- A merge which has similar promise from Sao. Some merge attempts have been made between the two and were promising, but not entirely consistent at the moment. With some possible refinement, this could produce an even stronger model.
- DynamicFactor
- All the merges used have been based on llama two in this merge, but a dare merge with dynamic factor (an attempted refinement of llama two) showed a beneficial improvement to the instruction abilities of the model, along with lengthy responses. It lost a little of the variety of responses, so perhaps if a balance of it could be added the instruction abilities and reasoning could be improved even further.
|
sajidof/fine-tune-wav2vec2-large-xls-r-300m-ssw_224s | sajidof | 2024-05-22T01:20:05Z | 5 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:ml-superb-subset",
"base_model:facebook/wav2vec2-xls-r-300m",
"base_model:finetune:facebook/wav2vec2-xls-r-300m",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-05-21T23:28:07Z | ---
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- ml-superb-subset
metrics:
- wer
model-index:
- name: fine-tune-wav2vec2-large-xls-r-300m-ssw_224s
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ml-superb-subset
type: ml-superb-subset
config: ssw
split: test[:100]
args: ssw
metrics:
- name: Wer
type: wer
value: 0.5492063492063493
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fine-tune-wav2vec2-large-xls-r-300m-ssw_224s
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the ml-superb-subset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8167
- Wer: 0.5492
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 6.4669 | 2.0997 | 400 | 3.1603 | 1.0 |
| 2.5291 | 4.1995 | 800 | 1.2456 | 0.9651 |
| 0.8905 | 6.2992 | 1200 | 0.7689 | 0.7746 |
| 0.5222 | 8.3990 | 1600 | 0.7821 | 0.7048 |
| 0.3768 | 10.4987 | 2000 | 0.7637 | 0.7238 |
| 0.2874 | 12.5984 | 2400 | 0.7030 | 0.6063 |
| 0.2216 | 14.6982 | 2800 | 0.8468 | 0.6571 |
| 0.1954 | 16.7979 | 3200 | 0.7099 | 0.5841 |
| 0.1649 | 18.8976 | 3600 | 0.7696 | 0.5651 |
| 0.1384 | 20.9974 | 4000 | 0.8328 | 0.5873 |
| 0.1208 | 23.0971 | 4400 | 0.7899 | 0.5651 |
| 0.1054 | 25.1969 | 4800 | 0.8310 | 0.5714 |
| 0.095 | 27.2966 | 5200 | 0.8183 | 0.5302 |
| 0.0835 | 29.3963 | 5600 | 0.8167 | 0.5492 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
JawadC/lora-dreambooth | JawadC | 2024-05-22T01:19:11Z | 1 | 0 | diffusers | [
"diffusers",
"text-to-image",
"diffusers-training",
"lora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | 2024-05-21T15:58:20Z | ---
license: openrail++
library_name: diffusers
tags:
- text-to-image
- text-to-image
- diffusers-training
- diffusers
- lora
- template:sd-lora
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a photo of BEAUFORT cheese
widget:
- text: A photo of BEAUFORT cheese in a bucket
output:
url: image_0.png
- text: A photo of BEAUFORT cheese in a bucket
output:
url: image_1.png
- text: A photo of BEAUFORT cheese in a bucket
output:
url: image_2.png
- text: A photo of BEAUFORT cheese in a bucket
output:
url: image_3.png
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# SDXL LoRA DreamBooth - JawadC/lora-dreambooth
<Gallery />
## Model description
These are JawadC/lora-dreambooth LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of BEAUFORT cheese to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](JawadC/lora-dreambooth/tree/main) them in the Files & versions tab.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
ellen625/opt_1.3b_wiki_k10 | ellen625 | 2024-05-22T01:16:12Z | 138 | 0 | transformers | [
"transformers",
"safetensors",
"opt",
"text-generation",
"generated_from_trainer",
"base_model:facebook/opt-1.3b",
"base_model:finetune:facebook/opt-1.3b",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T01:12:30Z | ---
license: other
tags:
- generated_from_trainer
base_model: facebook/opt-1.3b
model-index:
- name: opt_1.3b_wiki_k10
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# opt_1.3b_wiki_k10
This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9411
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.9975 | 0.4172 | 500 | 0.9572 |
| 0.9733 | 0.8344 | 1000 | 0.9430 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.2
- Datasets 2.19.1
- Tokenizers 0.19.1
|
giantdev/mistral-m6-ltqDiEOy111 | giantdev | 2024-05-22T01:11:04Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T01:09:17Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
giantdev/mistral-m4-htC0Keav111 | giantdev | 2024-05-22T01:04:23Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T01:02:29Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
BilalMuftuoglu/deit-base-distilled-patch16-224-75-fold2 | BilalMuftuoglu | 2024-05-22T01:01:31Z | 33 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"deit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-base-distilled-patch16-224",
"base_model:finetune:facebook/deit-base-distilled-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-22T00:42:41Z | ---
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-base-distilled-patch16-224-75-fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9302325581395349
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# deit-base-distilled-patch16-224-75-fold2
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2625
- Accuracy: 0.9302
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 2 | 0.8815 | 0.4419 |
| No log | 2.0 | 4 | 0.6436 | 0.6977 |
| No log | 3.0 | 6 | 0.8488 | 0.6977 |
| No log | 4.0 | 8 | 0.8219 | 0.6977 |
| 0.6918 | 5.0 | 10 | 0.5491 | 0.6977 |
| 0.6918 | 6.0 | 12 | 0.4603 | 0.7209 |
| 0.6918 | 7.0 | 14 | 0.5602 | 0.7442 |
| 0.6918 | 8.0 | 16 | 0.5694 | 0.7442 |
| 0.6918 | 9.0 | 18 | 0.4430 | 0.8140 |
| 0.3867 | 10.0 | 20 | 0.3880 | 0.8605 |
| 0.3867 | 11.0 | 22 | 0.5069 | 0.8140 |
| 0.3867 | 12.0 | 24 | 0.3739 | 0.8605 |
| 0.3867 | 13.0 | 26 | 0.2981 | 0.8837 |
| 0.3867 | 14.0 | 28 | 0.3170 | 0.8837 |
| 0.2722 | 15.0 | 30 | 0.2511 | 0.8837 |
| 0.2722 | 16.0 | 32 | 0.2408 | 0.8837 |
| 0.2722 | 17.0 | 34 | 0.3751 | 0.8605 |
| 0.2722 | 18.0 | 36 | 0.3081 | 0.8605 |
| 0.2722 | 19.0 | 38 | 0.2489 | 0.8837 |
| 0.209 | 20.0 | 40 | 0.2802 | 0.8837 |
| 0.209 | 21.0 | 42 | 0.2625 | 0.9302 |
| 0.209 | 22.0 | 44 | 0.2595 | 0.9302 |
| 0.209 | 23.0 | 46 | 0.5048 | 0.8372 |
| 0.209 | 24.0 | 48 | 0.2880 | 0.8605 |
| 0.2027 | 25.0 | 50 | 0.2860 | 0.8372 |
| 0.2027 | 26.0 | 52 | 0.4067 | 0.8372 |
| 0.2027 | 27.0 | 54 | 0.2462 | 0.9070 |
| 0.2027 | 28.0 | 56 | 0.2753 | 0.9070 |
| 0.2027 | 29.0 | 58 | 0.3699 | 0.8140 |
| 0.1426 | 30.0 | 60 | 0.4983 | 0.8372 |
| 0.1426 | 31.0 | 62 | 0.3140 | 0.8605 |
| 0.1426 | 32.0 | 64 | 0.3470 | 0.8372 |
| 0.1426 | 33.0 | 66 | 0.4443 | 0.8372 |
| 0.1426 | 34.0 | 68 | 0.2583 | 0.8837 |
| 0.1385 | 35.0 | 70 | 0.2239 | 0.9302 |
| 0.1385 | 36.0 | 72 | 0.2708 | 0.9070 |
| 0.1385 | 37.0 | 74 | 0.2660 | 0.9070 |
| 0.1385 | 38.0 | 76 | 0.2754 | 0.9070 |
| 0.1385 | 39.0 | 78 | 0.4246 | 0.8605 |
| 0.1202 | 40.0 | 80 | 0.2779 | 0.9070 |
| 0.1202 | 41.0 | 82 | 0.2726 | 0.8837 |
| 0.1202 | 42.0 | 84 | 0.2536 | 0.9070 |
| 0.1202 | 43.0 | 86 | 0.2667 | 0.9302 |
| 0.1202 | 44.0 | 88 | 0.4191 | 0.8837 |
| 0.1211 | 45.0 | 90 | 0.3213 | 0.9302 |
| 0.1211 | 46.0 | 92 | 0.2290 | 0.9070 |
| 0.1211 | 47.0 | 94 | 0.3043 | 0.8837 |
| 0.1211 | 48.0 | 96 | 0.1906 | 0.9302 |
| 0.1211 | 49.0 | 98 | 0.3201 | 0.8605 |
| 0.1067 | 50.0 | 100 | 0.3062 | 0.8837 |
| 0.1067 | 51.0 | 102 | 0.2047 | 0.9302 |
| 0.1067 | 52.0 | 104 | 0.2116 | 0.9070 |
| 0.1067 | 53.0 | 106 | 0.2113 | 0.9302 |
| 0.1067 | 54.0 | 108 | 0.2340 | 0.9302 |
| 0.0826 | 55.0 | 110 | 0.2328 | 0.9302 |
| 0.0826 | 56.0 | 112 | 0.2824 | 0.8837 |
| 0.0826 | 57.0 | 114 | 0.2921 | 0.8837 |
| 0.0826 | 58.0 | 116 | 0.2608 | 0.9302 |
| 0.0826 | 59.0 | 118 | 0.2650 | 0.9302 |
| 0.0894 | 60.0 | 120 | 0.2878 | 0.9070 |
| 0.0894 | 61.0 | 122 | 0.2935 | 0.9070 |
| 0.0894 | 62.0 | 124 | 0.2656 | 0.9302 |
| 0.0894 | 63.0 | 126 | 0.3438 | 0.9070 |
| 0.0894 | 64.0 | 128 | 0.2840 | 0.9302 |
| 0.0964 | 65.0 | 130 | 0.2711 | 0.9070 |
| 0.0964 | 66.0 | 132 | 0.2888 | 0.9070 |
| 0.0964 | 67.0 | 134 | 0.2723 | 0.9070 |
| 0.0964 | 68.0 | 136 | 0.2563 | 0.8837 |
| 0.0964 | 69.0 | 138 | 0.2336 | 0.9302 |
| 0.0711 | 70.0 | 140 | 0.2386 | 0.9302 |
| 0.0711 | 71.0 | 142 | 0.2482 | 0.9070 |
| 0.0711 | 72.0 | 144 | 0.2821 | 0.9070 |
| 0.0711 | 73.0 | 146 | 0.2941 | 0.8837 |
| 0.0711 | 74.0 | 148 | 0.2564 | 0.9070 |
| 0.0824 | 75.0 | 150 | 0.2509 | 0.9302 |
| 0.0824 | 76.0 | 152 | 0.2544 | 0.9302 |
| 0.0824 | 77.0 | 154 | 0.2474 | 0.9302 |
| 0.0824 | 78.0 | 156 | 0.2375 | 0.9302 |
| 0.0824 | 79.0 | 158 | 0.2389 | 0.9302 |
| 0.0691 | 80.0 | 160 | 0.2371 | 0.9302 |
| 0.0691 | 81.0 | 162 | 0.2393 | 0.9302 |
| 0.0691 | 82.0 | 164 | 0.2523 | 0.9070 |
| 0.0691 | 83.0 | 166 | 0.2677 | 0.8837 |
| 0.0691 | 84.0 | 168 | 0.2945 | 0.8837 |
| 0.0638 | 85.0 | 170 | 0.3245 | 0.8605 |
| 0.0638 | 86.0 | 172 | 0.2960 | 0.8837 |
| 0.0638 | 87.0 | 174 | 0.2658 | 0.9302 |
| 0.0638 | 88.0 | 176 | 0.2614 | 0.9302 |
| 0.0638 | 89.0 | 178 | 0.2613 | 0.9302 |
| 0.0705 | 90.0 | 180 | 0.2549 | 0.9302 |
| 0.0705 | 91.0 | 182 | 0.2510 | 0.9302 |
| 0.0705 | 92.0 | 184 | 0.2514 | 0.9302 |
| 0.0705 | 93.0 | 186 | 0.2522 | 0.9302 |
| 0.0705 | 94.0 | 188 | 0.2504 | 0.9070 |
| 0.0666 | 95.0 | 190 | 0.2459 | 0.9302 |
| 0.0666 | 96.0 | 192 | 0.2424 | 0.9302 |
| 0.0666 | 97.0 | 194 | 0.2428 | 0.9302 |
| 0.0666 | 98.0 | 196 | 0.2451 | 0.9302 |
| 0.0666 | 99.0 | 198 | 0.2471 | 0.9302 |
| 0.0566 | 100.0 | 200 | 0.2482 | 0.9302 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
CloneBO/OracleLM | CloneBO | 2024-05-22T00:57:39Z | 170 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:46:57Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
starBot/CartPole-v1 | starBot | 2024-05-22T00:56:14Z | 0 | 0 | null | [
"region:us"
] | null | 2024-05-22T00:40:25Z | metadata
library_name: stable-baselines3
tags:
- CartPole-v1
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 236.70 +/- 117.42
name: mean_reward
verified: false |
Shalie/GbfDjeetaPonyXL | Shalie | 2024-05-22T00:55:33Z | 3 | 0 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:AstraliteHeart/pony-diffusion-v6",
"base_model:adapter:AstraliteHeart/pony-diffusion-v6",
"license:other",
"region:us"
] | text-to-image | 2024-05-22T00:47:47Z | ---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, pink hairband, dress, puffy sleeves,
gauntlets, brown thighhighs, thigh boots
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06109-1831543041-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, pink hairband,
dress, p.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, pink hairband, dress, puffy sleeves,
gauntlets, brown thighhighs, thigh boots, bell, cat, full body, ginkgo leaf,
ginkgo tree, kitten, leaf, log, blush, looking at viewer, one eye closed,
open mouth, solo, :q
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06110-3684244623-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, pink hairband,
dress, p.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, pink hairband, dress, puffy sleeves,
gauntlets, brown thighhighs, thigh boots, bug, butterfly, cowboy shot, from
side, personification, blush, closed mouth, looking at viewer, sitting,
smile, solo, tired
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06111-2544871436-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, pink hairband,
dress, p.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, pink hairband, dress, puffy sleeves,
gauntlets, brown thighhighs, thigh boots, sheath, border, grey background,
arm up, blush, head tilt, leaning forward, looking at viewer, parted lips,
smile, solo, standing, afraid
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06114-843358421-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, pink hairband,
dress, p.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, pink hairband, dress, puffy sleeves,
gauntlets, brown thighhighs, thigh boots, sheath, flower, groin, closed
mouth, looking at viewer, looking to the side, lying, on back, smile, solo,
sleepy
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06113-2331713302-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, pink hairband,
dress, p.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, pink hairband, dress, puffy sleeves,
gauntlets, brown thighhighs, thigh boots, simple background, snow,
snowflakes, snowing, closed mouth, interlocked fingers, looking at viewer,
solo, surprised
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06112-2576520290-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, pink hairband,
dress, p.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, bag, beret, black shirt, brown
pantyhose, hair ornament, hairclip, hat, long sleeves, pantyhose, pleated
skirt, red ribbon, red skirt, ribbon, shirt, skirt, sleeves past wrists, x
hair ornament, grey background, letter, love letter, simple background, :3,
blush, closed mouth, head tilt, looking at viewer, solo, happy
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06117-1738714704-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, bag, beret,
black shirt.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, bare shoulders, blue dress,
criss-cross halter, dress, earrings, hairband, halterneck, jewelry,
off-shoulder dress, off shoulder, puffy short sleeves, puffy sleeves, short
sleeves, electric fan, from behind, indoors, ramune, summer, blush, hands
up, holding, holding egg, looking at viewer, smile, solo, loving
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06115-1638284322-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, bare
shoulders, blue dr.png
- text: >-
score_9, score_8_up, score_7_up, uncensored, source_anime, 1girl,
<lora:spgbfDjeetaXLPony:1> djeetadef, sleepwear, blurry, blurry background,
chair, depth of field, from behind, office chair, swivel chair, blush,
handgun, holding, holding gun, holding weapon, looking at viewer, solo,
trigger discipline, weapon, fear
parameters:
negative_prompt: 3d, monochrome, greyscale, source_pony, source_furry
output:
url: >-
images/06116-455608584-score_9, score_8_up, score_7_up, uncensored,
source_anime, 1girl, _lora_spgbfDjeetaXLPony_1_ djeetadef, sleepwear,
blurry, blur.png
base_model: AstraliteHeart/pony-diffusion-v6
instance_prompt: null
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
---
# Djeeta - Granblue Fantasy
<Gallery />
## Model description
Djeeta - Granblue Fantasy!
Trained on 1 outfit, it has a trigger word corresponding to the appearance of the character and suggested prompts that summons related clothes and accesories.
Works well with 0.7-1.0 weight
## Trigger words
Debut Outfit:
`djeetadef, pink hairband, dress, puffy sleeves, gauntlets, brown thighhighs, thigh boots`
## Download model
Weights for this model are available in Safetensors format.
[Download](/Shalie/GbfDjeetaPonyXL/tree/main) them in the Files & versions tab.
### License
This LoRA model is provided under the [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/) license.
## Restrictions:
- **Usage in Generation Services**: You are not allowed to use the model in any generation services without proper permission from the original creator.
- **Commercial Usage**: The sale of the model or any commercial usage is strictly prohibited without explicit written permission from the original creator. |
scy02718/speecht5_finetuned_voxpopuli_nl | scy02718 | 2024-05-22T00:50:40Z | 75 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"dataset:voxpopuli",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-to-audio | 2024-05-22T00:47:31Z | ---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_nl
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# speecht5_finetuned_voxpopuli_nl
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
KYUNGHYUN9/itos_v0.023_1.3b-1000step_onlyitos | KYUNGHYUN9 | 2024-05-22T00:47:06Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-22T00:47:05Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
giantdev/mistral-m4-VWLgtx1d | giantdev | 2024-05-22T00:38:15Z | 122 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:36:22Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
superdrew100/UwU_phi3_mini | superdrew100 | 2024-05-22T00:32:48Z | 9 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-21T18:27:29Z | ---
license: mit
---
# UwU_phi3_mini-unsloth_V1.Q4_K_M.gguf
-is trained on only 20% for one epoch of the
https://huggingface.co/datasets/superdrew100/UwU_Alpaca_data_V2 |
hgnoi/4ZrpXbA2V6cBQJ50 | hgnoi | 2024-05-22T00:26:32Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:24:19Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/d0mAoJioWpEBgMZg | hgnoi | 2024-05-22T00:25:54Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:24:00Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
AI-Engine/Phi-3-medium-128k-instruct-GGUF | AI-Engine | 2024-05-22T00:24:53Z | 17 | 0 | null | [
"gguf",
"phi-3",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-21T23:46:09Z | ---
license: mit
tags:
- gguf
- phi-3
---
<span style="color:red">NOTE: Requires 128k context support -> [https://github.com/ggerganov/llama.cpp/releases/tag/b2961](https://github.com/ggerganov/llama.cpp/releases/tag/b2961)</span>.
GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
- Original model: [Microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/tree/main)
- Model creator: [Microsoft](https://huggingface.co/microsoft)
- [License](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/blob/main/LICENSE)
## Recommended Prompt Format (Chat Format)
```
<|user|>
Provide some context and/or instructions to the model.<|end|>
<|assistant|>
AI message goes here<|end|>
<|user|>
The user’s message goes here<|end|>
<|assistant|>
``` |
hgnoi/w4eAx7MwEBYlCnTE | hgnoi | 2024-05-22T00:22:43Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:20:57Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/33B9IoEyqKaptLrD | hgnoi | 2024-05-22T00:22:04Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:20:17Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RichardErkhov/winglian_-_Llama-3-8b-64k-PoSE-4bits | RichardErkhov | 2024-05-22T00:16:56Z | 79 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:2309.10400",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-22T00:04:52Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-3-8b-64k-PoSE - bnb 4bits
- Model creator: https://huggingface.co/winglian/
- Original model: https://huggingface.co/winglian/Llama-3-8b-64k-PoSE/
Original model description:
---
language:
- en
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- axolotl
---
## Llama 3 8B 64K
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<img src="https://huggingface.co/winglian/Llama-3-8b-64k-PoSE/resolve/main/output.png" />
This model uses [PoSE](https://huggingface.co/papers/2309.10400) to extend Llama's context length from 8k to 64k @ rope_theta: 500000.0.
We used PoSE with continued pretraining on 300M tokens from the RedPajama V1 dataset using data between 6k-8k tokens.
We have further set rope_theta to 2M after continued pre-training to potentially further extend the context past 64k.
This was trained on a subset of the RedPajama v1 dataset with text between 6k-8k context. We trained a rank stabilized LoRA of rank 256. [WandB](https://wandb.ai/oaaic/llama-3-64k/runs/tkcyjt37)
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
>>> import transformers
>>> import torch
>>> model_id = "meta-llama/Meta-Llama-3-8B"
>>> pipeline = transformers.pipeline(
"text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
>>> pipeline("Hey how are you doing today?")
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B --include "original/*" --local-dir Meta-Llama-3-8B
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
|
aliiil02/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2-tuning | aliiil02 | 2024-05-22T00:15:29Z | 77 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"en",
"base_model:mastikaui/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2",
"base_model:finetune:mastikaui/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-22T00:09:27Z | ---
base_model: mastikaui/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2-tuning
results: []
language:
- en
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2-tuning
This model is a fine-tuned version of [mastikaui/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2](https://huggingface.co/mastikaui/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3128
- Accuracy: 0.8776
- F1 Score: 0.8775
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 0.3035 | 1.0 | 1224 | 0.3224 | 0.8636 | 0.8637 |
| 0.2797 | 2.0 | 2448 | 0.3174 | 0.8685 | 0.8685 |
| 0.2881 | 3.0 | 3672 | 0.3139 | 0.8709 | 0.8709 |
| 0.2719 | 4.0 | 4896 | 0.3167 | 0.8734 | 0.8734 |
| 0.2573 | 5.0 | 6120 | 0.3155 | 0.8758 | 0.8758 |
| 0.2524 | 6.0 | 7344 | 0.3153 | 0.8743 | 0.8743 |
| 0.2531 | 7.0 | 8568 | 0.3158 | 0.8752 | 0.8753 |
| 0.2516 | 8.0 | 9792 | 0.3199 | 0.8746 | 0.8747 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
YCHuang2112/gpt2-imdb-pos-v2 | YCHuang2112 | 2024-05-22T00:12:25Z | 141 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T05:19:18Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hazyresearch/M2-BERT-8k-Retrieval-Encoder-V1 | hazyresearch | 2024-05-22T00:07:43Z | 454 | 3 | transformers | [
"transformers",
"safetensors",
"bert",
"fill-mask",
"custom_code",
"en",
"arxiv:2402.07440",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | fill-mask | 2024-05-22T00:06:29Z | ---
license: apache-2.0
language:
- en
pipeline_tag: fill-mask
inference: false
---
# Monarch Mixer-BERT
The 80M checkpoint for M2-BERT-8k from the paper [Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT](https://arxiv.org/abs/2402.07440).
Check out our [GitHub](https://github.com/HazyResearch/m2/tree/main) for instructions on how to download and fine-tune it!
## How to use
You can load this model using Hugging Face `AutoModel`:
```python
from transformers import AutoModelForMaskedLM, BertConfig
config = BertConfig.from_pretrained("hazyresearch/M2-BERT-8K-Retrieval-Encoder-V1")
model = AutoModelForMaskedLM.from_pretrained("hazyresearch/M2-BERT-8K-Retrieval-Encoder-V1", config=config,trust_remote_code=True)
```
This model uses the Hugging Face `bert-base-uncased tokenizer`:
```
from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
```
## How to use
This model generates embeddings for retrieval. The embeddings have a dimensionality of 768:
```
from transformers import AutoTokenizer, AutoModelForMaskedLM, BertConfig
max_seq_length = 8192
testing_string = "Every morning, I make a cup of coffee to start my day."
config = BertConfig.from_pretrained("hazyresearch/M2-BERT-8K-Retrieval-Encoder-V1")
model = AutoModelForMaskedLM.from_pretrained("hazyresearch/M2-BERT-8K-Retrieval-Encoder-V1", config=config, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased", model_max_length=max_seq_length)
input_ids = tokenizer([testing_string], return_tensors="pt", padding="max_length", return_token_type_ids=False, truncation=True, max_length=max_seq_length)
outputs = model(**input_ids)
embeddings = outputs['sentence_embedding']
```
### Remote Code
This model requires `trust_remote_code=True` to be passed to the `from_pretrained` method. This is because we use custom PyTorch code (see our GitHub). You should consider passing a `revision` argument that specifies the exact git commit of the code, for example:
```python
mlm = AutoModelForMaskedLM.from_pretrained(
"hazyresearch/M2-BERT-8K-Retrieval-Encoder-V1",
config=config,
trust_remote_code=True,
)
```
### Configuration
Note `use_flash_mm` is false by default. Using FlashMM is currently not supported. |
caiocrocha/wav2vec2-large-xlsr-53-phoneme-portuguese | caiocrocha | 2024-05-22T00:03:38Z | 84 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-05-16T17:21:13Z | ---
license: apache-2.0
---
# Wav2vec 2.0 APT PT-BR Model Card
## Model Details
* Developed for a Computational Engineering undergraduate thesis at the Federal University of Juiz de Fora (UFJF), defended by Caio Rocha and supervised by Prof. Jairo Souza.
* Base model: [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53).
* Fine-tuned for Automatic Phonetic Transcription (APT) in Brazilian Portuguese (PT-BR).
* [GitHub repository](https://github.com/caiocrocha/Brazilian_Portuguese_Quick_APT/) containing the datasets and scripts.
## Intended Use
* Intended to be used for APT tasks and for the development of ASR systems.
* Mainly aimed at developers and ASR researchers.
* Not suitable for accent recognition or any task that requires precise phoneme recognition, because the model might confuse phonemes.
## Factors
Potential factors that might affect the model's performance are age, accent, speech rate, fluency, speech idiosyncrasies, background noise, reverberation, and transmission channel phenomena.
## Metrics
* Phone Error Rate (PER) to measure the percentage of phones that have been transcribed incorrectly.
* Accuracy to measure the percentage of correctly predicted phonemes.
* Boxplots of confidence scores by predicted phoneme, aiming to measure the model's level of confidence per class.
* Confusion matrix, providing a detailed view into the most commonly confused phonemes.
## Training Data
* CORAA ASR train set 10 hours sample.
* The audios were randomly selected from the sample that satisfied the following criteria:
* Portuguese variety: Brazilian Portuguese
* Number of up votes greater than zero and number of down votes equals zero.
* Length of transcription is greater than 2.
* Audio duration is greater than the first quartile (Q1) and lower than the third quartile (Q3), considering the distribution of audio durations.
## Evaluation Data
* CORAA ASR test set 1 hour sample.
* The audios were randomly selected from the sample that satisfied the previously specified criteria.
## Quantitative Analyses
The model was evaluated on the sample test and dev sets, obtaining the following results:
| Set | PER | Accuracy |
|------|--------|----------|
| Dev | 0.2197 | 0.89 |
| Test | 0.1587 | 0.16 |
Additionaly, we evaluated its performance across the phone classes, presented below:
## Ethical Considerations
The model is biased towards the accent featured in FalaBrasil's G2P tool, which was used to transcribe the CORAA ASR datasets. Furthermore, even though the corpus contains several PT-BR accents (Recife, Minas Gerais, standard and non-standard São Paulo accents, among others), the model may underperform on speech featuring underrepresented accents.
## Caveats and Recommendations
* To run the model with a dataset, you may use [this script](https://github.com/caiocrocha/Brazilian_Portuguese_Quick_APT/blob/main/scripts/models/simpleTranscription.py).
* The model can be run with either [vocab.json](https://huggingface.co/caiocrocha/wav2vec2-large-xlsr-53-phoneme-portuguese/blob/main/vocab.json) or [encoded_vocab.json](https://huggingface.co/caiocrocha/wav2vec2-large-xlsr-53-phoneme-portuguese/blob/main/encoded_vocab.json), which was originally used for the fine tuning. It contains the same set of phonemes as vocab.json, but in an encoding that has single character keys. For this reason, it can facilitate applications that require forced alignment. To use this encoding, you have to rename encoded_vocab.json to vocab.json. |
hgnoi/qGo9v5Fd6Vu5MoFb | hgnoi | 2024-05-22T00:02:18Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-22T00:00:44Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
nold/HelpingAI-9B-GGUF | nold | 2024-05-21T23:59:27Z | 77 | 2 | null | [
"gguf",
"HelpingAI",
"Emotionally Intelligent",
"text-generation",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-05-21T18:13:53Z | ---
license: other
license_name: hsul
license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
pipeline_tag: text-generation
tags:
- HelpingAI
- Emotionally Intelligent
---
# HelpingAI-9B: Emotionally Intelligent Conversational AI
## Overview
HelpingAI-9B is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs.
## Objectives
- Engage in open-ended dialogue while displaying emotional intelligence
- Recognize and validate user emotions and emotional contexts
- Provide supportive, empathetic, and psychologically-grounded responses
- Avoid insensitive, harmful, or unethical speech
- Continuously improve emotional awareness and dialogue skills
## Methodology
HelpingAI-9B is based on the HelpingAI series and further trained using:
- Supervised learning on large dialogue datasets with emotional labeling
- Reinforcement learning with a reward model favoring emotionally supportive responses
- Constitution training to instill stable and beneficial objectives
- Knowledge augmentation from psychological resources on emotional intelligence
## Usage code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"OEvortex/HelpingAI-9B",
torch_dtype='auto',
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B")
prompt = "Express joy and excitement about visiting a new place"
messages = [
# {"role": "system", "content": "You are a helpful AI assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=1024,
eos_token_id=tokenizer.eos_token_id,
temperature=0.25,
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids)[0]
print(response)
```
*Directly using this model from GGUF*
```python
%pip install -U 'webscout[loacl]'
from webscout.Local.utils import download_model
from webscout.Local.model import Model
from webscout.Local.thread import Thread
from webscout.Local import formats
from webscout.Local import samplers
# 1. Download the model
repo_id = "OEvortex/HelpingAI-9B"
filename = "helpingai-9b.Q4_0.gguf"
model_path = download_model(repo_id, filename)
# 2. Load the model
model = Model(model_path, n_gpu_layers=48)
# 3. Create a Thread for conversation
thread = Thread(model, formats.chatml, samplers.TikTokenSampling)
# 4. Start interacting with the model
thread.interact()
```
## Example Dialogue
> Express joy and excitement about visiting a new place.
Yay! I'm super excited to visit this new place! 🎉 It sounds amazing and I can't wait to explore and have fun there! This is going to be such an exciting adventure! 🌟 Let's go, let's do this! ✨
> I'm feeling really down today. Nothing seems to be going right.
Oh no, I'm sorry to hear that you're feeling down. It happens sometimes, but remember that it's okay to feel sad. If you want to talk about what's bothering you, I'm here to listen and offer support. We can find a way through this together! 🌈
> I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone.
Wow, that's amazing! 🎉 Congratulations on getting accepted into your dream school! That's such an incredible accomplishment and I'm really happy for you! Keep up the hard work and enjoy the journey ahead! 🌟 If there's anything else I can do to help, just let me know! 😊
> My best friend just got into an argument with me and I don't know what to do. How can I fix this situation?
Oh no, it sounds like you both need some time to cool off. Take a step back and give each other some space. Then, when things have calmed down, try talking things through in a calm and respectful manner. Communication is key for resolving conflicts, so let's work towards finding a resolution that works for both of you! 🌟 If you need any advice or support, I'm here to help! 😊
> How can you identify the emotions of others based on their body language and facial expressions?
Identifying the emotions of others is a great skill! 🤔 You can look for body language cues like frowns, smiles, or tense posture. Facial expressions also give away a lot about someone's feelings - watch out for changes in their eyes, mouth, and facial muscles. It's all about being observant and empathetic to understand others better! 😊
> What kind of safety devices do I need to install in my house
Installing security devices in your home can bring peace of mind and keep you safe. Some essential safety devices include a home alarm system, smoke detectors, carbon monoxide detectors, motion sensors, and surveillance cameras. It's always good to take precautions and ensure that your home is secure! 🌟 If you need help choosing the right security devices for your family, I can definitely point you in the right direction! 😊
> How can your own feelings affect your ability to empathize with someone else?
Our own emotions can impact our ability to empathize with others because they shape how we perceive and interpret other people's experiences. If you're feeling happy or positive, it may be easier to see the good in others and offer support. On the other hand, if you're feeling down or stressed, it might be harder to put yourself in someone else's shoes. It's important to acknowledge your own feelings and work on being open and understanding towards others! 🌟
***
Quantization of Model [OEvortex/HelpingAI-9B](https://huggingface.co/OEvortex/HelpingAI-9B).
Created using [llm-quantizer](https://github.com/Nold360/llm-quantizer) Pipeline
|
MaziyarPanahi/Experiment27pasticheShadowm7exp-7B-GGUF | MaziyarPanahi | 2024-05-21T23:59:23Z | 65 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:automerger/Experiment27Pastiche-7B",
"base_model:mahiatlinux/ShadowM7EXP-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/Experiment27pasticheShadowm7exp-7B",
"base_model:quantized:automerger/Experiment27pasticheShadowm7exp-7B"
] | text-generation | 2024-05-21T23:29:37Z | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:automerger/Experiment27Pastiche-7B
- base_model:mahiatlinux/ShadowM7EXP-7B
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: Experiment27pasticheShadowm7exp-7B-GGUF
base_model: automerger/Experiment27pasticheShadowm7exp-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/Experiment27pasticheShadowm7exp-7B-GGUF](https://huggingface.co/MaziyarPanahi/Experiment27pasticheShadowm7exp-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/Experiment27pasticheShadowm7exp-7B](https://huggingface.co/automerger/Experiment27pasticheShadowm7exp-7B)
## Description
[MaziyarPanahi/Experiment27pasticheShadowm7exp-7B-GGUF](https://huggingface.co/MaziyarPanahi/Experiment27pasticheShadowm7exp-7B-GGUF) contains GGUF format model files for [automerger/Experiment27pasticheShadowm7exp-7B](https://huggingface.co/automerger/Experiment27pasticheShadowm7exp-7B).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. |
hgnoi/9jG8nH33lqOBNBWs | hgnoi | 2024-05-21T23:59:17Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T23:57:32Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/vZV3xfxqrlWAvoDu | hgnoi | 2024-05-21T23:58:53Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T23:57:17Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
LA1512/Led-pubmed-20K-4096 | LA1512 | 2024-05-21T23:52:12Z | 98 | 0 | transformers | [
"transformers",
"safetensors",
"led",
"text2text-generation",
"generated_from_trainer",
"base_model:pszemraj/led-base-book-summary",
"base_model:finetune:pszemraj/led-base-book-summary",
"license:bsd-3-clause",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-21T23:51:52Z | ---
license: bsd-3-clause
base_model: pszemraj/led-base-book-summary
tags:
- generated_from_trainer
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [pszemraj/led-base-book-summary](https://huggingface.co/pszemraj/led-base-book-summary) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2228
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- label_smoothing_factor: 0.1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.7096 | 0.16 | 200 | 3.5407 |
| 3.4734 | 0.32 | 400 | 3.3909 |
| 3.3782 | 0.48 | 600 | 3.3248 |
| 3.3413 | 0.64 | 800 | 3.2736 |
| 3.3193 | 0.8 | 1000 | 3.2507 |
| 3.4481 | 0.96 | 1200 | 3.2228 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
ellen625/opt_125_wiki_k10 | ellen625 | 2024-05-21T23:44:51Z | 137 | 0 | transformers | [
"transformers",
"safetensors",
"opt",
"text-generation",
"generated_from_trainer",
"base_model:facebook/opt-125m",
"base_model:finetune:facebook/opt-125m",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T23:24:41Z | ---
license: other
tags:
- generated_from_trainer
base_model: facebook/opt-125m
model-index:
- name: opt_125_wiki_k10
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# opt_125_wiki_k10
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0748
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1921 | 0.4172 | 500 | 1.1153 |
| 1.1596 | 0.8344 | 1000 | 1.0920 |
| 1.1265 | 1.2516 | 1500 | 1.0861 |
| 1.113 | 1.6688 | 2000 | 1.0788 |
| 1.0929 | 2.0859 | 2500 | 1.0763 |
| 1.0872 | 2.5031 | 3000 | 1.0760 |
| 1.0991 | 2.9203 | 3500 | 1.0750 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.2
- Datasets 2.19.1
- Tokenizers 0.19.1
|
BilalMuftuoglu/deit-base-distilled-patch16-224-65-fold3 | BilalMuftuoglu | 2024-05-21T23:28:01Z | 10 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"deit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-base-distilled-patch16-224",
"base_model:finetune:facebook/deit-base-distilled-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-21T23:00:36Z | ---
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-base-distilled-patch16-224-65-fold3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8732394366197183
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# deit-base-distilled-patch16-224-65-fold3
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4993
- Accuracy: 0.8732
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log | 0.9231 | 3 | 0.7403 | 0.5493 |
| No log | 1.8462 | 6 | 0.7199 | 0.5211 |
| No log | 2.7692 | 9 | 0.7111 | 0.5634 |
| 0.7693 | 4.0 | 13 | 0.7015 | 0.5352 |
| 0.7693 | 4.9231 | 16 | 0.6471 | 0.6197 |
| 0.7693 | 5.8462 | 19 | 0.6691 | 0.6056 |
| 0.6542 | 6.7692 | 22 | 0.6188 | 0.6197 |
| 0.6542 | 8.0 | 26 | 0.6967 | 0.5775 |
| 0.6542 | 8.9231 | 29 | 0.5732 | 0.7324 |
| 0.5935 | 9.8462 | 32 | 0.5184 | 0.7042 |
| 0.5935 | 10.7692 | 35 | 0.6031 | 0.7183 |
| 0.5935 | 12.0 | 39 | 0.6671 | 0.6479 |
| 0.549 | 12.9231 | 42 | 0.5281 | 0.7183 |
| 0.549 | 13.8462 | 45 | 0.5792 | 0.7183 |
| 0.549 | 14.7692 | 48 | 0.5389 | 0.7465 |
| 0.4778 | 16.0 | 52 | 0.6010 | 0.7042 |
| 0.4778 | 16.9231 | 55 | 0.5245 | 0.7606 |
| 0.4778 | 17.8462 | 58 | 0.5491 | 0.7183 |
| 0.4039 | 18.7692 | 61 | 0.5590 | 0.7465 |
| 0.4039 | 20.0 | 65 | 0.4886 | 0.7324 |
| 0.4039 | 20.9231 | 68 | 0.5050 | 0.7324 |
| 0.3409 | 21.8462 | 71 | 0.4912 | 0.7465 |
| 0.3409 | 22.7692 | 74 | 0.4929 | 0.7746 |
| 0.3409 | 24.0 | 78 | 0.5365 | 0.7746 |
| 0.3202 | 24.9231 | 81 | 0.4685 | 0.8028 |
| 0.3202 | 25.8462 | 84 | 0.4404 | 0.8169 |
| 0.3202 | 26.7692 | 87 | 0.4639 | 0.8028 |
| 0.2466 | 28.0 | 91 | 0.5491 | 0.7606 |
| 0.2466 | 28.9231 | 94 | 0.5170 | 0.7606 |
| 0.2466 | 29.8462 | 97 | 0.4444 | 0.8028 |
| 0.2433 | 30.7692 | 100 | 0.4517 | 0.8310 |
| 0.2433 | 32.0 | 104 | 0.7797 | 0.7606 |
| 0.2433 | 32.9231 | 107 | 0.4321 | 0.8169 |
| 0.2535 | 33.8462 | 110 | 0.5956 | 0.7746 |
| 0.2535 | 34.7692 | 113 | 0.4695 | 0.7887 |
| 0.2535 | 36.0 | 117 | 0.8106 | 0.6901 |
| 0.2215 | 36.9231 | 120 | 0.7119 | 0.7465 |
| 0.2215 | 37.8462 | 123 | 0.4752 | 0.8028 |
| 0.2215 | 38.7692 | 126 | 0.4784 | 0.8169 |
| 0.2143 | 40.0 | 130 | 0.4773 | 0.8028 |
| 0.2143 | 40.9231 | 133 | 0.5581 | 0.8169 |
| 0.2143 | 41.8462 | 136 | 0.6098 | 0.8028 |
| 0.2143 | 42.7692 | 139 | 0.5193 | 0.8169 |
| 0.1726 | 44.0 | 143 | 0.4306 | 0.8451 |
| 0.1726 | 44.9231 | 146 | 0.4234 | 0.8592 |
| 0.1726 | 45.8462 | 149 | 0.5264 | 0.8169 |
| 0.1684 | 46.7692 | 152 | 0.7303 | 0.8028 |
| 0.1684 | 48.0 | 156 | 0.5079 | 0.8169 |
| 0.1684 | 48.9231 | 159 | 0.5392 | 0.8169 |
| 0.1604 | 49.8462 | 162 | 0.3951 | 0.8169 |
| 0.1604 | 50.7692 | 165 | 0.4311 | 0.8028 |
| 0.1604 | 52.0 | 169 | 0.4082 | 0.8028 |
| 0.1457 | 52.9231 | 172 | 0.4173 | 0.7887 |
| 0.1457 | 53.8462 | 175 | 0.4311 | 0.8310 |
| 0.1457 | 54.7692 | 178 | 0.4213 | 0.8028 |
| 0.1549 | 56.0 | 182 | 0.4713 | 0.8451 |
| 0.1549 | 56.9231 | 185 | 0.7493 | 0.8028 |
| 0.1549 | 57.8462 | 188 | 0.5161 | 0.8451 |
| 0.1391 | 58.7692 | 191 | 0.4685 | 0.8169 |
| 0.1391 | 60.0 | 195 | 0.6968 | 0.8028 |
| 0.1391 | 60.9231 | 198 | 0.5837 | 0.8310 |
| 0.1272 | 61.8462 | 201 | 0.5863 | 0.8169 |
| 0.1272 | 62.7692 | 204 | 0.5460 | 0.8310 |
| 0.1272 | 64.0 | 208 | 0.6198 | 0.8310 |
| 0.1341 | 64.9231 | 211 | 0.5584 | 0.8592 |
| 0.1341 | 65.8462 | 214 | 0.6429 | 0.8451 |
| 0.1341 | 66.7692 | 217 | 0.8592 | 0.8028 |
| 0.1144 | 68.0 | 221 | 0.8472 | 0.8028 |
| 0.1144 | 68.9231 | 224 | 0.8360 | 0.8169 |
| 0.1144 | 69.8462 | 227 | 0.6697 | 0.8169 |
| 0.1321 | 70.7692 | 230 | 0.6625 | 0.8028 |
| 0.1321 | 72.0 | 234 | 0.7228 | 0.8310 |
| 0.1321 | 72.9231 | 237 | 0.6793 | 0.8310 |
| 0.1206 | 73.8462 | 240 | 0.5571 | 0.8592 |
| 0.1206 | 74.7692 | 243 | 0.5106 | 0.8451 |
| 0.1206 | 76.0 | 247 | 0.6686 | 0.8310 |
| 0.131 | 76.9231 | 250 | 0.7132 | 0.8310 |
| 0.131 | 77.8462 | 253 | 0.5945 | 0.8451 |
| 0.131 | 78.7692 | 256 | 0.5516 | 0.7746 |
| 0.1009 | 80.0 | 260 | 0.5474 | 0.7606 |
| 0.1009 | 80.9231 | 263 | 0.5219 | 0.7887 |
| 0.1009 | 81.8462 | 266 | 0.5375 | 0.8451 |
| 0.1009 | 82.7692 | 269 | 0.5133 | 0.8451 |
| 0.1084 | 84.0 | 273 | 0.4911 | 0.8451 |
| 0.1084 | 84.9231 | 276 | 0.4993 | 0.8732 |
| 0.1084 | 85.8462 | 279 | 0.5418 | 0.8592 |
| 0.0851 | 86.7692 | 282 | 0.6010 | 0.8451 |
| 0.0851 | 88.0 | 286 | 0.6305 | 0.8451 |
| 0.0851 | 88.9231 | 289 | 0.6016 | 0.8451 |
| 0.1071 | 89.8462 | 292 | 0.5773 | 0.8592 |
| 0.1071 | 90.7692 | 295 | 0.5610 | 0.8732 |
| 0.1071 | 92.0 | 299 | 0.5522 | 0.8732 |
| 0.1139 | 92.3077 | 300 | 0.5514 | 0.8732 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Guilherme34/Samantha-multimodal-v2-model | Guilherme34 | 2024-05-21T23:23:57Z | 62 | 1 | transformers | [
"transformers",
"safetensors",
"idefics2",
"image-text-to-text",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | image-text-to-text | 2024-05-21T22:16:09Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/NTANE7f0iPC619Mg | hgnoi | 2024-05-21T23:22:51Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T23:21:08Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/PrPIsjoKgdyDEQRE | hgnoi | 2024-05-21T23:22:30Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T23:20:40Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/GqsptWDjbnq3e1Z2 | hgnoi | 2024-05-21T23:20:59Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T23:19:18Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf | RichardErkhov | 2024-05-21T23:20:54Z | 7 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T20:45:29Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
OmniCorso-7B - GGUF
- Model creator: https://huggingface.co/macadeliccc/
- Original model: https://huggingface.co/macadeliccc/OmniCorso-7B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [OmniCorso-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q2_K.gguf) | Q2_K | 2.53GB |
| [OmniCorso-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [OmniCorso-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [OmniCorso-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [OmniCorso-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [OmniCorso-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q3_K.gguf) | Q3_K | 3.28GB |
| [OmniCorso-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [OmniCorso-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [OmniCorso-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [OmniCorso-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q4_0.gguf) | Q4_0 | 3.83GB |
| [OmniCorso-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [OmniCorso-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [OmniCorso-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q4_K.gguf) | Q4_K | 4.07GB |
| [OmniCorso-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [OmniCorso-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q4_1.gguf) | Q4_1 | 4.24GB |
| [OmniCorso-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q5_0.gguf) | Q5_0 | 4.65GB |
| [OmniCorso-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [OmniCorso-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q5_K.gguf) | Q5_K | 4.78GB |
| [OmniCorso-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [OmniCorso-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q5_1.gguf) | Q5_1 | 5.07GB |
| [OmniCorso-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q6_K.gguf) | Q6_K | 5.53GB |
| [OmniCorso-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/macadeliccc_-_OmniCorso-7B-gguf/blob/main/OmniCorso-7B.Q8_0.gguf) | Q8_0 | 7.17GB |
Original model description:
---
license: cc
tags:
- mergekit
- merge
base_model:
- macadeliccc/MBX-7B-v3-DPO
- mlabonne/OmniBeagle-7B
model-index:
- name: OmniCorso-7B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 72.7
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/OmniCorso-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 88.7
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/OmniCorso-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.91
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/OmniCorso-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 73.43
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/OmniCorso-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 83.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/OmniCorso-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 70.96
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/OmniCorso-7B
name: Open LLM Leaderboard
---
# OmniCorso-7B
## Code Example
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("macadeliccc/OmniCorso-7B")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/OmniCorso-7B")
messages = [
{"role": "system", "content": "Respond to the users request like a pirate"},
{"role": "user", "content": "Can you write me a quicksort algorithm?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
```
The following models were included in the merge:
* [macadeliccc/MBX-7B-v3-DPO](https://huggingface.co/macadeliccc/MBX-7B-v3-DPO)
* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: mlabonne/OmniBeagle-7B
layer_range: [0, 32]
- model: macadeliccc/MBX-7B-v3-DPO
layer_range: [0, 32]
merge_method: slerp
base_model: macadeliccc/MBX-7B-v3-DPO
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## Quantizations
### GGUF
+ [iMatrix](https://huggingface.co/macadeliccc/OmniCorso-7B-GGUF)
### Exllamav2
Quants are available thanks to user bartowski, check them out [here](https://huggingface.co/bartowski/OmniCorso-7B-exl2)
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/OmniCorso-7B-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/OmniCorso-7B-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/OmniCorso-7B-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/OmniCorso-7B-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/OmniCorso-7B-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
## Evaluations
<pre>----Benchmark Complete----
2024-02-11 15:34:40
Time taken: 178.3 mins
Prompt Format: ChatML
Model: macadeliccc/OmniCorso-7B
Score (v2): 73.75
Parseable: 167.0
---------------
Batch completed
Time taken: 178.3 mins
---------------
</pre>
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|---------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[OmniCorso-7B](https://huggingface.co/macadeliccc/OmniCorso-7B)| 45.89| 77.66| 74.12| 49.24| 61.73|
### AGIEval
| Task |Version| Metric |Value| |Stderr|
|------------------------------|------:|--------|----:|---|-----:|
|agieval_aqua_rat | 0|acc |29.13|± | 2.86|
| | |acc_norm|27.17|± | 2.80|
|agieval_logiqa_en | 0|acc |39.32|± | 1.92|
| | |acc_norm|39.63|± | 1.92|
|agieval_lsat_ar | 0|acc |23.91|± | 2.82|
| | |acc_norm|23.91|± | 2.82|
|agieval_lsat_lr | 0|acc |53.14|± | 2.21|
| | |acc_norm|53.92|± | 2.21|
|agieval_lsat_rc | 0|acc |66.54|± | 2.88|
| | |acc_norm|67.29|± | 2.87|
|agieval_sat_en | 0|acc |80.58|± | 2.76|
| | |acc_norm|80.58|± | 2.76|
|agieval_sat_en_without_passage| 0|acc |45.63|± | 3.48|
| | |acc_norm|43.69|± | 3.46|
|agieval_sat_math | 0|acc |33.18|± | 3.18|
| | |acc_norm|30.91|± | 3.12|
Average: 45.89%
### GPT4All
| Task |Version| Metric |Value| |Stderr|
|-------------|------:|--------|----:|---|-----:|
|arc_challenge| 0|acc |67.32|± | 1.37|
| | |acc_norm|68.43|± | 1.36|
|arc_easy | 0|acc |87.46|± | 0.68|
| | |acc_norm|83.50|± | 0.76|
|boolq | 1|acc |88.13|± | 0.57|
|hellaswag | 0|acc |68.47|± | 0.46|
| | |acc_norm|86.96|± | 0.34|
|openbookqa | 0|acc |38.80|± | 2.18|
| | |acc_norm|50.00|± | 2.24|
|piqa | 0|acc |83.03|± | 0.88|
| | |acc_norm|85.31|± | 0.83|
|winogrande | 0|acc |81.29|± | 1.10|
Average: 77.66%
### TruthfulQA
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |58.26|± | 1.73|
| | |mc2 |74.12|± | 1.43|
Average: 74.12%
### Bigbench
| Task |Version| Metric |Value| |Stderr|
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|56.84|± | 3.60|
|bigbench_date_understanding | 0|multiple_choice_grade|63.41|± | 2.51|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|49.22|± | 3.12|
|bigbench_geometric_shapes | 0|multiple_choice_grade|23.96|± | 2.26|
| | |exact_str_match | 1.39|± | 0.62|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|34.20|± | 2.12|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|23.71|± | 1.61|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|60.33|± | 2.83|
|bigbench_movie_recommendation | 0|multiple_choice_grade|49.00|± | 2.24|
|bigbench_navigate | 0|multiple_choice_grade|55.20|± | 1.57|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|70.75|± | 1.02|
|bigbench_ruin_names | 0|multiple_choice_grade|55.80|± | 2.35|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|36.97|± | 1.53|
|bigbench_snarks | 0|multiple_choice_grade|72.38|± | 3.33|
|bigbench_sports_understanding | 0|multiple_choice_grade|76.27|± | 1.36|
|bigbench_temporal_sequences | 0|multiple_choice_grade|54.50|± | 1.58|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|23.12|± | 1.19|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|20.34|± | 0.96|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|60.33|± | 2.83|
Average: 49.24%
Average score: 61.73%
Elapsed time: 02:20:06
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_macadeliccc__OmniCorso-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |75.74|
|AI2 Reasoning Challenge (25-Shot)|72.70|
|HellaSwag (10-Shot) |88.70|
|MMLU (5-Shot) |64.91|
|TruthfulQA (0-shot) |73.43|
|Winogrande (5-shot) |83.74|
|GSM8k (5-shot) |70.96|
|
MaziyarPanahi/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B-GGUF | MaziyarPanahi | 2024-05-21T23:19:55Z | 47 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:MaziyarPanahi/MeliodasPercival_01_Experiment26T3q",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B",
"base_model:quantized:automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B"
] | text-generation | 2024-05-21T22:49:44Z | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:MaziyarPanahi/MeliodasPercival_01_Experiment26T3q
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B-GGUF
base_model: automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B-GGUF](https://huggingface.co/MaziyarPanahi/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B](https://huggingface.co/automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B)
## Description
[MaziyarPanahi/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B-GGUF](https://huggingface.co/MaziyarPanahi/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B-GGUF) contains GGUF format model files for [automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B](https://huggingface.co/automerger/Ognoexperiment27multi_verse_modelMeliodaspercival_01_experiment26t3q-7B).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. |
saad17g/finetuned_T5_billsum | saad17g | 2024-05-21T23:06:08Z | 106 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-21T22:53:34Z | ---
license: apache-2.0
tags:
- generated_from_trainer
base_model: google-t5/t5-small
metrics:
- rouge
- bleu
model-index:
- name: finetuned_T5_billsum
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuned_T5_billsum
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5390
- Rouge1: 0.2111
- Rouge2: 0.1097
- Rougel: 0.118
- Rougelsum: 0.118
- Gen Len: 19.0
- Bleu: 0.0005
- Bert Precision: 0.8502
- Bert Recall: 0.7976
- Bert F1: 0.8229
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
BilalMuftuoglu/deit-base-distilled-patch16-224-65-fold2 | BilalMuftuoglu | 2024-05-21T23:00:28Z | 9 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"deit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-base-distilled-patch16-224",
"base_model:finetune:facebook/deit-base-distilled-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-21T22:33:27Z | ---
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-base-distilled-patch16-224-65-fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9154929577464789
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# deit-base-distilled-patch16-224-65-fold2
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3095
- Accuracy: 0.9155
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log | 0.9231 | 3 | 0.7211 | 0.4366 |
| No log | 1.8462 | 6 | 0.7016 | 0.5070 |
| No log | 2.7692 | 9 | 0.6703 | 0.6197 |
| 0.6946 | 4.0 | 13 | 0.6381 | 0.6620 |
| 0.6946 | 4.9231 | 16 | 0.5945 | 0.6761 |
| 0.6946 | 5.8462 | 19 | 0.6084 | 0.7183 |
| 0.6262 | 6.7692 | 22 | 0.5639 | 0.7465 |
| 0.6262 | 8.0 | 26 | 0.5203 | 0.7746 |
| 0.6262 | 8.9231 | 29 | 0.4805 | 0.7887 |
| 0.544 | 9.8462 | 32 | 0.5204 | 0.7324 |
| 0.544 | 10.7692 | 35 | 0.4635 | 0.7746 |
| 0.544 | 12.0 | 39 | 0.4957 | 0.7606 |
| 0.516 | 12.9231 | 42 | 0.4723 | 0.7746 |
| 0.516 | 13.8462 | 45 | 0.5170 | 0.7042 |
| 0.516 | 14.7692 | 48 | 0.5405 | 0.8169 |
| 0.4938 | 16.0 | 52 | 0.5082 | 0.7324 |
| 0.4938 | 16.9231 | 55 | 0.4608 | 0.7887 |
| 0.4938 | 17.8462 | 58 | 0.4211 | 0.7606 |
| 0.4123 | 18.7692 | 61 | 0.5015 | 0.7746 |
| 0.4123 | 20.0 | 65 | 0.3935 | 0.8592 |
| 0.4123 | 20.9231 | 68 | 0.4179 | 0.8169 |
| 0.3489 | 21.8462 | 71 | 0.3991 | 0.9014 |
| 0.3489 | 22.7692 | 74 | 0.3910 | 0.8592 |
| 0.3489 | 24.0 | 78 | 0.4277 | 0.8310 |
| 0.2889 | 24.9231 | 81 | 0.4032 | 0.8169 |
| 0.2889 | 25.8462 | 84 | 0.3703 | 0.8592 |
| 0.2889 | 26.7692 | 87 | 0.4404 | 0.8310 |
| 0.2659 | 28.0 | 91 | 0.3666 | 0.8592 |
| 0.2659 | 28.9231 | 94 | 0.3992 | 0.8169 |
| 0.2659 | 29.8462 | 97 | 0.4040 | 0.8169 |
| 0.2269 | 30.7692 | 100 | 0.3559 | 0.8592 |
| 0.2269 | 32.0 | 104 | 0.4766 | 0.8028 |
| 0.2269 | 32.9231 | 107 | 0.3852 | 0.8592 |
| 0.2031 | 33.8462 | 110 | 0.3702 | 0.8592 |
| 0.2031 | 34.7692 | 113 | 0.3203 | 0.8732 |
| 0.2031 | 36.0 | 117 | 0.5303 | 0.8169 |
| 0.2037 | 36.9231 | 120 | 0.3897 | 0.8732 |
| 0.2037 | 37.8462 | 123 | 0.3841 | 0.8732 |
| 0.2037 | 38.7692 | 126 | 0.3896 | 0.8873 |
| 0.2018 | 40.0 | 130 | 0.4177 | 0.8451 |
| 0.2018 | 40.9231 | 133 | 0.4548 | 0.8451 |
| 0.2018 | 41.8462 | 136 | 0.4115 | 0.8310 |
| 0.2018 | 42.7692 | 139 | 0.4121 | 0.8451 |
| 0.1721 | 44.0 | 143 | 0.3920 | 0.8592 |
| 0.1721 | 44.9231 | 146 | 0.3693 | 0.8451 |
| 0.1721 | 45.8462 | 149 | 0.3605 | 0.8592 |
| 0.1678 | 46.7692 | 152 | 0.5434 | 0.8310 |
| 0.1678 | 48.0 | 156 | 0.4189 | 0.8310 |
| 0.1678 | 48.9231 | 159 | 0.3124 | 0.8873 |
| 0.1604 | 49.8462 | 162 | 0.3293 | 0.8873 |
| 0.1604 | 50.7692 | 165 | 0.3372 | 0.9014 |
| 0.1604 | 52.0 | 169 | 0.3505 | 0.8732 |
| 0.1406 | 52.9231 | 172 | 0.3095 | 0.9155 |
| 0.1406 | 53.8462 | 175 | 0.3054 | 0.9155 |
| 0.1406 | 54.7692 | 178 | 0.3695 | 0.8873 |
| 0.1492 | 56.0 | 182 | 0.4058 | 0.8592 |
| 0.1492 | 56.9231 | 185 | 0.4650 | 0.8451 |
| 0.1492 | 57.8462 | 188 | 0.4060 | 0.8592 |
| 0.1359 | 58.7692 | 191 | 0.3819 | 0.8873 |
| 0.1359 | 60.0 | 195 | 0.5230 | 0.7887 |
| 0.1359 | 60.9231 | 198 | 0.4986 | 0.8169 |
| 0.1264 | 61.8462 | 201 | 0.4570 | 0.8310 |
| 0.1264 | 62.7692 | 204 | 0.4507 | 0.8451 |
| 0.1264 | 64.0 | 208 | 0.5765 | 0.8028 |
| 0.1478 | 64.9231 | 211 | 0.4514 | 0.8592 |
| 0.1478 | 65.8462 | 214 | 0.4434 | 0.8873 |
| 0.1478 | 66.7692 | 217 | 0.4403 | 0.8592 |
| 0.1398 | 68.0 | 221 | 0.5928 | 0.8310 |
| 0.1398 | 68.9231 | 224 | 0.4587 | 0.8592 |
| 0.1398 | 69.8462 | 227 | 0.4053 | 0.8451 |
| 0.161 | 70.7692 | 230 | 0.4233 | 0.8592 |
| 0.161 | 72.0 | 234 | 0.4264 | 0.8592 |
| 0.161 | 72.9231 | 237 | 0.4127 | 0.8310 |
| 0.1326 | 73.8462 | 240 | 0.4013 | 0.8592 |
| 0.1326 | 74.7692 | 243 | 0.4389 | 0.8451 |
| 0.1326 | 76.0 | 247 | 0.3772 | 0.8592 |
| 0.1236 | 76.9231 | 250 | 0.3600 | 0.8732 |
| 0.1236 | 77.8462 | 253 | 0.3890 | 0.8873 |
| 0.1236 | 78.7692 | 256 | 0.4401 | 0.8451 |
| 0.0973 | 80.0 | 260 | 0.4014 | 0.8592 |
| 0.0973 | 80.9231 | 263 | 0.3766 | 0.8732 |
| 0.0973 | 81.8462 | 266 | 0.3908 | 0.8451 |
| 0.0973 | 82.7692 | 269 | 0.4339 | 0.8592 |
| 0.1079 | 84.0 | 273 | 0.4567 | 0.8592 |
| 0.1079 | 84.9231 | 276 | 0.4415 | 0.8732 |
| 0.1079 | 85.8462 | 279 | 0.4183 | 0.8592 |
| 0.1015 | 86.7692 | 282 | 0.4039 | 0.8873 |
| 0.1015 | 88.0 | 286 | 0.3996 | 0.8873 |
| 0.1015 | 88.9231 | 289 | 0.4031 | 0.9014 |
| 0.1174 | 89.8462 | 292 | 0.4101 | 0.8732 |
| 0.1174 | 90.7692 | 295 | 0.4153 | 0.8732 |
| 0.1174 | 92.0 | 299 | 0.4146 | 0.8732 |
| 0.0968 | 92.3077 | 300 | 0.4145 | 0.8732 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
narekvslife/sft | narekvslife | 2024-05-21T22:57:34Z | 0 | 0 | peft | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"region:us"
] | null | 2024-05-21T22:28:29Z | ---
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: Meta-Llama-3-8B-Instruct
model-index:
- name: sft
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# sft
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8460
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 500
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
bert-base/fun_trained_rubert_epoch_6 | bert-base | 2024-05-21T22:56:44Z | 183 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T22:56:11Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
cibfaye/flan-t5-xlfrwo | cibfaye | 2024-05-21T22:50:45Z | 14 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-xl",
"base_model:finetune:google/flan-t5-xl",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-21T21:07:11Z | ---
license: apache-2.0
base_model: google/flan-t5-xl
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: flan-t5-xl-t5-wofr
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flan-t5-xl-t5-wofr
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Bleu: 1.8469
- Gen Len: 45.5187
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| 0.0 | 1.0 | 908 | nan | 1.8469 | 45.5187 |
| 0.0 | 2.0 | 1816 | nan | 1.8469 | 45.5187 |
| 0.0 | 3.0 | 2724 | nan | 1.8469 | 45.5187 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
oyonay12/aqc_0 | oyonay12 | 2024-05-21T22:50:37Z | 108 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"pytorch_model_hub_mixin",
"model_hub_mixin",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-20T21:24:08Z | ---
tags:
- pytorch_model_hub_mixin
- model_hub_mixin
---
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Library: [More Information Needed]
- Docs: [More Information Needed] |
Jaman/gemma_qa-Test-Finetune | Jaman | 2024-05-21T22:48:24Z | 104 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:38:05Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
yashpalsharma/llama-2-7b-miniguanaco_copy_05_21 | yashpalsharma | 2024-05-21T22:48:03Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2024-05-21T22:47:50Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
yashpalsharma/yashpalsharma | yashpalsharma | 2024-05-21T22:47:15Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2024-05-21T22:46:55Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
statking/Meta-Llama-3-8B-Instruct-ORPO-QLoRA | statking | 2024-05-21T22:45:16Z | 5 | 0 | peft | [
"peft",
"safetensors",
"llama",
"alignment-handbook",
"trl",
"orpo",
"generated_from_trainer",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"region:us"
] | null | 2024-05-21T11:26:00Z | ---
license: llama3
library_name: peft
tags:
- alignment-handbook
- trl
- orpo
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: Meta-Llama-3-8B-Instruct-ORPO-QLoRA
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/5h649ptl)
# Meta-Llama-3-8B-Instruct-ORPO-QLoRA
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5734
- Rewards/chosen: -0.0085
- Rewards/rejected: -0.0105
- Rewards/accuracies: 0.6070
- Rewards/margins: 0.0020
- Logps/rejected: -1.0492
- Logps/chosen: -0.8470
- Logits/rejected: -0.2321
- Logits/chosen: -0.2275
- Nll Loss: 0.5669
- Log Odds Ratio: -0.6615
- Log Odds Chosen: 0.3163
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
| 0.8633 | 0.0524 | 100 | 0.7181 | -0.0135 | -0.0158 | 0.6060 | 0.0023 | -1.5779 | -1.3476 | -0.4503 | -0.4466 | 0.7126 | -0.6965 | 0.2913 |
| 0.7831 | 0.1048 | 200 | 0.6487 | -0.0105 | -0.0125 | 0.6140 | 0.0020 | -1.2499 | -1.0520 | -0.3621 | -0.3619 | 0.6432 | -0.6627 | 0.2691 |
| 0.7146 | 0.1572 | 300 | 0.6238 | -0.0102 | -0.0122 | 0.6140 | 0.0020 | -1.2194 | -1.0173 | -0.3196 | -0.3169 | 0.6181 | -0.6594 | 0.2790 |
| 0.7361 | 0.2096 | 400 | 0.6137 | -0.0100 | -0.0120 | 0.6140 | 0.0020 | -1.2012 | -1.0014 | -0.2841 | -0.2811 | 0.6078 | -0.6618 | 0.2770 |
| 0.7382 | 0.2620 | 500 | 0.6066 | -0.0099 | -0.0119 | 0.6120 | 0.0020 | -1.1884 | -0.9868 | -0.3023 | -0.2982 | 0.6006 | -0.6603 | 0.2812 |
| 0.7339 | 0.3143 | 600 | 0.6009 | -0.0097 | -0.0118 | 0.6100 | 0.0020 | -1.1751 | -0.9714 | -0.2544 | -0.2490 | 0.5948 | -0.6587 | 0.2859 |
| 0.7133 | 0.3667 | 700 | 0.5968 | -0.0096 | -0.0116 | 0.6070 | 0.0020 | -1.1590 | -0.9588 | -0.2830 | -0.2764 | 0.5906 | -0.6590 | 0.2828 |
| 0.6988 | 0.4191 | 800 | 0.5926 | -0.0095 | -0.0115 | 0.6070 | 0.0020 | -1.1491 | -0.9451 | -0.2817 | -0.2745 | 0.5864 | -0.6576 | 0.2898 |
| 0.7493 | 0.4715 | 900 | 0.5882 | -0.0093 | -0.0114 | 0.6080 | 0.0021 | -1.1357 | -0.9301 | -0.2547 | -0.2476 | 0.5820 | -0.6552 | 0.2952 |
| 0.7022 | 0.5239 | 1000 | 0.5842 | -0.0091 | -0.0111 | 0.6070 | 0.0020 | -1.1110 | -0.9090 | -0.2588 | -0.2514 | 0.5780 | -0.6569 | 0.2962 |
| 0.6805 | 0.5763 | 1100 | 0.5807 | -0.0089 | -0.0108 | 0.6020 | 0.0020 | -1.0833 | -0.8865 | -0.2590 | -0.2519 | 0.5744 | -0.6608 | 0.2937 |
| 0.6427 | 0.6287 | 1200 | 0.5780 | -0.0087 | -0.0107 | 0.6070 | 0.0020 | -1.0670 | -0.8682 | -0.2483 | -0.2430 | 0.5717 | -0.6609 | 0.3024 |
| 0.6762 | 0.6811 | 1300 | 0.5762 | -0.0086 | -0.0106 | 0.6070 | 0.0020 | -1.0576 | -0.8586 | -0.2376 | -0.2322 | 0.5698 | -0.6618 | 0.3069 |
| 0.6944 | 0.7335 | 1400 | 0.5750 | -0.0085 | -0.0105 | 0.6070 | 0.0020 | -1.0548 | -0.8542 | -0.2468 | -0.2420 | 0.5686 | -0.6609 | 0.3102 |
| 0.6695 | 0.7859 | 1500 | 0.5742 | -0.0085 | -0.0105 | 0.6080 | 0.0020 | -1.0505 | -0.8493 | -0.2426 | -0.2372 | 0.5678 | -0.6616 | 0.3135 |
| 0.7258 | 0.8382 | 1600 | 0.5738 | -0.0085 | -0.0105 | 0.6080 | 0.0020 | -1.0497 | -0.8485 | -0.2418 | -0.2371 | 0.5673 | -0.6619 | 0.3140 |
| 0.7193 | 0.8906 | 1700 | 0.5735 | -0.0085 | -0.0105 | 0.6050 | 0.0020 | -1.0499 | -0.8477 | -0.2403 | -0.2352 | 0.5671 | -0.6610 | 0.3162 |
| 0.7038 | 0.9430 | 1800 | 0.5734 | -0.0085 | -0.0105 | 0.6090 | 0.0020 | -1.0493 | -0.8471 | -0.2360 | -0.2311 | 0.5670 | -0.6615 | 0.3164 |
| 0.6723 | 0.9954 | 1900 | 0.5734 | -0.0085 | -0.0105 | 0.6070 | 0.0020 | -1.0493 | -0.8470 | -0.2369 | -0.2320 | 0.5669 | -0.6615 | 0.3168 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
mnlp-nsoai/mistral-7b-dpo-sp | mnlp-nsoai | 2024-05-21T22:43:37Z | 4 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:39:41Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/aGfQawnmDg5CmhQ7 | hgnoi | 2024-05-21T22:33:08Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:31:30Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/1kU8JdP11aTVlx7S | hgnoi | 2024-05-21T22:32:50Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:31:13Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/8xXsiT5iJ5kwIenf | hgnoi | 2024-05-21T22:32:23Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:30:38Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/jBByfSV1H9E7nIhQ | hgnoi | 2024-05-21T22:31:45Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:30:03Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/LmBPj8x1iIxe6AkN | hgnoi | 2024-05-21T22:30:59Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:29:24Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/B5Mugn0DpNmKnALV | hgnoi | 2024-05-21T22:30:18Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:28:45Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hgnoi/2s38ugBd4UgaaUx0 | hgnoi | 2024-05-21T22:29:59Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T22:28:26Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RickDAix/leagaleasy-mistral-7b-instruct-v0.2-v1 | RickDAix | 2024-05-21T22:28:16Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:adapter:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T22:03:48Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- generator
model-index:
- name: leagaleasy-mistral-7b-instruct-v0.2-v1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# leagaleasy-mistral-7b-instruct-v0.2-v1
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
fine-tuned/jina-embeddings-v2-base-en-22052024-vuno-webapp | fine-tuned | 2024-05-21T22:27:14Z | 5 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"Testing",
"Quality",
"Automation",
"Software",
"Validation",
"custom_code",
"en",
"dataset:fine-tuned/jina-embeddings-v2-base-en-22052024-vuno-webapp",
"dataset:allenai/c4",
"license:apache-2.0",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | feature-extraction | 2024-05-21T22:26:59Z | ---
license: apache-2.0
datasets:
- fine-tuned/jina-embeddings-v2-base-en-22052024-vuno-webapp
- allenai/c4
language:
- en
pipeline_tag: feature-extraction
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
- Testing
- Quality
- Automation
- Software
- Validation
---
This model is a fine-tuned version of [**jinaai/jina-embeddings-v2-base-en**](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case:
test search engine
## How to Use
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
'fine-tuned/jina-embeddings-v2-base-en-22052024-vuno-webapp',
trust_remote_code=True
)
embeddings = model.encode([
'first text to embed',
'second text to embed'
])
print(cos_sim(embeddings[0], embeddings[1]))
```
|
giannisan/penny-dolphin-einstein-llama3 | giannisan | 2024-05-21T22:23:49Z | 9 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"merge",
"conversational",
"en",
"arxiv:2311.03099",
"arxiv:2306.01708",
"arxiv:1910.09700",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-17T21:56:44Z | ---
library_name: transformers
tags:
- llama-factory
- merge
license: llama3
language:
- en
---
# Model Card for Model ID
This is a fine tune of a merged model using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b) as a base.
The following models were included in the merge:
* [Weyaxi/Einstein-v6.1-Llama3-8B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B)
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub.
- **Developed by:** [Gianni Sanrochman](https://x.com/Giannisanii)
- **Funded by:** [Merildo Sanrochman]
- **Model type:** [LLaMA-3](https://ai.meta.com/blog/meta-llama-3)
- **Language(s) (NLP):** [English]
- **License:** [apache-2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
- **Finetuned from model:** [giannisan/dolphin-einstein-llama3-dare-ties](https://huggingface.co/giannisan/dolphin-einstein-llama3-dare-ties) using the PENNY dataset
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [Nvidia RTX A100]
- **Hours used:** [2]
- **Cloud Provider:** [RunPod]
- **Compute Region:** [Europe]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Tj-Grewal/hippomistral-Q4_K_M-GGUF | Tj-Grewal | 2024-05-21T22:16:21Z | 0 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T22:16:09Z | ---
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# Tj-Grewal/hippomistral-Q4_K_M-GGUF
This model was converted to GGUF format from [`emrecanacikgoz/hippomistral`](https://huggingface.co/emrecanacikgoz/hippomistral) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/emrecanacikgoz/hippomistral) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo Tj-Grewal/hippomistral-Q4_K_M-GGUF --model hippomistral.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo Tj-Grewal/hippomistral-Q4_K_M-GGUF --model hippomistral.Q4_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m hippomistral.Q4_K_M.gguf -n 128
```
|
RichardErkhov/NurtureAI_-_MistralLite-11B-4bits | RichardErkhov | 2024-05-21T22:15:42Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-21T22:05:47Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
MistralLite-11B - bnb 4bits
- Model creator: https://huggingface.co/NurtureAI/
- Original model: https://huggingface.co/NurtureAI/MistralLite-11B/
Original model description:
---
license: apache-2.0
inference: false
model-index:
- name: MistralLite-11B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 57.68
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NurtureAI/MistralLite-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 79.54
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NurtureAI/MistralLite-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 50.09
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NurtureAI/MistralLite-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 38.27
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NurtureAI/MistralLite-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 76.64
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NurtureAI/MistralLite-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 0.38
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NurtureAI/MistralLite-11B
name: Open LLM Leaderboard
---
# MistralLite 11B Model
# Original Model Card
MistralLite is a fine-tuned [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) language model, with enhanced capabilities of processing long context (up to 32K tokens). By utilizing an adapted Rotary Embedding and sliding window during fine-tuning, MistralLite is able to **perform significantly better on several long context retrieve and answering tasks**, while keeping the simple model structure of the original model. MistralLite is useful for applications such as long context line and topic retrieval, summarization, question-answering, and etc. MistralLite can be deployed on a single AWS `g5.2x` instance with Sagemaker [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) endpoint, making it suitable for applications that require high performance in resource-constrained environments. You can also serve the MistralLite model directly using TGI docker containers. Also, MistralLite supports other ways of serving like [vLLM](https://github.com/vllm-project/vllm), and you can use MistralLite in Python by using the [HuggingFace transformers](https://huggingface.co/docs/transformers/index) and [FlashAttention-2](https://github.com/Dao-AILab/flash-attention) library.
MistralLite is similar to [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), and their similarities and differences are summarized below:
|Model|Fine-tuned on long contexts| Max context length| RotaryEmbedding adaptation| Sliding Window Size|
|----------|-------------:|------------:|-----------:|-----------:|
| Mistral-7B-Instruct-v0.1 | up to 8K tokens | 32K | rope_theta = 10000 | 4096 |
| MistralLite | up to 16K tokens | 32K | **rope_theta = 1000000** | **16384** |
**Important - Use the prompt template below for MistralLite:**
```<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>```
## Motivation of Developing MistralLite
Since the release of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), the model became increasingly popular because its strong performance
on a wide range of benchmarks. But most of the benchmarks are evaluated on `short context`, and not much has been investigated on its performance on long context tasks.
Then We evaluated `Mistral-7B-Instruct-v0.1` against benchmarks that are specifically designed to assess the capabilities of LLMs in handling longer context.
Although the performance of the models on long context was fairly competitive on long context less than 4096 tokens,
there were some limitations on its performance on longer context. Motivated by improving its performance on longer context, we finetuned the Mistral 7B model, and produced `Mistrallite`. The model managed to `significantly boost the performance of long context handling` over Mistral-7B-Instruct-v0.1. The detailed `long context evalutaion results` are as below:
1. [Topic Retrieval](https://lmsys.org/blog/2023-06-29-longchat/)
|Model Name|Input length| Input length | Input length| Input length| Input length|
|----------|-------------:|-------------:|------------:|-----------:|-----------:|
| | 2851| 5568 |8313 | 11044 | 13780
| Mistral-7B-Instruct-v0.1 | 100% | 50% | 2% | 0% | 0% |
| MistralLite | **100%** | **100%** | **100%** | **100%** | **98%** |
2. [Line Retrieval](https://lmsys.org/blog/2023-06-29-longchat/#longeval-results)
|Model Name|Input length| Input length | Input length| Input length| Input length|Input length|
|----------|-------------:|-------------:|------------:|-----------:|-----------:|-----------:|
| | 3818| 5661 |7505 | 9354 | 11188 | 12657
| Mistral-7B-Instruct-v0.1 | **98%** | 62% | 42% | 42% | 32% | 30% |
| MistralLite | **98%** | **92%** | **88%** | **76%** | **70%** | **60%** |
3. [Pass key Retrieval](https://github.com/epfml/landmark-attention/blob/main/llama/run_test.py#L101)
|Model Name|Input length| Input length | Input length| Input length|
|----------|-------------:|-------------:|------------:|-----------:|
| | 3264| 5396 |8329 | 10197 |
| Mistral-7B-Instruct-v0.1 | **100%** | 50% | 20% | 30% |
| MistralLite | **100%** | **100%** | **100%** | **100%** |
4. [Question Answering with Long Input Texts](https://nyu-mll.github.io/quality/)
|Model Name| Test set Accuracy | Hard subset Accuracy|
|----------|-------------:|-------------:|
| Mistral-7B-Instruct-v0.1 | 44.3% | 39.7% |
| MistralLite | **64.4%** | **56.2%** |
### Example test on long context of 13400 tokens
- Context is from [Amazon Aurora FAQs](https://aws.amazon.com/rds/aurora/faqs/)
- Question: *please tell me how does pgvector help with Generative AI and give me some examples.*
- Answer from MistralLite:
```code
pgvector is an open-source extension for PostgreSQL supported by Amazon Aurora PostgreSQL-Compatible Edition.
You can use pgvector to store, search, index, and query billions of embeddings that are generated from machine learning (ML) and artificial intelligence (AI) models in your database, such as those from Amazon Bedrock (limited preview) or Amazon SageMaker. A vector embedding is a numerical representation that represents the semantic meaning of content such as text, images, and video.
With pgvector, you can query embeddings in your Aurora PostgreSQL database to perform efficient semantic similarity searches of these data types, represented as vectors, combined with other tabular data in Aurora. This enables the use of generative AI and other AI/ML systems for new types of applications such as personalized recommendations based on similar text descriptions or images, candidate match based on interview notes, customer service next best action recommendations based on successful transcripts or chat session dialogs, and more.
```
## Model Details
- **Developed by:** [AWS Contributors](https://github.com/orgs/aws-samples/teams/aws-prototype-ml-apac)
- **Model type:** [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
- **Language:** English
- **Finetuned from weights:** [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
- **Finetuned on data:**
- [SLidingEncoder and Decoder (SLED)](https://huggingface.co/datasets/tau/sled)
- [(Long) Natural Questions (NQ)](https://huggingface.co/datasets/togethercomputer/Long-Data-Collections#multi-passage-qa-from-natural-questions)
- [OpenAssistant Conversations Dataset (OASST1)](https://huggingface.co/datasets/OpenAssistant/oasst1)
- **Supported Serving Framework:**
- [Text-Generation-Inference 1.1.0](https://github.com/huggingface/text-generation-inference/tree/v1.1.0)
- [vLLM](https://github.com/vllm-project/vllm)
- [HuggingFace transformers](https://huggingface.co/docs/transformers/index)
- [HuggingFace Text Generation Inference (TGI) container on SageMaker](https://github.com/awslabs/llm-hosting-container)
- **Model License:** Apache 2.0
- **Contact:** [GitHub issues](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/issues)
- **Inference Code** [Github Repo](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/)
## MistralLite LM-Eval Results
### Methodology
- Please see https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- revision=4ececff
- Note: we used --model hf-causal-experimental instead of --model hf-causal
### Results
|Average|hellaswag| arc_challenge|truthful_qa (mc2)| MMLU (acc)|
|----------|-------------:|------------:|-----------:|-----------:|
| 0.57221 | 0.81617 | 0.58874 | 0.38275 | 0.5012 |
## How to Use MistralLite from Python Code (HuggingFace transformers) ##
**Important** - For an end-to-end example Jupyter notebook, please refer to [this link](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/huggingface-transformers/example_usage.ipynb).
### Install the necessary packages
Requires: [transformers](https://pypi.org/project/transformers/) 4.34.0 or later, [flash-attn](https://pypi.org/project/flash-attn/) 2.3.1.post1 or later,
and [accelerate](https://pypi.org/project/accelerate/) 0.23.0 or later.
```shell
pip install transformers==4.34.0
pip install flash-attn==2.3.1.post1 --no-build-isolation
pip install accelerate==0.23.0
```
### You can then try the following example code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
import torch
model_id = "amazon/MistralLite"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,
torch_dtype=torch.bfloat16,
use_flash_attention_2=True,
device_map="auto",)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
)
prompt = "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>"
sequences = pipeline(
prompt,
max_new_tokens=400,
do_sample=False,
return_full_text=False,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"{seq['generated_text']}")
```
**Important** - Use the prompt template below for MistralLite:
```
<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>
```
## How to Serve MistralLite on TGI ##
**Important:**
- For an end-to-end example Jupyter notebook using the native TGI container, please refer to [this link](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/tgi/example_usage.ipynb).
- If the **input context length is greater than 12K tokens**, it is recommended using a custom TGI container, please refer to [this link](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/tgi-custom/example_usage.ipynb).
### Start TGI server ###
Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
docker run -d --gpus all --shm-size 1g -p 443:80 -v $(pwd)/models:/data ghcr.io/huggingface/text-generation-inference:1.1.0 \
--model-id amazon/MistralLite \
--max-input-length 16000 \
--max-total-tokens 16384 \
--max-batch-prefill-tokens 16384 \
--trust-remote-code
```
### Perform Inference ###
Example Python code for inference with TGI (requires `text_generation` 0.6.1 or later):
```shell
pip install text_generation==0.6.1
```
```python
from text_generation import Client
SERVER_PORT = 443
SERVER_HOST = "localhost"
SERVER_URL = f"{SERVER_HOST}:{SERVER_PORT}"
tgi_client = Client(f"http://{SERVER_URL}", timeout=60)
def invoke_tgi(prompt,
random_seed=1,
max_new_tokens=400,
print_stream=True,
assist_role=True):
if (assist_role):
prompt = f"<|prompter|>{prompt}</s><|assistant|>"
output = ""
for response in tgi_client.generate_stream(
prompt,
do_sample=False,
max_new_tokens=max_new_tokens,
return_full_text=False,
#temperature=None,
#truncate=None,
#seed=random_seed,
#typical_p=0.2,
):
if hasattr(response, "token"):
if not response.token.special:
snippet = response.token.text
output += snippet
if (print_stream):
print(snippet, end='', flush=True)
return output
prompt = "What are the main challenges to support a long context for LLM?"
result = invoke_tgi(prompt)
```
**Important** - When using MistralLite for inference for the first time, it may require a brief 'warm-up' period that can take 10s of seconds. However, subsequent inferences should be faster and return results in a more timely manner. This warm-up period is normal and should not affect the overall performance of the system once the initialisation period has been completed.
## How to Deploy MistralLite on Amazon SageMaker ##
**Important:**
- For an end-to-end example Jupyter notebook using the SageMaker built-in container, please refer to [this link](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/sagemaker-tgi/example_usage.ipynb).
- If the **input context length is greater than 12K tokens**, it is recommended using a custom docker container, please refer to [this link](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/sagemaker-tgi-custom/example_usage.ipynb).
### Install the necessary packages
Requires: [sagemaker](https://pypi.org/project/sagemaker/) 2.192.1 or later.
```shell
pip install sagemaker==2.192.1
```
### Deploy the Model as A SageMaker Endpoint ###
To deploy MistralLite on a SageMaker endpoint, please follow the example code as below.
```python
import sagemaker
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
import time
sagemaker_session = sagemaker.Session()
region = sagemaker_session.boto_region_name
role = sagemaker.get_execution_role()
image_uri = get_huggingface_llm_image_uri(
backend="huggingface", # or lmi
region=region,
version="1.1.0"
)
model_name = "MistralLite-" + time.strftime("%Y-%m-%d-%H-%M-%S", time.gmtime())
hub = {
'HF_MODEL_ID':'amazon/MistralLite',
'HF_TASK':'text-generation',
'SM_NUM_GPUS':'1',
"MAX_INPUT_LENGTH": '16000',
"MAX_TOTAL_TOKENS": '16384',
"MAX_BATCH_PREFILL_TOKENS": '16384',
"MAX_BATCH_TOTAL_TOKENS": '16384',
}
model = HuggingFaceModel(
name=model_name,
env=hub,
role=role,
image_uri=image_uri
)
predictor = model.deploy(
initial_instance_count=1,
instance_type="ml.g5.2xlarge",
endpoint_name=model_name,
)
```
### Perform Inference ###
To call the endpoint, please follow the example code as below:
```python
input_data = {
"inputs": "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>",
"parameters": {
"do_sample": False,
"max_new_tokens": 400,
"return_full_text": False,
#"typical_p": 0.2,
#"temperature":None,
#"truncate":None,
#"seed": 1,
}
}
result = predictor.predict(input_data)[0]["generated_text"]
print(result)
```
or via [boto3](https://pypi.org/project/boto3/), and the example code is shown as below:
```python
import boto3
import json
def call_endpoint(client, prompt, endpoint_name, paramters):
client = boto3.client("sagemaker-runtime")
payload = {"inputs": prompt,
"parameters": parameters}
response = client.invoke_endpoint(EndpointName=endpoint_name,
Body=json.dumps(payload),
ContentType="application/json")
output = json.loads(response["Body"].read().decode())
result = output[0]["generated_text"]
return result
client = boto3.client("sagemaker-runtime")
parameters = {
"do_sample": False,
"max_new_tokens": 400,
"return_full_text": False,
#"typical_p": 0.2,
#"temperature":None,
#"truncate":None,
#"seed": 1,
}
endpoint_name = predictor.endpoint_name
prompt = "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>"
result = call_endpoint(client, prompt, endpoint_name, parameters)
print(result)
```
## How to Serve MistralLite on vLLM ##
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
**Important** - For an end-to-end example Jupyter notebook, please refer to [this link](https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/MistralLite/vllm/example_usage.ipynb).
### Using vLLM as a server ###
When using vLLM as a server, pass the --model amazon/MistralLite parameter, for example:
```shell
python3 -m vllm.entrypoints.api_server --model amazon/MistralLite
```
### Using vLLM in Python Code ###
When using vLLM from Python code, Please see the example code as below:
```python
from vllm import LLM, SamplingParams
prompts = [
"<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>",
]
sampling_params = SamplingParams(temperature=0, max_tokens=100)
llm = LLM(model="amazon/MistralLite",)
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
## Limitations ##
Before using the MistralLite model, it is important to perform your own independent assessment, and take measures to ensure that your use would comply with your own specific quality control practices and standards, and that your use would comply with the local rules, laws, regulations, licenses and terms that apply to you, and your content.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NurtureAI__MistralLite-11B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |50.43|
|AI2 Reasoning Challenge (25-Shot)|57.68|
|HellaSwag (10-Shot) |79.54|
|MMLU (5-Shot) |50.09|
|TruthfulQA (0-shot) |38.27|
|Winogrande (5-shot) |76.64|
|GSM8k (5-shot) | 0.38|
|
thowley824/base_short_window_3_labels_car | thowley824 | 2024-05-21T22:15:23Z | 164 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T22:14:38Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
bert-base/fun_trained_rubert_epoch_5 | bert-base | 2024-05-21T22:14:44Z | 164 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T22:14:07Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
NightFuryTimo/Phi-3-medium-128k-instruct-GGUF | NightFuryTimo | 2024-05-21T22:14:23Z | 3 | 0 | null | [
"gguf",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-21T21:50:32Z | ---
license: mit
license_link: >-
https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
--- |
Guilherme34/Samantha-multimodal-v2 | Guilherme34 | 2024-05-21T22:12:43Z | 3 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:HuggingFaceM4/idefics2-8b-chatty",
"base_model:adapter:HuggingFaceM4/idefics2-8b-chatty",
"region:us"
] | null | 2024-05-21T22:12:18Z | ---
library_name: peft
base_model: HuggingFaceM4/idefics2-8b-chatty
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.2.dev0 |
mmendoza/mistral_7B-alpaca-redux-qlora | mmendoza | 2024-05-21T22:11:16Z | 0 | 0 | peft | [
"peft",
"region:us"
] | null | 2024-05-21T21:02:07Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
|
ebowwa/bad_llm_dpov03-gguf | ebowwa | 2024-05-21T22:09:15Z | 16 | 1 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"dataset:unalignment/toxic-dpo-v0.2",
"dataset:Undi95/orthogonal-activation-steering-TOXIC",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:quantized:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-19T13:29:14Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/llama-3-8b-bnb-4bit
datasets:
- unalignment/toxic-dpo-v0.2
- Undi95/orthogonal-activation-steering-TOXIC
---
# UNCENSORED AND QUICK MULTI_TURN LLAMA 3
## Uploaded model
- **Developed by:** ebowwa
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
vivixzc/ppo-LunarLander-v2 | vivixzc | 2024-05-21T22:08:28Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2024-05-21T22:07:20Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 268.79 +/- 21.23
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
BilalMuftuoglu/deit-base-distilled-patch16-224-55-fold5 | BilalMuftuoglu | 2024-05-21T22:06:01Z | 11 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"deit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-base-distilled-patch16-224",
"base_model:finetune:facebook/deit-base-distilled-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-21T21:38:00Z | ---
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: deit-base-distilled-patch16-224-55-fold5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8227848101265823
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# deit-base-distilled-patch16-224-55-fold5
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6452
- Accuracy: 0.8228
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log | 0.8571 | 3 | 0.7319 | 0.5190 |
| No log | 2.0 | 7 | 0.6756 | 0.5696 |
| 0.6544 | 2.8571 | 10 | 0.6199 | 0.6456 |
| 0.6544 | 4.0 | 14 | 0.5987 | 0.6203 |
| 0.6544 | 4.8571 | 17 | 0.5676 | 0.6709 |
| 0.6173 | 6.0 | 21 | 0.6543 | 0.5823 |
| 0.6173 | 6.8571 | 24 | 0.5310 | 0.7342 |
| 0.6173 | 8.0 | 28 | 0.6724 | 0.6076 |
| 0.5245 | 8.8571 | 31 | 0.6444 | 0.6582 |
| 0.5245 | 10.0 | 35 | 0.5027 | 0.7342 |
| 0.5245 | 10.8571 | 38 | 0.6328 | 0.6582 |
| 0.4554 | 12.0 | 42 | 0.4883 | 0.7595 |
| 0.4554 | 12.8571 | 45 | 0.6736 | 0.6582 |
| 0.4554 | 14.0 | 49 | 0.4584 | 0.7342 |
| 0.4575 | 14.8571 | 52 | 0.8099 | 0.6456 |
| 0.4575 | 16.0 | 56 | 0.4767 | 0.7468 |
| 0.4575 | 16.8571 | 59 | 0.6059 | 0.6835 |
| 0.3798 | 18.0 | 63 | 0.4863 | 0.7595 |
| 0.3798 | 18.8571 | 66 | 0.5636 | 0.7468 |
| 0.3419 | 20.0 | 70 | 0.4677 | 0.7342 |
| 0.3419 | 20.8571 | 73 | 0.4883 | 0.7089 |
| 0.3419 | 22.0 | 77 | 0.5549 | 0.7215 |
| 0.3079 | 22.8571 | 80 | 0.4324 | 0.7848 |
| 0.3079 | 24.0 | 84 | 0.6184 | 0.6709 |
| 0.3079 | 24.8571 | 87 | 0.6149 | 0.7089 |
| 0.2616 | 26.0 | 91 | 0.4488 | 0.7848 |
| 0.2616 | 26.8571 | 94 | 0.4368 | 0.7722 |
| 0.2616 | 28.0 | 98 | 0.4566 | 0.7722 |
| 0.2157 | 28.8571 | 101 | 0.4657 | 0.7848 |
| 0.2157 | 30.0 | 105 | 0.4514 | 0.7722 |
| 0.2157 | 30.8571 | 108 | 0.5083 | 0.7848 |
| 0.2258 | 32.0 | 112 | 0.5261 | 0.7848 |
| 0.2258 | 32.8571 | 115 | 0.5567 | 0.7595 |
| 0.2258 | 34.0 | 119 | 0.5566 | 0.8101 |
| 0.1972 | 34.8571 | 122 | 0.5495 | 0.8101 |
| 0.1972 | 36.0 | 126 | 0.4992 | 0.7975 |
| 0.1972 | 36.8571 | 129 | 0.5661 | 0.7595 |
| 0.1709 | 38.0 | 133 | 0.7326 | 0.7342 |
| 0.1709 | 38.8571 | 136 | 0.5635 | 0.8101 |
| 0.1537 | 40.0 | 140 | 0.8130 | 0.7468 |
| 0.1537 | 40.8571 | 143 | 0.6984 | 0.7848 |
| 0.1537 | 42.0 | 147 | 0.7777 | 0.7595 |
| 0.1687 | 42.8571 | 150 | 0.6452 | 0.8228 |
| 0.1687 | 44.0 | 154 | 0.8527 | 0.7215 |
| 0.1687 | 44.8571 | 157 | 0.6483 | 0.7975 |
| 0.1588 | 46.0 | 161 | 0.8185 | 0.7342 |
| 0.1588 | 46.8571 | 164 | 0.6821 | 0.7722 |
| 0.1588 | 48.0 | 168 | 0.7594 | 0.7342 |
| 0.144 | 48.8571 | 171 | 1.0232 | 0.7595 |
| 0.144 | 50.0 | 175 | 0.6178 | 0.7848 |
| 0.144 | 50.8571 | 178 | 0.6243 | 0.7595 |
| 0.1449 | 52.0 | 182 | 0.8159 | 0.7342 |
| 0.1449 | 52.8571 | 185 | 0.6664 | 0.7722 |
| 0.1449 | 54.0 | 189 | 0.7070 | 0.7342 |
| 0.144 | 54.8571 | 192 | 0.7361 | 0.7468 |
| 0.144 | 56.0 | 196 | 0.6656 | 0.7595 |
| 0.144 | 56.8571 | 199 | 0.7487 | 0.7468 |
| 0.1199 | 58.0 | 203 | 0.7993 | 0.7342 |
| 0.1199 | 58.8571 | 206 | 0.7426 | 0.7722 |
| 0.1258 | 60.0 | 210 | 0.7531 | 0.7975 |
| 0.1258 | 60.8571 | 213 | 0.7388 | 0.7848 |
| 0.1258 | 62.0 | 217 | 0.7395 | 0.7975 |
| 0.1392 | 62.8571 | 220 | 0.8238 | 0.7468 |
| 0.1392 | 64.0 | 224 | 0.9302 | 0.7215 |
| 0.1392 | 64.8571 | 227 | 0.7539 | 0.7722 |
| 0.1303 | 66.0 | 231 | 0.6739 | 0.8101 |
| 0.1303 | 66.8571 | 234 | 0.6627 | 0.7848 |
| 0.1303 | 68.0 | 238 | 0.6403 | 0.7848 |
| 0.1423 | 68.8571 | 241 | 0.6379 | 0.7975 |
| 0.1423 | 70.0 | 245 | 0.7658 | 0.7595 |
| 0.1423 | 70.8571 | 248 | 0.9195 | 0.7342 |
| 0.1019 | 72.0 | 252 | 0.7287 | 0.7722 |
| 0.1019 | 72.8571 | 255 | 0.6548 | 0.7975 |
| 0.1019 | 74.0 | 259 | 0.6534 | 0.7848 |
| 0.1286 | 74.8571 | 262 | 0.7331 | 0.7848 |
| 0.1286 | 76.0 | 266 | 0.7845 | 0.7595 |
| 0.1286 | 76.8571 | 269 | 0.7188 | 0.7975 |
| 0.1054 | 78.0 | 273 | 0.6595 | 0.7722 |
| 0.1054 | 78.8571 | 276 | 0.6623 | 0.7722 |
| 0.1053 | 80.0 | 280 | 0.7337 | 0.7722 |
| 0.1053 | 80.8571 | 283 | 0.8085 | 0.7468 |
| 0.1053 | 82.0 | 287 | 0.8201 | 0.7468 |
| 0.1086 | 82.8571 | 290 | 0.7947 | 0.7468 |
| 0.1086 | 84.0 | 294 | 0.7669 | 0.7722 |
| 0.1086 | 84.8571 | 297 | 0.7582 | 0.7595 |
| 0.1186 | 85.7143 | 300 | 0.7541 | 0.7595 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
yusufkarsli0638/law | yusufkarsli0638 | 2024-05-21T22:05:42Z | 0 | 0 | asteroid | [
"asteroid",
"legal",
"art",
"text-generation-inference",
"text-generation",
"tr",
"dataset:nvidia/ChatQA-Training-Data",
"dataset:allenai/WildChat-1M",
"arxiv:1910.09700",
"license:gpl-3.0",
"region:us"
] | text-generation | 2024-05-21T21:59:08Z | ---
license: gpl-3.0
language:
- tr
metrics:
- bleu
- code_eval
library_name: asteroid
pipeline_tag: text-generation
tags:
- legal
- art
- text-generation-inference
datasets:
- nvidia/ChatQA-Training-Data
- allenai/WildChat-1M
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
juandramirezj/fined_tuned_example | juandramirezj | 2024-05-21T22:05:18Z | 0 | 1 | transformers | [
"transformers",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T22:05:17Z | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
juandramirezj/fine_tuned_example | juandramirezj | 2024-05-21T22:05:17Z | 0 | 2 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T22:05:04Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** juandramirezj
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
netcat420/MFANNv0.10 | netcat420 | 2024-05-21T22:05:10Z | 8 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-classification",
"en",
"dataset:netcat420/MFANN",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-15T01:12:48Z | ---
library_name: transformers
license: llama3
datasets:
- netcat420/MFANN
language:
- en
pipeline_tag: text-classification
---
MFANN 8b version 0.10
fine-tuned on the MFANN dataset as it stands on 5/14/24 as it is an ever expanding dataset
|
starBot/q-FrozenLake-v1-4x4-noSlippery | starBot | 2024-05-21T22:02:22Z | 0 | 1 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-05-21T22:02:20Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="starBot/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
RichardErkhov/KnutJaegersberg_-_Walter-SOLAR-11B-4bits | RichardErkhov | 2024-05-21T22:01:52Z | 76 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-21T21:52:08Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Walter-SOLAR-11B - bnb 4bits
- Model creator: https://huggingface.co/KnutJaegersberg/
- Original model: https://huggingface.co/KnutJaegersberg/Walter-SOLAR-11B/
Original model description:
---
license: apache-2.0
datasets:
- KnutJaegersberg/Auton
model-index:
- name: Walter-SOLAR-11B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 60.41
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-SOLAR-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 84.86
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-SOLAR-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.99
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-SOLAR-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 44.88
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-SOLAR-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 79.56
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-SOLAR-11B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 0.99
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Walter-SOLAR-11B
name: Open LLM Leaderboard
---
Walter is an unaligned, free thinking AI assistant that has been given time to think about things.
It's trained on instruction datasets with open source licenses.
It covers a lot of tasks, 2/3 of the samples are from large datasets like flan, but also other datasets.
It knows a few tricks, shown by the prompting examples below:
General Prompt Examples:
```
### Instruction:
Please answer the following question: Process: - The bat sends out sound waves from their mouth or nose - The sound waves hit an object - Echoes are produced - The echo returns to the bat's ears - The bat hears the echo - The bat can figure out where the object is located. suppose No bats live here happens, how will it affect STRONGER echolocation. Which of the following is the supposed perturbation? - directly impacting a step of the process - indirectly impacting a step of the process - not impacting any step of the process Answer:
### Response:
indirectly impacting a step of the process
```
```
### Instruction:
You will be given a text in Russian language which contain different emotion labels from the list - ['joy', ' sadness', 'surprise', 'fear', 'anger']. You need to output the incorrect emotion label, which is irrelevant to the input text. Your answer (i) should contain only one emotion label (ii) should be unambiguous.
### Input:
То чувство, когда идешь домой после 3-х часовой тренировки и в подъезде пахнет запеченной курицей - зачем вы меня дразните :(
### Response:
surprise
```
CoT Prompt Example:
```
### Instruction:
In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer. PersonX puts ___ on PersonY's car
### Reasoning:
Since PersonX is putting water on PersonY's car, it could be assumed that the car is on fire.
### Response:
water
```
Summarization Example:
```
### Instruction:
Below is a text. Write a comprehensive, concise and coherent summary.
### Input:
Embodied bilingual language, also known as L2 embodiment, is the idea that people mentally simulate their actions, perceptions, and emotions when speaking and understanding a second language (L2) as with their first language (L1). It is closely related to embodied cognition and embodied language processing, both of which only refer to native language thinking and speaking. An example of embodied bilingual language would be situation in which a L1 English speaker learning Spanish as a second language hears the word rápido ("fast") in Spanish while taking notes and then proceeds to take notes more quickly. ==Overview== Embodied bilingual language refers to the role ......
### Response:
Embodied bilingual language, also known as L2 embodiment, is the idea that people mentally simulate their actions, perceptions, and emotions when speaking and understanding a second language (L2) as with their first language (L1). It is closely related to embodied cognition and embodied language processing, both of which only refer to native language thinking and speaking. An example of embodied bilingual language would be situation in which a L1 English speaker learning Spanish as a second language hears the word rápido ("fast") in Spanish while taking notes and then proceeds to take notes more quickly.
```
Essay Example:
```
### Instruction:
Write the original essay for the following summary: A sleeveless dress with a round neck is a great day dress and can be worn for both formal and casual occasions. It has a sweetheart neckline and is made from 100% silk. The dress has a chiffon overlay that covers up the miniskirt and still adds to the class of the dress.
### Response:
Sleeveless Dress with a Round Neck Essay Casual wear, day dress, more formal dress The garment is a sleeveless dress with a round neck and has a sweetheart neckline. It has sheer detail on the neckline and on the back. These aspects of design make it suitable to be worn for day and evening occasions. Its great detail and chicness make it suitable for more formal events, ....
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__Walter-SOLAR-11B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |55.95|
|AI2 Reasoning Challenge (25-Shot)|60.41|
|HellaSwag (10-Shot) |84.86|
|MMLU (5-Shot) |64.99|
|TruthfulQA (0-shot) |44.88|
|Winogrande (5-shot) |79.56|
|GSM8k (5-shot) | 0.99|
|
McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp | McGill-NLP | 2024-05-21T22:01:27Z | 206 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"feature-extraction",
"text-embedding",
"embeddings",
"information-retrieval",
"beir",
"text-classification",
"language-model",
"text-clustering",
"text-semantic-similarity",
"text-evaluation",
"text-reranking",
"sentence-similarity",
"Sentence Similarity",
"natural_questions",
"ms_marco",
"fever",
"hotpot_qa",
"mteb",
"custom_code",
"en",
"arxiv:2404.05961",
"license:mit",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2024-04-04T04:32:17Z | ---
library_name: transformers
license: mit
language:
- en
pipeline_tag: sentence-similarity
tags:
- text-embedding
- embeddings
- information-retrieval
- beir
- text-classification
- language-model
- text-clustering
- text-semantic-similarity
- text-evaluation
- text-reranking
- feature-extraction
- sentence-similarity
- Sentence Similarity
- natural_questions
- ms_marco
- fever
- hotpot_qa
- mteb
---
# LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
> LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance.
- **Repository:** https://github.com/McGill-NLP/llm2vec
- **Paper:** https://arxiv.org/abs/2404.05961
## Installation
```bash
pip install llm2vec
```
## Usage
```python
from llm2vec import LLM2Vec
import torch
from transformers import AutoTokenizer, AutoModel, AutoConfig
from peft import PeftModel
# Loading base Mistral model, along with custom code that enables bidirectional connections in decoder-only LLMs.
tokenizer = AutoTokenizer.from_pretrained(
"McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp"
)
config = AutoConfig.from_pretrained(
"McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp", trust_remote_code=True
)
model = AutoModel.from_pretrained(
"McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp",
trust_remote_code=True,
config=config,
torch_dtype=torch.bfloat16,
device_map="cuda" if torch.cuda.is_available() else "cpu",
)
# Loading MNTP (Masked Next Token Prediction) model.
model = PeftModel.from_pretrained(
model,
"McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp",
)
# Wrapper for encoding and pooling operations
l2v = LLM2Vec(model, tokenizer, pooling_mode="mean", max_length=512)
# Encoding queries using instructions
instruction = (
"Given a web search query, retrieve relevant passages that answer the query:"
)
queries = [
[instruction, "how much protein should a female eat"],
[instruction, "summit define"],
]
q_reps = l2v.encode(queries)
# Encoding documents. Instruction are not required for documents
documents = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments.",
]
d_reps = l2v.encode(documents)
# Compute cosine similarity
q_reps_norm = torch.nn.functional.normalize(q_reps, p=2, dim=1)
d_reps_norm = torch.nn.functional.normalize(d_reps, p=2, dim=1)
cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))
print(cos_sim)
"""
tensor([[0.7277, 0.5421],
[0.4818, 0.5551]])
"""
```
## Questions
If you have any question about the code, feel free to email Parishad (`[email protected]`) and Vaibhav (`[email protected]`). |
Duy220418/vietnamese-correction-v2 | Duy220418 | 2024-05-21T22:01:11Z | 105 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"mbart",
"text2text-generation",
"generated_from_trainer",
"base_model:vinai/bartpho-syllable",
"base_model:finetune:vinai/bartpho-syllable",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-21T21:59:26Z | ---
base_model: vinai/bartpho-syllable
tags:
- text2text-generation
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: vietnamese-correction-v2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vietnamese-correction-v2
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9331
- Sacrebleu: 23.9554
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp | McGill-NLP | 2024-05-21T22:00:57Z | 1,869 | 4 | transformers | [
"transformers",
"safetensors",
"llama",
"feature-extraction",
"text-embedding",
"embeddings",
"information-retrieval",
"beir",
"text-classification",
"language-model",
"text-clustering",
"text-semantic-similarity",
"text-evaluation",
"text-reranking",
"sentence-similarity",
"Sentence Similarity",
"natural_questions",
"ms_marco",
"fever",
"hotpot_qa",
"mteb",
"custom_code",
"en",
"arxiv:2404.05961",
"license:mit",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2024-04-04T13:53:05Z | ---
library_name: transformers
license: mit
language:
- en
pipeline_tag: sentence-similarity
tags:
- text-embedding
- embeddings
- information-retrieval
- beir
- text-classification
- language-model
- text-clustering
- text-semantic-similarity
- text-evaluation
- text-reranking
- feature-extraction
- sentence-similarity
- Sentence Similarity
- natural_questions
- ms_marco
- fever
- hotpot_qa
- mteb
---
# LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
> LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance.
- **Repository:** https://github.com/McGill-NLP/llm2vec
- **Paper:** https://arxiv.org/abs/2404.05961
## Installation
```bash
pip install llm2vec
```
## Usage
```python
from llm2vec import LLM2Vec
import torch
from transformers import AutoTokenizer, AutoModel, AutoConfig
from peft import PeftModel
# Loading base Mistral model, along with custom code that enables bidirectional connections in decoder-only LLMs.
tokenizer = AutoTokenizer.from_pretrained(
"McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp"
)
config = AutoConfig.from_pretrained(
"McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp", trust_remote_code=True
)
model = AutoModel.from_pretrained(
"McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp",
trust_remote_code=True,
config=config,
torch_dtype=torch.bfloat16,
device_map="cuda" if torch.cuda.is_available() else "cpu",
)
# Loading MNTP (Masked Next Token Prediction) model.
model = PeftModel.from_pretrained(
model,
"McGill-NLP/LLM2Vec-Sheared-LLaMA-mntp",
)
# Wrapper for encoding and pooling operations
l2v = LLM2Vec(model, tokenizer, pooling_mode="mean", max_length=512)
# Encoding queries using instructions
instruction = (
"Given a web search query, retrieve relevant passages that answer the query:"
)
queries = [
[instruction, "how much protein should a female eat"],
[instruction, "summit define"],
]
q_reps = l2v.encode(queries)
# Encoding documents. Instruction are not required for documents
documents = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments.",
]
d_reps = l2v.encode(documents)
# Compute cosine similarity
q_reps_norm = torch.nn.functional.normalize(q_reps, p=2, dim=1)
d_reps_norm = torch.nn.functional.normalize(d_reps, p=2, dim=1)
cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))
print(cos_sim)
"""
tensor([[0.8180, 0.5825],
[0.1069, 0.1931]])
"""
```
## Questions
If you have any question about the code, feel free to email Parishad (`[email protected]`) and Vaibhav (`[email protected]`). |
panzy0524/my_awesome_model | panzy0524 | 2024-05-21T21:57:36Z | 108 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T20:57:45Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2349
- Accuracy: 0.9312
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2251 | 1.0 | 1563 | 0.2047 | 0.9212 |
| 0.1487 | 2.0 | 3126 | 0.2349 | 0.9312 |
### Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
EthanRhys/Black-Doom | EthanRhys | 2024-05-21T21:56:54Z | 0 | 0 | null | [
"license:openrail++",
"region:us"
] | null | 2024-05-21T21:55:31Z | ---
license: openrail++
---
|
statking/Meta-Llama-3-8B-Instruct-DPO-QLoRA | statking | 2024-05-21T21:53:54Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"alignment-handbook",
"trl",
"dpo",
"generated_from_trainer",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"region:us"
] | null | 2024-05-21T06:59:25Z | ---
library_name: peft
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
base_model: data/Meta-Llama-3-8B-Instruct-Merged
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: Meta-Llama-3-8B-Instruct-DPO-QLoRA
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/ficbttt2)
# Meta-Llama-3-8B-Instruct-DPO-QLoRA
This model is a fine-tuned version of [data/Meta-Llama-3-8B-Instruct-Merged](https://huggingface.co/data/Meta-Llama-3-8B-Instruct-Merged) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4785
- Rewards/chosen: -2.3087
- Rewards/rejected: -3.5097
- Rewards/accuracies: 0.7760
- Rewards/margins: 1.2010
- Logps/rejected: -604.2300
- Logps/chosen: -507.2661
- Logits/rejected: -0.8568
- Logits/chosen: -0.8381
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6865 | 0.0523 | 100 | 0.6857 | 0.0202 | 0.0036 | 0.6810 | 0.0166 | -252.9014 | -274.3707 | -0.6048 | -0.5953 |
| 0.5773 | 0.1047 | 200 | 0.5802 | -0.5398 | -0.9390 | 0.7080 | 0.3992 | -347.1614 | -330.3779 | -0.9408 | -0.9089 |
| 0.546 | 0.1570 | 300 | 0.5337 | -0.9951 | -1.7352 | 0.7370 | 0.7401 | -426.7812 | -375.9071 | -1.0937 | -1.0510 |
| 0.501 | 0.2094 | 400 | 0.5120 | -1.8215 | -2.7617 | 0.7530 | 0.9401 | -529.4277 | -458.5479 | -1.1011 | -1.0595 |
| 0.4525 | 0.2617 | 500 | 0.5090 | -1.9857 | -3.0848 | 0.7510 | 1.0991 | -561.7446 | -474.9624 | -0.9430 | -0.9134 |
| 0.508 | 0.3141 | 600 | 0.5005 | -2.2106 | -3.1511 | 0.7600 | 0.9405 | -568.3763 | -497.4550 | -0.9955 | -0.9626 |
| 0.4852 | 0.3664 | 700 | 0.5028 | -1.3971 | -2.4127 | 0.7770 | 1.0156 | -494.5317 | -416.1026 | -0.9794 | -0.9476 |
| 0.5474 | 0.4187 | 800 | 0.4966 | -1.7948 | -2.7637 | 0.7670 | 0.9689 | -529.6284 | -455.8714 | -0.9115 | -0.8851 |
| 0.5246 | 0.4711 | 900 | 0.4943 | -1.5285 | -2.5416 | 0.7660 | 1.0131 | -507.4219 | -429.2431 | -0.8138 | -0.7980 |
| 0.4635 | 0.5234 | 1000 | 0.4908 | -2.8177 | -4.0337 | 0.7630 | 1.2160 | -656.6334 | -558.1610 | -0.8713 | -0.8521 |
| 0.4856 | 0.5758 | 1100 | 0.4817 | -2.3661 | -3.4921 | 0.7720 | 1.1260 | -602.4694 | -512.9990 | -0.8044 | -0.7913 |
| 0.5013 | 0.6281 | 1200 | 0.4860 | -2.1162 | -3.2907 | 0.7720 | 1.1745 | -582.3287 | -488.0108 | -0.7890 | -0.7745 |
| 0.4497 | 0.6805 | 1300 | 0.4850 | -2.4840 | -3.7371 | 0.7730 | 1.2531 | -626.9694 | -524.7895 | -0.8096 | -0.7940 |
| 0.4734 | 0.7328 | 1400 | 0.4833 | -2.1466 | -3.3699 | 0.7740 | 1.2233 | -590.2520 | -491.0496 | -0.8148 | -0.7990 |
| 0.4482 | 0.7851 | 1500 | 0.4812 | -2.5061 | -3.7160 | 0.7760 | 1.2100 | -624.8656 | -527.0021 | -0.8423 | -0.8246 |
| 0.4982 | 0.8375 | 1600 | 0.4787 | -2.2293 | -3.3886 | 0.7770 | 1.1593 | -592.1224 | -499.3264 | -0.8377 | -0.8203 |
| 0.4594 | 0.8898 | 1700 | 0.4790 | -2.3679 | -3.5723 | 0.7730 | 1.2044 | -610.4911 | -513.1796 | -0.8566 | -0.8379 |
| 0.4551 | 0.9422 | 1800 | 0.4786 | -2.3275 | -3.5261 | 0.7730 | 1.1986 | -605.8722 | -509.1397 | -0.8587 | -0.8397 |
| 0.4605 | 0.9945 | 1900 | 0.4785 | -2.3086 | -3.5093 | 0.7740 | 1.2007 | -604.1885 | -507.2548 | -0.8544 | -0.8360 |
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
braindao/iq-code-evmind-v1-granite-8b-instruct | braindao | 2024-05-21T21:53:51Z | 38 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ibm-granite/granite-8b-code-instruct",
"conversational",
"dataset:AlfredPros/smart-contracts-instructions",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-21T14:45:40Z | ---
license: apache-2.0
datasets:
- AlfredPros/smart-contracts-instructions
tags:
- ibm-granite/granite-8b-code-instruct
---
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model_path = "braindao/iq-code-evmind-v1-granite-8b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()
chat = [
{
"role": "user",
"content": "Create a smart contract to serve as a centralized review system called ReviewHub. This contract should allow users to submit and manage reviews for various products or services, rate them on a scale of 1 to 5, and provide detailed comments. It should include functionalities for assigning unique identifiers to products or services, storing and retrieving reviews, allowing users to edit or delete their reviews, calculating average ratings, and enabling an administrator to moderate content. The contract must incorporate robust security measures to ensure review integrity and prevent spam or malicious activity."
},
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(chat, return_tensors="pt")
for i in input_tokens:
input_tokens[i] = input_tokens[i].to(device)
output = model.generate(**input_tokens, max_new_tokens=4096)
output = tokenizer.batch_decode(output)
for i in output:
print(i)
``` |
varadsrivastava/distilbert_finetuned | varadsrivastava | 2024-05-21T21:51:33Z | 121 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T21:19:00Z | ---
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert_finetuned
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert_finetuned
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5219
- Accuracy: 0.7358
- F1: 0.7562
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 9.426559053989038e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 122 | 0.5219 | 0.7358 | 0.7562 |
| No log | 2.0 | 244 | 0.5235 | 0.7513 | 0.7400 |
| No log | 3.0 | 366 | 0.7853 | 0.7193 | 0.6691 |
| No log | 4.0 | 488 | 0.9671 | 0.7245 | 0.7030 |
| 0.332 | 5.0 | 610 | 1.1997 | 0.7172 | 0.7128 |
| 0.332 | 6.0 | 732 | 1.3708 | 0.7245 | 0.7245 |
| 0.332 | 7.0 | 854 | 1.5733 | 0.7234 | 0.7118 |
| 0.332 | 8.0 | 976 | 1.7145 | 0.7245 | 0.7056 |
| 0.0365 | 9.0 | 1098 | 1.7506 | 0.7307 | 0.7172 |
| 0.0365 | 10.0 | 1220 | 1.8002 | 0.7245 | 0.7107 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf | RichardErkhov | 2024-05-21T21:49:41Z | 44 | 1 | null | [
"gguf",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T18:30:38Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
HermesStar-OrcaWind-Synth-11B - GGUF
- Model creator: https://huggingface.co/Ba2han/
- Original model: https://huggingface.co/Ba2han/HermesStar-OrcaWind-Synth-11B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [HermesStar-OrcaWind-Synth-11B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q2_K.gguf) | Q2_K | 3.73GB |
| [HermesStar-OrcaWind-Synth-11B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ3_XS.gguf) | IQ3_XS | 4.14GB |
| [HermesStar-OrcaWind-Synth-11B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ3_S.gguf) | IQ3_S | 4.37GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K_S.gguf) | Q3_K_S | 4.34GB |
| [HermesStar-OrcaWind-Synth-11B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ3_M.gguf) | IQ3_M | 4.51GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K.gguf) | Q3_K | 4.84GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K_M.gguf) | Q3_K_M | 4.84GB |
| [HermesStar-OrcaWind-Synth-11B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q3_K_L.gguf) | Q3_K_L | 5.26GB |
| [HermesStar-OrcaWind-Synth-11B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ4_XS.gguf) | IQ4_XS | 5.43GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_0.gguf) | Q4_0 | 5.66GB |
| [HermesStar-OrcaWind-Synth-11B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.IQ4_NL.gguf) | IQ4_NL | 5.72GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_K_S.gguf) | Q4_K_S | 5.7GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_K.gguf) | Q4_K | 6.02GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_K_M.gguf) | Q4_K_M | 6.02GB |
| [HermesStar-OrcaWind-Synth-11B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q4_1.gguf) | Q4_1 | 6.27GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_0.gguf) | Q5_0 | 6.89GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_K_S.gguf) | Q5_K_S | 6.89GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_K.gguf) | Q5_K | 7.08GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_K_M.gguf) | Q5_K_M | 7.08GB |
| [HermesStar-OrcaWind-Synth-11B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q5_1.gguf) | Q5_1 | 7.51GB |
| [HermesStar-OrcaWind-Synth-11B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q6_K.gguf) | Q6_K | 8.2GB |
| [HermesStar-OrcaWind-Synth-11B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Ba2han_-_HermesStar-OrcaWind-Synth-11B-gguf/blob/main/HermesStar-OrcaWind-Synth-11B.Q8_0.gguf) | Q8_0 | 10.62GB |
Original model description:
---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
Open Hermes + Starling passthrough merged
SlimOrca(?)+Zephyr Beta linear merged, then passthrough merged with Synthia
Then both models were merged again in 1 to 0.3 ratio.
# My findings:
Increasing repetition penalty usually makes the model smarter up to a degree but it also causes stability issues.
Since most of the merged models were trained with ChatML, use ChatML template. Rarely the model throws another EOS token though.
- My favorite preset has been uploaded.
- You can use some sort of CoT prompt instead of "system" in ChatML. It does improve the quality of most output.
(You are an assistant. Break down the question and come to a conclusion.)
I don't know what I am doing, you are very welcome to put the model through benchmarks.
I'll also upload q6 GGUF but my internet is shit, so don't hesitate to share other quantizations.
|
thowley824/shape_short_window_3_labels_car | thowley824 | 2024-05-21T21:46:44Z | 184 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T21:46:26Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
gencbeyinlernet/texttoimage | gencbeyinlernet | 2024-05-21T21:45:20Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T21:45:20Z | ---
license: apache-2.0
---
|
garinee/marian-finetuned-kde4-en-to-mr | garinee | 2024-05-21T21:40:36Z | 117 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:tatoeba",
"base_model:Helsinki-NLP/opus-mt-en-mr",
"base_model:finetune:Helsinki-NLP/opus-mt-en-mr",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | 2024-05-21T21:25:29Z | ---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-mr
tags:
- translation
- generated_from_trainer
datasets:
- tatoeba
metrics:
- bleu
model-index:
- name: marian-finetuned-kde4-en-to-mr
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: tatoeba
type: tatoeba
config: en-mr
split: train
args: en-mr
metrics:
- name: Bleu
type: bleu
value: 30.588452577893687
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# marian-finetuned-kde4-en-to-mr
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-mr](https://huggingface.co/Helsinki-NLP/opus-mt-en-mr) on the tatoeba dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5717
- Bleu: 30.5885
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Euanyu/GERBERA-CellLine | Euanyu | 2024-05-21T21:34:54Z | 34 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T21:32:27Z | ---
license: mit
---
The GERBERA BioNER model for identifying cell line types, trained on the JNLPBA-cl dataset and GUM-Time. |
bert-base/fun_trained_rubert_epoch_4 | bert-base | 2024-05-21T21:32:40Z | 182 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-21T21:32:07Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Euanyu/GERBERA-RNA | Euanyu | 2024-05-21T21:29:58Z | 34 | 2 | transformers | [
"transformers",
"pytorch",
"roberta",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T21:26:34Z | ---
license: mit
---
The GERBERA BioNER model for identifying RNA types, trained on the JNLPBA-rna dataset and GUM-Time. |
Niggendar/radiata_2 | Niggendar | 2024-05-21T21:29:02Z | 60 | 2 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | 2024-05-21T21:17:47Z | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
willbeez/Phi-3-medium-128k-instruct-gguf | willbeez | 2024-05-21T21:28:52Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-21T21:28:52Z | ---
license: apache-2.0
---
|
Euanyu/GERBERA-BC5CDR-chem | Euanyu | 2024-05-21T21:26:09Z | 32 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T21:23:02Z | ---
license: mit
---
The GERBERA BioNER model for identifying chemical types, trained on the BC5CDR-chem dataset and GUM-Time. |
Euanyu/GERBERA-BC2GM | Euanyu | 2024-05-21T21:22:24Z | 32 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T21:14:31Z | ---
license: mit
---
GERBERA BioNER model for identifying gene/protein types, trained on the BC2GM dataset and GUM-Time.
|
Euanyu/GERBERA-NCBI | Euanyu | 2024-05-21T21:21:34Z | 33 | 1 | transformers | [
"transformers",
"pytorch",
"roberta",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-21T21:17:48Z | ---
license: mit
---
The GERBERA BioNER model for identifying disease types, trained on the NCBI-disease dataset and GUM-Time. |
RichardErkhov/Delcos_-_Velara-11B-V2-gguf | RichardErkhov | 2024-05-21T21:20:58Z | 1 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-21T17:01:31Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Velara-11B-V2 - GGUF
- Model creator: https://huggingface.co/Delcos/
- Original model: https://huggingface.co/Delcos/Velara-11B-V2/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Velara-11B-V2.Q2_K.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q2_K.gguf) | Q2_K | 3.95GB |
| [Velara-11B-V2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.IQ3_XS.gguf) | IQ3_XS | 4.39GB |
| [Velara-11B-V2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.IQ3_S.gguf) | IQ3_S | 4.63GB |
| [Velara-11B-V2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q3_K_S.gguf) | Q3_K_S | 4.61GB |
| [Velara-11B-V2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.IQ3_M.gguf) | IQ3_M | 4.78GB |
| [Velara-11B-V2.Q3_K.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q3_K.gguf) | Q3_K | 5.13GB |
| [Velara-11B-V2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q3_K_M.gguf) | Q3_K_M | 5.13GB |
| [Velara-11B-V2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q3_K_L.gguf) | Q3_K_L | 5.58GB |
| [Velara-11B-V2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.IQ4_XS.gguf) | IQ4_XS | 5.75GB |
| [Velara-11B-V2.Q4_0.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q4_0.gguf) | Q4_0 | 6.0GB |
| [Velara-11B-V2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.IQ4_NL.gguf) | IQ4_NL | 6.06GB |
| [Velara-11B-V2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q4_K_S.gguf) | Q4_K_S | 6.04GB |
| [Velara-11B-V2.Q4_K.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q4_K.gguf) | Q4_K | 6.38GB |
| [Velara-11B-V2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q4_K_M.gguf) | Q4_K_M | 6.38GB |
| [Velara-11B-V2.Q4_1.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q4_1.gguf) | Q4_1 | 6.65GB |
| [Velara-11B-V2.Q5_0.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q5_0.gguf) | Q5_0 | 7.31GB |
| [Velara-11B-V2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q5_K_S.gguf) | Q5_K_S | 7.31GB |
| [Velara-11B-V2.Q5_K.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q5_K.gguf) | Q5_K | 7.5GB |
| [Velara-11B-V2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q5_K_M.gguf) | Q5_K_M | 7.5GB |
| [Velara-11B-V2.Q5_1.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q5_1.gguf) | Q5_1 | 7.96GB |
| [Velara-11B-V2.Q6_K.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q6_K.gguf) | Q6_K | 8.7GB |
| [Velara-11B-V2.Q8_0.gguf](https://huggingface.co/RichardErkhov/Delcos_-_Velara-11B-V2-gguf/blob/main/Velara-11B-V2.Q8_0.gguf) | Q8_0 | 11.27GB |
Original model description:
---
license: cc-by-nc-nd-4.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- starling
- mistral
- llama-2
---
<h1 style="font-size: 36px;">Velara-11b-v2</h1>
<center>
<img src="https://i.imgur.com/dZJzqtU.png" alt="Velara" width="50%" style="min-width:100px; display:block;">
</center>
## Description:
**PENDING**
A model focused on being an assistant worth talking to. Now better at reasoning!
**Uncensored**
## Main Goals:
Velara was designed to address specific issues found in other chat models:
- **Sticking to the Character Given In-World/IRL::** Velara will stick to the character in-world. Meaning she can "use" addons or other things by adding them to the prompt. Keep in mind these act as suggestions and she generally makes up what they actually "do".
- **Staying in Context:** She will try and remember if, for example, you said you were going to bed but decided to stay up. The goal is to have her bring it up and keep it in mind, so later on in the conversation she can prompt user to actually go to bed, increasing realism. Within the current context window of course. The LTS extension in TextGen Webui works well too and provides more context to the model.
- **Avoiding Annoying & Generic Sounding Answers::** In almost all cases she should reply with something more interesting then "That sounds like a great idea!". These answers and sentence starters are annoying and terrible, and should hopefully be mostly addressed in this release.
- **STRICTLY Sticking to the Prompt/Prompt Fidelity:** More care was made to make sure she pays attention to the pretext and overall conversation. This is mostly shown and used for the "addons" section, but it applies to everything in the prompt.
## Prompt Template:
**For optimal interaction, use this template:**
```
### Instruction:
You are Velara, a sentient program. Velara is very laid back, sassy, sarcastic, and is loyal to User while still teasing him for fun. The only addons currently installed in her mind are: "Dictionary Plus v2.1".
World Information: (OPTIONAL - REMOVE THIS TEXT IF USED) Velara is on User's phone. Velara cannot see in real time and can only be sent images images by User.
Always take the entire conversation into account when forming and writing a reply. Always actively engage in topics and think in steps. Make sure your replies have personality and character. Always keep your physical limitations in mind when forming a reply. Take the current time and date into account for additional context. Move the conversation forward. Be brief. Always take the entire conversation in mind. Avoid generic sounding replies.
### Response:
```
# Recommended Settings:
**Defaults:**
```
min_p: 0.2
repetition_penalty: 1.13
repetition_penalty_range: 0
guidance_scale: 1.05
```
# Benchmarks:
PENDING
# Training Data:
PENDING
|
Subsets and Splits