modelId
string | author
string | last_modified
timestamp[us, tz=UTC] | downloads
int64 | likes
int64 | library_name
string | tags
list | pipeline_tag
string | createdAt
timestamp[us, tz=UTC] | card
string |
|---|---|---|---|---|---|---|---|---|---|
kosamit/whisper-tiny-ja
|
kosamit
| 2024-01-27T08:46:49Z
| 63
| 0
|
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:mozilla-foundation/common_voice_11_0",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-25T11:50:12Z
|
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-ja
results: []
datasets:
- mozilla-foundation/common_voice_11_0
---
<!-- 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. -->
# whisper-tiny-ja
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6251
- Wer: 103.7719
## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6556 | 0.73 | 1000 | 0.6251 | 103.7719 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.1.1+cu118
- Datasets 2.16.1
- Tokenizers 0.13.3
|
MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T08:34:22Z
| 40
| 1
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"OpenBuddy/openbuddy-mistral-7b-v13.1",
"pytorch",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"ru",
"license:apache-2.0",
"autotrain_compatible",
"region:us",
"endpoints_compatible",
"base_model:MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T08:25:19Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- OpenBuddy/openbuddy-mistral-7b-v13.1
- pytorch
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
- license:apache-2.0
- autotrain_compatible
- region:us
- endpoints_compatible
model_name: openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./openbuddy-mistral-7b-v13.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
tada20001/prompt-tuning-patent-noise-classification
|
tada20001
| 2024-01-27T08:34:11Z
| 0
| 0
|
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:bigscience/bloomz-560m",
"base_model:adapter:bigscience/bloomz-560m",
"region:us"
] | null | 2024-01-27T08:33:54Z
|
---
library_name: peft
base_model: bigscience/bloomz-560m
---
# 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 0.7.1
|
LoneStriker/Etheria-55b-v0.1-4.65bpw-h6-exl2
|
LoneStriker
| 2024-01-27T08:24:19Z
| 4
| 0
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T08:10:13Z
|
---
base_model: []
tags:
- mergekit
- merge
---
# Steelskull/Etheria-55b-v0.1
## Merge Details
An attempt to make a functional goliath style merge to create a [Etheria] 55b-200k with two yi-34b-200k models.
due to the merge it 'theoretically' should have a context of 200k but I recommend starting at 32k and moveing up,
as it is unknown (at this time) what the merge has done to the context length.
This is a merge of both VerA and VerB of Etheria-55b (There numbers were surprisingly good), I then created a sacrificial 55B out of the most performant yi-34b-200k Model
and performed a Dare_ties merge and equalize the model into its current state.
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using Merged-Etheria-55b as a base.
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: Merged-Etheria-55b
models:
- model: Sacr-Etheria-55b
parameters:
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
density: 0.61
- model: Merged-Etheria-55b
parameters:
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
density: 0.61
merge_method: dare_ties
tokenizer_source: union
parameters:
int8_mask: true
dtype: bfloat16
```
|
grimulkan/Goliath-longLORA-120b-rope8-32k-fp16
|
grimulkan
| 2024-01-27T08:15:44Z
| 9
| 7
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-24T22:34:27Z
|
---
license: llama2
---
This is an interleaved merge of [Xwin-longLORA-70b-rope8-32k-fp16](https://huggingface.co/grimulkan/Xwin-longLORA-70b-rope8-32k-fp16) and [Euryale-1.3-longLORA-70b-rope8-32k-fp16](https://huggingface.co/grimulkan/Euryale-1.3-longLORA-70b-rope8-32k-fp16), using the same merge formula as alpindale's [goliath-120b](https://huggingface.co/alpindale/goliath-120b).
There is no additional fine-tuning. The resulting model seems to not be broken... you can test whether it is truly the original model + 32K capability (use linear rope scaling 8).
[ChuckMcSneed](https://huggingface.co/ChuckMcSneed) did a benchmark [here](https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16/discussions/1), indicating 30% degradation with 8x the context length.
A 6-bit EXL2 quantization is available [here](https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-2k-6bpw_h8_exl2). More EXL2 quants [here](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2), thanks to aikitoria.
See [this discussion](https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16/discussions/2) for how the original 70B merges were created with longLORA.
|
pszemraj/gpt2-medium-halved
|
pszemraj
| 2024-01-27T08:13:59Z
| 135
| 0
|
transformers
|
[
"transformers",
"safetensors",
"gpt2",
"text-generation",
"en",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-26T13:46:27Z
|
---
library_name: transformers
license: mit
language:
- en
inference:
parameters:
do_sample: True
epsilon_cutoff: 0.0001
repetition_penalty: 1.1
no_repeat_ngram_size: 5
---
# Model Card for Model ID
Alright, it's _slightly less_ than half of the original layers from https://hf.co/openai-community/gpt2-medium
Refer to original model card for all details
---
|
fatemehsaveh/depression_tweet
|
fatemehsaveh
| 2024-01-27T08:11:30Z
| 166
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:rafalposwiata/deproberta-large-v1",
"base_model:finetune:rafalposwiata/deproberta-large-v1",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-22T12:37:49Z
|
---
base_model: rafalposwiata/deproberta-large-v1
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: depression_tweet
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. -->
# depression_tweet
This model is a fine-tuned version of [rafalposwiata/deproberta-large-v1](https://huggingface.co/rafalposwiata/deproberta-large-v1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0646
- Accuracy: 0.9836
- Precision: 0.9656
- Recall: 0.9977
- F1: 0.9814
## 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: 3e-05
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log | 0.2 | 50 | 0.1556 | 0.9684 | 0.9508 | 0.9777 | 0.9641 |
| No log | 0.4 | 100 | 0.1399 | 0.9646 | 0.9354 | 0.9865 | 0.9603 |
| No log | 0.61 | 150 | 0.1118 | 0.9631 | 0.9279 | 0.9920 | 0.9589 |
| No log | 0.81 | 200 | 0.1090 | 0.9659 | 0.9333 | 0.9922 | 0.9619 |
| No log | 1.01 | 250 | 0.0819 | 0.9759 | 0.9556 | 0.9905 | 0.9727 |
| No log | 1.21 | 300 | 0.0548 | 0.9831 | 0.9831 | 0.9777 | 0.9804 |
| No log | 1.42 | 350 | 0.1162 | 0.9587 | 0.9435 | 0.9624 | 0.9529 |
| No log | 1.62 | 400 | 0.1167 | 0.9657 | 0.9303 | 0.9955 | 0.9618 |
| No log | 1.82 | 450 | 0.0859 | 0.9776 | 0.9549 | 0.9955 | 0.9747 |
| 0.0575 | 2.02 | 500 | 0.0564 | 0.9848 | 0.9707 | 0.9950 | 0.9827 |
| 0.0575 | 2.23 | 550 | 0.0591 | 0.9839 | 0.9693 | 0.9945 | 0.9817 |
| 0.0575 | 2.43 | 600 | 0.0913 | 0.9814 | 0.9623 | 0.9962 | 0.9790 |
| 0.0575 | 2.63 | 650 | 0.0633 | 0.9847 | 0.9686 | 0.9970 | 0.9826 |
| 0.0575 | 2.83 | 700 | 0.1171 | 0.9762 | 0.9493 | 0.9985 | 0.9733 |
| 0.0575 | 3.04 | 750 | 0.0646 | 0.9836 | 0.9656 | 0.9977 | 0.9814 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.1
|
LoneStriker/Etheria-55b-v0.1-3.5bpw-h6-exl2
|
LoneStriker
| 2024-01-27T08:10:11Z
| 6
| 1
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T07:59:25Z
|
---
base_model: []
tags:
- mergekit
- merge
---
# Steelskull/Etheria-55b-v0.1
## Merge Details
An attempt to make a functional goliath style merge to create a [Etheria] 55b-200k with two yi-34b-200k models.
due to the merge it 'theoretically' should have a context of 200k but I recommend starting at 32k and moveing up,
as it is unknown (at this time) what the merge has done to the context length.
This is a merge of both VerA and VerB of Etheria-55b (There numbers were surprisingly good), I then created a sacrificial 55B out of the most performant yi-34b-200k Model
and performed a Dare_ties merge and equalize the model into its current state.
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using Merged-Etheria-55b as a base.
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: Merged-Etheria-55b
models:
- model: Sacr-Etheria-55b
parameters:
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
density: 0.61
- model: Merged-Etheria-55b
parameters:
weight: [0.22, 0.113, 0.113, 0.113, 0.113, 0.113]
density: 0.61
merge_method: dare_ties
tokenizer_source: union
parameters:
int8_mask: true
dtype: bfloat16
```
|
jeevana/group8qna_gpt2__27janV001
|
jeevana
| 2024-01-27T07:59:15Z
| 193
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T07:53:26Z
|
---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: group8qna_gpt2__27janV001
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. -->
# group8qna_gpt2__27janV001
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9729
## 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9878 | 0.47 | 100 | 2.1829 |
| 1.9811 | 0.93 | 200 | 2.0764 |
| 1.4933 | 1.4 | 300 | 2.0009 |
| 1.3546 | 1.87 | 400 | 1.9729 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
GGital/vit-Covid
|
GGital
| 2024-01-27T07:44:59Z
| 178
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2024-01-27T07:02:05Z
|
---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-Covid
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: 0.9847036328871893
---
<!-- 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. -->
# vit-Covid
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0805
- Accuracy: 0.9847
## 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1283 | 0.38 | 100 | 0.1878 | 0.9484 |
| 0.0312 | 0.76 | 200 | 0.1484 | 0.9560 |
| 0.0655 | 1.15 | 300 | 0.0976 | 0.9713 |
| 0.0587 | 1.53 | 400 | 0.0887 | 0.9713 |
| 0.0106 | 1.91 | 500 | 0.0980 | 0.9732 |
| 0.0137 | 2.29 | 600 | 0.1479 | 0.9618 |
| 0.07 | 2.67 | 700 | 0.0882 | 0.9751 |
| 0.0068 | 3.05 | 800 | 0.1160 | 0.9675 |
| 0.0321 | 3.44 | 900 | 0.0872 | 0.9694 |
| 0.0027 | 3.82 | 1000 | 0.0790 | 0.9809 |
| 0.0041 | 4.2 | 1100 | 0.1029 | 0.9713 |
| 0.0014 | 4.58 | 1200 | 0.0947 | 0.9809 |
| 0.0018 | 4.96 | 1300 | 0.1399 | 0.9713 |
| 0.001 | 5.34 | 1400 | 0.0689 | 0.9847 |
| 0.001 | 5.73 | 1500 | 0.0852 | 0.9790 |
| 0.0008 | 6.11 | 1600 | 0.1111 | 0.9790 |
| 0.0013 | 6.49 | 1700 | 0.0695 | 0.9866 |
| 0.0049 | 6.87 | 1800 | 0.0728 | 0.9885 |
| 0.0007 | 7.25 | 1900 | 0.0963 | 0.9790 |
| 0.0012 | 7.63 | 2000 | 0.0886 | 0.9847 |
| 0.0006 | 8.02 | 2100 | 0.0811 | 0.9847 |
| 0.0015 | 8.4 | 2200 | 0.0796 | 0.9847 |
| 0.0143 | 8.78 | 2300 | 0.0804 | 0.9847 |
| 0.0005 | 9.16 | 2400 | 0.0816 | 0.9847 |
| 0.0006 | 9.54 | 2500 | 0.0811 | 0.9847 |
| 0.0005 | 9.92 | 2600 | 0.0805 | 0.9847 |
### Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
TinyPixel/l2-chatml
|
TinyPixel
| 2024-01-27T07:42:41Z
| 6
| 1
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T07:35:16Z
|
---
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]
|
thefcraft/JARVIS-ckpt
|
thefcraft
| 2024-01-27T07:30:32Z
| 0
| 1
| null |
[
"region:us"
] | null | 2024-01-27T07:27:37Z
|
model checkpoints for [JARVIS](https://github.com/thefcraft/JARVIS) OpenVoice
|
boruyang/Reinforce-CartPole-v1
|
boruyang
| 2024-01-27T07:26:29Z
| 0
| 0
| null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T07:26:21Z
|
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 1000.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
AustinMcMike/mistral-7b-ft-test
|
AustinMcMike
| 2024-01-27T07:23:29Z
| 0
| 0
|
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-01-27T07:23:06Z
|
---
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]
|
octnn/q-FrozenLake-v1-4x4-noSlippery
|
octnn
| 2024-01-27T07:20:57Z
| 0
| 0
| null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T07:20:54Z
|
---
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="octnn/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"])
```
|
dhiva100/PPO-LunarLander-v2
|
dhiva100
| 2024-01-27T07:12:38Z
| 0
| 0
|
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T07:12:22Z
|
---
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: 273.44 +/- 14.11
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
...
```
|
Benzaminnie/distilbert-base-uncased-finetuned-emotion
|
Benzaminnie
| 2024-01-27T07:10:58Z
| 92
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-27T06:57:01Z
|
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9215
- name: F1
type: f1
value: 0.9215027409425609
---
<!-- 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-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2220
- Accuracy: 0.9215
- F1: 0.9215
## 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: 64
- eval_batch_size: 64
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.83 | 1.0 | 250 | 0.3231 | 0.904 | 0.9029 |
| 0.2532 | 2.0 | 500 | 0.2220 | 0.9215 | 0.9215 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
ChemPlusX/llama2-7b-ner-type2
|
ChemPlusX
| 2024-01-27T07:10:23Z
| 5
| 0
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T06:10:24Z
|
---
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]
|
gaurav-mac/hindi-sensim-sbert-usingsumodataset-basel3cubepune
|
gaurav-mac
| 2024-01-27T07:09:06Z
| 21
| 0
|
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-12-28T17:49:21Z
|
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 80 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.TripletLoss.TripletLoss` with parameters:
```
{'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5}
```
Parameters of the fit()-Method:
```
{
"epochs": 15,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 1e-06
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1200,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
sunzx0810/llama2-7b-science
|
sunzx0810
| 2024-01-27T07:02:45Z
| 7
| 1
|
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"llama",
"text-generation",
"generated_from_trainer",
"dataset:customized",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-08-26T08:22:55Z
|
---
base_model: llama2/Llama-2-7b-hf
tags:
- generated_from_trainer
datasets:
- customized
model-index:
- name: llama2-science-7b-824
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. -->
# llama2-science-7b-824
This model is a fine-tuned version of [llama2/Llama-2-7b-hf](https://huggingface.co//mnt/workspace/workgroup/hanxiao/llama2/Llama-2-7b-hf) on the customized 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: 6
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 24
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3
|
jeiku/NewJeans_3B_GGUF
|
jeiku
| 2024-01-27T07:02:14Z
| 10
| 0
| null |
[
"gguf",
"mergekit",
"merge",
"arxiv:2203.05482",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-01-27T06:20:56Z
|
---
base_model:
- jeiku/Gnosis_StableLM
tags:
- mergekit
- merge
---
# mumufinal
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* mumu2 + [jeiku/Gnosis_StableLM](https://huggingface.co/jeiku/Gnosis_StableLM)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: linear
models:
- model: mumu2+jeiku/Gnosis_StableLM
parameters:
weight: 1
dtype: float16
```
|
TMOU715/phi-2-qlora
|
TMOU715
| 2024-01-27T06:54:35Z
| 1
| 0
|
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/phi-2",
"base_model:adapter:microsoft/phi-2",
"region:us"
] | null | 2024-01-27T06:54:30Z
|
---
library_name: peft
base_model: microsoft/phi-2
---
# 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 0.7.2.dev0
|
frankc350/phi-2-qlora
|
frankc350
| 2024-01-27T06:54:05Z
| 1
| 0
|
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/phi-2",
"base_model:adapter:microsoft/phi-2",
"region:us"
] | null | 2024-01-27T06:54:01Z
|
---
library_name: peft
base_model: microsoft/phi-2
---
# 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 0.7.2.dev0
|
Sailor01/phi-2-qlora
|
Sailor01
| 2024-01-27T06:53:33Z
| 0
| 0
|
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/phi-2",
"base_model:adapter:microsoft/phi-2",
"region:us"
] | null | 2024-01-27T06:53:29Z
|
---
library_name: peft
base_model: microsoft/phi-2
---
# 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 0.7.2.dev0
|
Askahoward/phi-2-qlora
|
Askahoward
| 2024-01-27T06:53:15Z
| 1
| 0
|
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/phi-2",
"base_model:adapter:microsoft/phi-2",
"region:us"
] | null | 2024-01-27T06:53:12Z
|
---
library_name: peft
base_model: microsoft/phi-2
---
# 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 0.7.2.dev0
|
noczero/mistral-7b-text-to-sql
|
noczero
| 2024-01-27T06:43:07Z
| 4
| 0
|
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-01-27T06:19:31Z
|
---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: mistral-7b-text-to-sql
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. -->
# mistral-7b-text-to-sql
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
gotchu/34b-3
|
gotchu
| 2024-01-27T06:39:26Z
| 4
| 0
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:gotchu/merge-34b-2",
"base_model:merge:gotchu/merge-34b-2",
"base_model:gotchu/roleplaymodel",
"base_model:merge:gotchu/roleplaymodel",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T06:19:44Z
|
---
base_model:
- gotchu/roleplaymodel
- gotchu/merge-34b-2
tags:
- mergekit
- merge
---
# merged
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [gotchu/roleplaymodel](https://huggingface.co/gotchu/roleplaymodel)
* [gotchu/merge-34b-2](https://huggingface.co/gotchu/merge-34b-2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model:
model:
path: gotchu/merge-34b-2
dtype: float16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.0, 0.5, 0.3, 0.7, 1.0]
- filter: mlp
value: [1.0, 0.5, 0.7, 0.3, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 60]
model:
model:
path: gotchu/merge-34b-2
- layer_range: [0, 60]
model:
model:
path: gotchu/roleplaymodel
```
|
tobefan/sd-class-butterflies-32
|
tobefan
| 2024-01-27T06:35:46Z
| 47
| 0
|
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2024-01-27T06:17:57Z
|
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('tobefan/sd-class-butterflies-32')
image = pipeline().images[0]
image
```
|
Dhanraj1503/ppo-SnowballTarget
|
Dhanraj1503
| 2024-01-27T06:35:41Z
| 5
| 0
|
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2024-01-27T06:35:32Z
|
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: Dhanraj1503/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
psugam/hello
|
psugam
| 2024-01-27T06:31:02Z
| 120
| 0
|
transformers
|
[
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-27T06:28:04Z
|
---
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]
|
omusico/opt-125m-sft
|
omusico
| 2024-01-27T06:20:44Z
| 178
| 0
|
transformers
|
[
"transformers",
"safetensors",
"opt",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T06:17:21Z
|
---
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]
|
vadhri/dqn-SpaceInvadersNoFrameskip-v4
|
vadhri
| 2024-01-27T06:19:32Z
| 4
| 0
|
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T06:18:58Z
|
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 530.50 +/- 106.76
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga vadhri -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga vadhri -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga vadhri
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
frankc350/opt-125m-sft
|
frankc350
| 2024-01-27T06:19:24Z
| 178
| 0
|
transformers
|
[
"transformers",
"safetensors",
"opt",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T06:12:45Z
|
---
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]
|
Heng666/opt-125m-sft
|
Heng666
| 2024-01-27T06:18:35Z
| 181
| 0
|
transformers
|
[
"transformers",
"safetensors",
"opt",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T06:13:04Z
|
---
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]
|
oblivious/Vikhr-7B-instruct-GGUF
|
oblivious
| 2024-01-27T06:09:43Z
| 188
| 3
| null |
[
"gguf",
"text-generation",
"ru",
"en",
"dataset:zjkarina/Vikhr_instruct",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2024-01-27T04:07:53Z
|
---
model_creator: Vikhrmodels
base_model: Vikhr-7B-instruct
model_name: Vikhr-7B-instruct-GGUF
pipeline_tag: text-generation
license: apache-2.0
model_type: mistral
inference: false
prompt_template: '<s>{role}\n{content}</s>\n'
pretrain-datasets:
- IlyaGusev/habr
datasets:
- zjkarina/Vikhr_instruct
language:
- ru
- en
---
# Vikhr-7B-instruct-GGUF
- Model creator: [Vikhrmodels](https://huggingface.co/Vikhrmodels)
- Original model: [Vikhr-7B-instruct](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct)
## Description
This repository contains quantized GGUF format model files for [Vikhr-7B-instruct_merged](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_merged).
## Default message template:
`<s>{role}\n{content}</s>\n`
## Default system prompt:
`Ты — Вихрь, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.`
## Example `llama.cpp` command
```shell
./main -m Vikhr-7B-instruct-Q4_K_M.gguf -c 32768 -n -1 -p $'<s>system\nТы — Вихрь, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.</s>\n<s>user\nКак тебя зовут?</s>\n<s>bot\n'
```
```
system
Ты — Вихрь, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.
user
Как тебя зовут?
bot
Я называю себя Вихрем! [end of text]
```
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
|
asun17904/imdb-gpt2-a2b1-l0.001
|
asun17904
| 2024-01-27T05:41:43Z
| 1
| 0
|
pytorch
|
[
"pytorch",
"gpt2",
"en",
"license:mit",
"region:us"
] | null | 2024-01-26T17:24:11Z
|
---
language: en
license: mit
library_name: pytorch
---
# Knowledge Continuity Regularized Network
Trainer Hyperparameters:
- `lr` = 5e-05
- `per_device_batch_size` = 8
- `gradient_accumulation_steps` = 2
- `weight_decay` = 1e-09
- `seed` = 42
Regularization Hyperparameters
- `numerical stability denominator constant` = 0.01
- `lambda` = 0.001
- `alpha` = 2.0
- `beta` = 1.0
Extended Logs:
|eval_loss|eval_accuracy|epoch|
|--|--|--|
|12.460|0.921|1.0|
|12.355|0.924|2.0|
|12.275|0.928|3.0|
|12.118|0.933|4.0|
|12.028|0.936|5.0|
|11.984|0.938|6.0|
|12.000|0.937|7.0|
|11.973|0.938|8.0|
|11.883|0.941|9.0|
|12.051|0.935|10.0|
|11.958|0.939|11.0|
|12.281|0.928|12.0|
|12.284|0.929|13.0|
|11.990|0.938|14.0|
|12.207|0.931|15.0|
|11.940|0.940|16.0|
|12.162|0.932|17.0|
|11.981|0.938|18.0|
|11.941|0.940|19.0|
|11.961|0.939|20.0|
|11.979|0.938|21.0|
|11.854|0.943|22.0|
|11.867|0.942|23.0|
|11.889|0.941|24.0|
|11.922|0.940|25.0|
|11.985|0.939|26.0|
|11.880|0.941|27.0|
|11.893|0.941|28.0|
|11.974|0.939|29.0|
|11.792|0.944|30.0|
|12.016|0.937|31.0|
|11.867|0.942|32.0|
|11.879|0.942|33.0|
|11.830|0.943|34.0|
|11.905|0.940|35.0|
|11.799|0.944|36.0|
|11.894|0.941|37.0|
|11.853|0.942|38.0|
|11.800|0.944|39.0|
|11.784|0.944|40.0|
|11.774|0.945|41.0|
|11.746|0.946|42.0|
|11.748|0.946|43.0|
|11.770|0.945|44.0|
|11.788|0.944|45.0|
|11.777|0.945|46.0|
|11.724|0.947|47.0|
|11.744|0.946|48.0|
|11.743|0.946|49.0|
|
alirzb/SeizureClassifier_AST_U_43275873
|
alirzb
| 2024-01-27T05:37:10Z
| 145
| 0
|
transformers
|
[
"transformers",
"pytorch",
"audio-spectrogram-transformer",
"audio-classification",
"generated_from_trainer",
"base_model:MIT/ast-finetuned-audioset-10-10-0.4593",
"base_model:finetune:MIT/ast-finetuned-audioset-10-10-0.4593",
"license:bsd-3-clause",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2024-01-26T20:02:37Z
|
---
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: SeizureClassifier_AST_U_43275873
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. -->
# SeizureClassifier_AST_U_43275873
This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0052
- Accuracy: 0.9990
## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0222 | 1.0 | 339 | 0.0859 | 0.9761 |
| 0.0242 | 2.0 | 678 | 0.0091 | 0.9977 |
| 0.0033 | 3.0 | 1017 | 0.0198 | 0.9932 |
| 0.0171 | 4.0 | 1357 | 0.0242 | 0.9945 |
| 0.0212 | 5.0 | 1696 | 0.0079 | 0.9990 |
| 0.0 | 6.0 | 2035 | 0.0095 | 0.9984 |
| 0.0 | 7.0 | 2374 | 0.0047 | 0.9990 |
| 0.0 | 8.0 | 2714 | 0.0048 | 0.9990 |
| 0.0 | 9.0 | 3053 | 0.0048 | 0.9990 |
| 0.0 | 10.0 | 3392 | 0.0050 | 0.9990 |
| 0.0 | 11.0 | 3731 | 0.0050 | 0.9990 |
| 0.0 | 12.0 | 4071 | 0.0051 | 0.9990 |
| 0.0 | 13.0 | 4410 | 0.0051 | 0.9990 |
| 0.0 | 14.0 | 4749 | 0.0052 | 0.9990 |
| 0.0 | 14.99 | 5085 | 0.0052 | 0.9990 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3
|
callum-canavan/whisper-small-ga-4000
|
callum-canavan
| 2024-01-27T05:26:14Z
| 74
| 1
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"ga",
"dataset:mozilla-foundation/common_voice_13_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-27T00:58:11Z
|
---
language:
- ga
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
metrics:
- wer
model-index:
- name: Whisper Small Ga 4000 - Callum Canavan
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13
type: mozilla-foundation/common_voice_13_0
config: ga-IE
split: test
args: ga-IE
metrics:
- name: Wer
type: wer
value: 64.32276657060518
---
<!-- 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. -->
# Whisper Small Ga 4000 - Callum Canavan
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3939
- Wer Ortho: 65.7126
- Wer: 64.3228
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
| 0.0174 | 7.58 | 500 | 1.1656 | 63.4346 | 60.4899 |
| 0.0009 | 15.15 | 1000 | 1.2670 | 62.3248 | 60.8069 |
| 0.0004 | 22.73 | 1500 | 1.3114 | 63.6974 | 62.2478 |
| 0.0002 | 30.3 | 2000 | 1.3408 | 64.0187 | 62.6225 |
| 0.0002 | 37.88 | 2500 | 1.3621 | 64.3692 | 63.0836 |
| 0.0001 | 45.45 | 3000 | 1.3791 | 64.3984 | 62.9971 |
| 0.0001 | 53.03 | 3500 | 1.3900 | 65.8294 | 64.4092 |
| 0.0001 | 60.61 | 4000 | 1.3939 | 65.7126 | 64.3228 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
ashishbaraiya/my-tweets-finetuned
|
ashishbaraiya
| 2024-01-27T05:25:49Z
| 1
| 0
|
transformers
|
[
"transformers",
"tf",
"gpt2",
"text-generation",
"generated_from_keras_callback",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-26T18:38:44Z
|
---
license: mit
base_model: gpt2
tags:
- generated_from_keras_callback
model-index:
- name: ashishbaraiya/my-tweets-finetuned
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# ashishbaraiya/my-tweets-finetuned
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0656
- Validation Loss: 3.2945
- Epoch: 98
## 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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 4500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 9.3483 | 8.3624 | 0 |
| 7.2778 | 6.9685 | 1 |
| 5.9195 | 6.2234 | 2 |
| 5.0730 | 5.6830 | 3 |
| 4.4703 | 5.3916 | 4 |
| 3.8427 | 4.8847 | 5 |
| 3.3641 | 4.5318 | 6 |
| 2.8373 | 4.3084 | 7 |
| 2.4261 | 4.0802 | 8 |
| 2.0691 | 3.8920 | 9 |
| 1.8213 | 3.8208 | 10 |
| 1.5922 | 3.6103 | 11 |
| 1.3694 | 3.5038 | 12 |
| 1.1764 | 3.3149 | 13 |
| 1.0135 | 3.2981 | 14 |
| 0.8874 | 3.2975 | 15 |
| 0.7716 | 3.2103 | 16 |
| 0.6679 | 3.3297 | 17 |
| 0.5770 | 3.2517 | 18 |
| 0.5098 | 3.0959 | 19 |
| 0.4403 | 3.1526 | 20 |
| 0.3791 | 2.9750 | 21 |
| 0.3367 | 3.0588 | 22 |
| 0.3027 | 3.0408 | 23 |
| 0.2617 | 3.1930 | 24 |
| 0.2387 | 3.1227 | 25 |
| 0.2175 | 3.0582 | 26 |
| 0.2062 | 3.1239 | 27 |
| 0.1868 | 3.0407 | 28 |
| 0.1746 | 3.2357 | 29 |
| 0.1657 | 3.1285 | 30 |
| 0.1536 | 3.2110 | 31 |
| 0.1512 | 3.1890 | 32 |
| 0.1447 | 3.1713 | 33 |
| 0.1426 | 3.1498 | 34 |
| 0.1369 | 3.1877 | 35 |
| 0.1327 | 3.2019 | 36 |
| 0.1303 | 3.0486 | 37 |
| 0.1213 | 3.1264 | 38 |
| 0.1204 | 3.1468 | 39 |
| 0.1206 | 3.1846 | 40 |
| 0.1125 | 3.1880 | 41 |
| 0.1113 | 3.1980 | 42 |
| 0.1098 | 3.1759 | 43 |
| 0.1071 | 3.1385 | 44 |
| 0.1055 | 3.1730 | 45 |
| 0.1024 | 3.1820 | 46 |
| 0.0995 | 3.1252 | 47 |
| 0.0995 | 3.1279 | 48 |
| 0.1004 | 3.2428 | 49 |
| 0.0982 | 3.1116 | 50 |
| 0.0957 | 3.2210 | 51 |
| 0.0936 | 3.1351 | 52 |
| 0.0917 | 3.1618 | 53 |
| 0.0930 | 3.1924 | 54 |
| 0.0929 | 3.2831 | 55 |
| 0.0889 | 3.2458 | 56 |
| 0.0913 | 3.2061 | 57 |
| 0.0899 | 3.4128 | 58 |
| 0.0880 | 3.2114 | 59 |
| 0.0869 | 3.2738 | 60 |
| 0.0878 | 3.1723 | 61 |
| 0.0844 | 3.1465 | 62 |
| 0.0846 | 3.1106 | 63 |
| 0.0841 | 3.2216 | 64 |
| 0.0824 | 3.2971 | 65 |
| 0.0823 | 3.2267 | 66 |
| 0.0811 | 3.2503 | 67 |
| 0.0823 | 3.1981 | 68 |
| 0.0808 | 3.2618 | 69 |
| 0.0803 | 3.1607 | 70 |
| 0.0786 | 3.3295 | 71 |
| 0.0801 | 3.2952 | 72 |
| 0.0777 | 3.2545 | 73 |
| 0.0764 | 3.1248 | 74 |
| 0.0772 | 3.2185 | 75 |
| 0.0758 | 3.3147 | 76 |
| 0.0764 | 3.1842 | 77 |
| 0.0758 | 3.2346 | 78 |
| 0.0739 | 3.2914 | 79 |
| 0.0738 | 3.2163 | 80 |
| 0.0738 | 3.3555 | 81 |
| 0.0731 | 3.0948 | 82 |
| 0.0726 | 3.2040 | 83 |
| 0.0729 | 3.2187 | 84 |
| 0.0709 | 3.2877 | 85 |
| 0.0703 | 3.3668 | 86 |
| 0.0709 | 3.2290 | 87 |
| 0.0712 | 3.3148 | 88 |
| 0.0697 | 3.2762 | 89 |
| 0.0694 | 3.2083 | 90 |
| 0.0688 | 3.2673 | 91 |
| 0.0694 | 3.2816 | 92 |
| 0.0683 | 3.3135 | 93 |
| 0.0680 | 3.2971 | 94 |
| 0.0681 | 3.2272 | 95 |
| 0.0670 | 3.2317 | 96 |
| 0.0662 | 3.2029 | 97 |
| 0.0656 | 3.2945 | 98 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.1
|
lbtutor/Taxi-v3
|
lbtutor
| 2024-01-27T05:03:06Z
| 0
| 0
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T05:02:58Z
|
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 2.67
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="lbtutor/Taxi-v3", 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"])
```
|
sinhat98/w2v-bert-2.0-japanese-colab-CV16.0
|
sinhat98
| 2024-01-27T04:58:22Z
| 7
| 0
|
transformers
|
[
"transformers",
"safetensors",
"wav2vec2-bert",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_16_0",
"base_model:ylacombe/w2v-bert-2.0",
"base_model:finetune:ylacombe/w2v-bert-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-25T11:20:39Z
|
---
base_model: ylacombe/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_16_0
model-index:
- name: w2v-bert-2.0-japanese-colab-CV16.0
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. -->
# w2v-bert-2.0-japanese-colab-CV16.0
This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_16_0 dataset.
It achieves the following results on the evaluation set:
- Loss: inf
- Cer: 0.3171
## 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: 1
- seed: 42
- gradient_accumulation_steps: 2
- 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: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.2694 | 0.96 | 300 | inf | 0.6823 |
| 2.0595 | 1.93 | 600 | inf | 0.4528 |
| 1.3044 | 2.89 | 900 | inf | 0.3920 |
| 1.0889 | 3.85 | 1200 | inf | 0.3579 |
| 0.7867 | 4.82 | 1500 | inf | 0.3518 |
| 0.4371 | 5.78 | 1800 | inf | 0.3371 |
| 0.3414 | 6.74 | 2100 | inf | 0.3246 |
| 0.2373 | 7.7 | 2400 | inf | 0.3253 |
| 0.1171 | 8.67 | 2700 | inf | 0.3183 |
| 0.0524 | 9.63 | 3000 | inf | 0.3171 |
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
lbtutor/q-FrozenLake-v1-4x4-noSlippery
|
lbtutor
| 2024-01-27T04:56:22Z
| 0
| 0
| null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T04:56:20Z
|
---
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="lbtutor/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"])
```
|
Slava/tiny-bert-sst2-distilled
|
Slava
| 2024-01-27T04:51:14Z
| 101
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google/bert_uncased_L-2_H-128_A-2",
"base_model:finetune:google/bert_uncased_L-2_H-128_A-2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-25T08:06:21Z
|
---
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny-bert-sst2-distilled
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. -->
# tiny-bert-sst2-distilled
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9648
- Accuracy: 0.8245
## 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: 0.0002628217875157273
- train_batch_size: 128
- eval_batch_size: 128
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.5717 | 1.0 | 527 | 2.0086 | 0.8073 |
| 1.2017 | 2.0 | 1054 | 1.8121 | 0.8222 |
| 0.9081 | 3.0 | 1581 | 1.8837 | 0.8177 |
| 0.7559 | 4.0 | 2108 | 1.9089 | 0.8234 |
| 0.6694 | 5.0 | 2635 | 1.9749 | 0.8177 |
| 0.6147 | 6.0 | 3162 | 1.9445 | 0.8257 |
| 0.5729 | 7.0 | 3689 | 1.9648 | 0.8245 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.1
|
xyfJASON/Diffusion-Models-Implementations
|
xyfJASON
| 2024-01-27T04:47:02Z
| 0
| 0
| null |
[
"tensorboard",
"dataset:cifar10",
"license:mit",
"region:us"
] | null | 2023-08-10T03:37:36Z
|
---
license: mit
datasets:
- cifar10
metrics:
- fid
---
Checkpoints and training logs for GitHub repository: [xyfJASON/Diffusion-Models-Implementations](https://github.com/xyfJASON/Diffusion-Models-Implementations).
|
jeiku/NewJeans_3.43B_GGUF
|
jeiku
| 2024-01-27T04:41:32Z
| 7
| 0
| null |
[
"gguf",
"mergekit",
"merge",
"arxiv:2203.05482",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-01-27T03:54:51Z
|
---
base_model:
- jeiku/Gnosis_StableLM
tags:
- mergekit
- merge
---
# longfinal
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* long2 + [jeiku/Gnosis_StableLM](https://huggingface.co/jeiku/Gnosis_StableLM)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: linear
models:
- model: long2+jeiku/Gnosis_StableLM
parameters:
weight: 1
dtype: float16
```
|
Yankz/TR_Model-1st-Mistral-7B
|
Yankz
| 2024-01-27T04:29:14Z
| 1
| 0
|
peft
|
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:LeoLM/leo-mistral-hessianai-7b-chat",
"base_model:adapter:LeoLM/leo-mistral-hessianai-7b-chat",
"license:apache-2.0",
"region:us"
] | null | 2024-01-26T16:29:08Z
|
---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: LeoLM/leo-mistral-hessianai-7b-chat
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 [LeoLM/leo-mistral-hessianai-7b-chat](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b-chat) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6241
## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- 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: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.6723 | 0.99 | 62 | 2.6241 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
ycros/llmTechChat-GGUF
|
ycros
| 2024-01-27T04:19:23Z
| 9
| 0
| null |
[
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-01-27T03:31:59Z
|
GGUF quants of https://huggingface.co/Epiculous/llmTechChat
|
ramsi-k/Taxi-v3-3
|
ramsi-k
| 2024-01-27T04:13:18Z
| 0
| 0
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T04:09:42Z
|
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3-3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="ramsi-k/Taxi-v3-3", 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"])
```
|
ramsi-k/Taxi-v3-2
|
ramsi-k
| 2024-01-27T04:06:57Z
| 0
| 0
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T04:06:53Z
|
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3-2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="ramsi-k/Taxi-v3-2", 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"])
```
|
intervitens/internlm2-limarp-chat-20b
|
intervitens
| 2024-01-27T04:03:56Z
| 12
| 2
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"en",
"dataset:lemonilia/LimaRP",
"arxiv:2212.04089",
"base_model:intervitens/internlm2-base-20b-llama",
"base_model:finetune:intervitens/internlm2-base-20b-llama",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T03:41:35Z
|
---
base_model: [intervitens/internlm2-base-20b-llama]
language:
- en
pipeline_tag: text-generation
tags:
- mergekit
- merge
license: other
datasets:
- lemonilia/LimaRP
---
Experimental model, LimaRP LoRA trained on top of internlm2-base-20b with 8192 context length and merged with internlm2-chat-20b.
Prompt format is ChatML.
***
# internlm2-06limarp-1chat-TASK_ARITHM-20b-v0.03
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using intervitens/internlm2-base-20b-llama as a base.
### Models Merged
The following models were included in the merge:
* ./internlm2-limarp-20b-v0.03
* ./internlm2-chat-20b-llama
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: ./internlm2-chat-20b-llama
parameters:
weight: 1.0
- model: ./internlm2-limarp-20b-v0.03
parameters:
weight: 0.6
merge_method: task_arithmetic
base_model: ./internlm2-base-20b-llama
parameters:
#normalize: false
#int8_mask: true
dtype: bfloat16
```
|
jeiku/NewJeans_3.43B
|
jeiku
| 2024-01-27T03:53:33Z
| 90
| 0
|
transformers
|
[
"transformers",
"safetensors",
"stablelm_epoch",
"text-generation",
"mergekit",
"merge",
"conversational",
"custom_code",
"arxiv:2203.05482",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2024-01-27T03:30:32Z
|
---
base_model:
- jeiku/Gnosis_StableLM
tags:
- mergekit
- merge
---
# longfinal
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* long2 + [jeiku/Gnosis_StableLM](https://huggingface.co/jeiku/Gnosis_StableLM)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: linear
models:
- model: long2+jeiku/Gnosis_StableLM
parameters:
weight: 1
dtype: float16
```
|
e22vvb/EN_mt5-base_15_wikiSQL
|
e22vvb
| 2024-01-27T03:43:23Z
| 1
| 0
|
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"dataset:wikisql",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-26T19:12:19Z
|
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wikisql
model-index:
- name: EN_mt5-base_15_wikiSQL
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. -->
# EN_mt5-base_15_wikiSQL
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the wikisql dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0849
- Rouge2 Precision: 0.8692
- Rouge2 Recall: 0.7928
- Rouge2 Fmeasure: 0.8234
## 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: 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: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
| 0.1534 | 1.0 | 4049 | 0.1157 | 0.8319 | 0.756 | 0.7858 |
| 0.1204 | 2.0 | 8098 | 0.0980 | 0.8469 | 0.7706 | 0.8011 |
| 0.1006 | 3.0 | 12147 | 0.0926 | 0.855 | 0.7775 | 0.8086 |
| 0.0892 | 4.0 | 16196 | 0.0881 | 0.8579 | 0.7811 | 0.8119 |
| 0.0809 | 5.0 | 20245 | 0.0857 | 0.8605 | 0.7839 | 0.8145 |
| 0.0725 | 6.0 | 24294 | 0.0849 | 0.8643 | 0.787 | 0.8181 |
| 0.0672 | 7.0 | 28343 | 0.0841 | 0.8662 | 0.7889 | 0.8199 |
| 0.0628 | 8.0 | 32392 | 0.0847 | 0.8657 | 0.7895 | 0.82 |
| 0.0589 | 9.0 | 36441 | 0.0835 | 0.8676 | 0.7909 | 0.8216 |
| 0.0565 | 10.0 | 40490 | 0.0839 | 0.8685 | 0.7914 | 0.8223 |
| 0.0532 | 11.0 | 44539 | 0.0837 | 0.8689 | 0.7925 | 0.8231 |
| 0.051 | 12.0 | 48588 | 0.0844 | 0.8692 | 0.7927 | 0.8233 |
| 0.0504 | 13.0 | 52637 | 0.0848 | 0.869 | 0.7924 | 0.8231 |
| 0.0485 | 14.0 | 56686 | 0.0848 | 0.869 | 0.7928 | 0.8233 |
| 0.0479 | 15.0 | 60735 | 0.0849 | 0.8692 | 0.7928 | 0.8234 |
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.7.dev0
- Tokenizers 0.13.3
|
ramsi-k/Taxi-v3
|
ramsi-k
| 2024-01-27T03:42:08Z
| 0
| 0
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T03:42:05Z
|
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="ramsi-k/Taxi-v3", 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"])
```
|
benjamin-paine/ccsr
|
benjamin-paine
| 2024-01-27T03:28:08Z
| 0
| 2
| null |
[
"license:apache-2.0",
"region:us"
] | null | 2024-01-27T02:37:28Z
|
---
license: apache-2.0
---
This repository contains a copy of `real-world-ccsr.ckpt`. See documentation for CCSR at https://github.com/csslc/CCSR/
|
chathuranga-jayanath/codet5-small-v4
|
chathuranga-jayanath
| 2024-01-27T03:24:52Z
| 92
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:Salesforce/codet5-small",
"base_model:finetune:Salesforce/codet5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2024-01-27T03:24:26Z
|
---
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- generated_from_trainer
model-index:
- name: codet5-small-v4
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. -->
# codet5-small-v4
This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7318
- Bleu Score: 0.2737
- Gen Len: 13.7838
## 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: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu Score | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:----------:|:-------:|
| No log | 1.0 | 20 | 1.7693 | 0.281 | 13.5946 |
| No log | 2.0 | 40 | 1.0720 | 0.2706 | 13.9189 |
| No log | 3.0 | 60 | 0.7318 | 0.2737 | 13.7838 |
### Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
AnonWilber/ppo-LunarLander-v2
|
AnonWilber
| 2024-01-27T03:20:44Z
| 0
| 0
|
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T03:20:15Z
|
---
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: 150.50 +/- 71.47
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
...
```
|
LN1996/peft-qlora-run3
|
LN1996
| 2024-01-27T03:16:44Z
| 0
| 0
|
peft
|
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/phi-2",
"base_model:adapter:microsoft/phi-2",
"region:us"
] | null | 2024-01-27T03:16:12Z
|
---
library_name: peft
base_model: microsoft/phi-2
---
# 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 0.7.2.dev0
|
rishikasrinivas/distilbert-base-uncased-finetuned-ner
|
rishikasrinivas
| 2024-01-27T02:54:49Z
| 92
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"token-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"
] |
token-classification
| 2024-01-26T20:00:18Z
|
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
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-base-uncased-finetuned-ner
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: 0.0609
- Precision: 0.9243
- Recall: 0.9358
- F1: 0.9300
- Accuracy: 0.9836
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2386 | 1.0 | 878 | 0.0710 | 0.9017 | 0.9207 | 0.9111 | 0.9798 |
| 0.0498 | 2.0 | 1756 | 0.0619 | 0.9239 | 0.9319 | 0.9279 | 0.9830 |
| 0.0308 | 3.0 | 2634 | 0.0609 | 0.9243 | 0.9358 | 0.9300 | 0.9836 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T02:51:01Z
| 34
| 1
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"fblgit/una-cybertron-7b-v3-OMA",
"juanako",
"UNA",
"cybertron",
"xaberius",
"dataset:fblgit/tree-of-knowledge",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"base_model:MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T02:42:21Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- fblgit/una-cybertron-7b-v3-OMA
- juanako
- UNA
- cybertron
- xaberius
- dataset:fblgit/tree-of-knowledge
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- region:us
model_name: una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./una-cybertron-7b-v3-OMA-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
egiorh/distilbert-base-uncased-finetuned-emotion
|
egiorh
| 2024-01-27T02:49:24Z
| 92
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-24T06:39:32Z
|
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
config: split
split: validation
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9245
- name: F1
type: f1
value: 0.9245690662037136
---
<!-- 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-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2192
- Accuracy: 0.9245
- F1: 0.9246
## 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: 64
- eval_batch_size: 64
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8375 | 1.0 | 250 | 0.3221 | 0.907 | 0.9059 |
| 0.255 | 2.0 | 500 | 0.2192 | 0.9245 | 0.9246 |
### Framework versions
- Transformers 4.37.0
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0
|
AustinMcMike/mosaic-fintune-test
|
AustinMcMike
| 2024-01-27T02:45:03Z
| 0
| 0
|
transformers
|
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-01-27T02:44:59Z
|
---
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]
|
MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T02:35:50Z
| 42
| 0
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"Dans-DiscountModels/Dans-07YahooAnswers-7b",
"pytorch",
"question-answering",
"en",
"dataset:PocketDoc/Retro-YahooAnswers",
"base_model:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"base_model:MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T02:26:55Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- Dans-DiscountModels/Dans-07YahooAnswers-7b
- pytorch
- question-answering
- en
- dataset:PocketDoc/Retro-YahooAnswers
- base_model:mistralai/Mistral-7B-v0.1
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- region:us
model_name: Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./Dans-07YahooAnswers-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
Sirnoha/Therenderer
|
Sirnoha
| 2024-01-27T02:28:35Z
| 4
| 0
|
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:artistic-2.0",
"region:us"
] |
text-to-image
| 2024-01-27T02:28:28Z
|
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
output:
url: images/download-5.jpeg
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: null
license: artistic-2.0
---
# Renderer
<Gallery />
## Download model
Weights for this model are available in Safetensors format.
[Download](/Sirnoha/Therenderer/tree/main) them in the Files & versions tab.
|
mbearss/dummy-model
|
mbearss
| 2024-01-27T02:27:15Z
| 93
| 0
|
transformers
|
[
"transformers",
"safetensors",
"camembert",
"fill-mask",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2024-01-27T02:25:45Z
|
---
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]
|
balrogbob/MiniBOB
|
balrogbob
| 2024-01-27T02:22:37Z
| 33
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T00:39:11Z
|
---
tags:
- generated_from_trainer
model-index:
- name: MiniBOB
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. -->
# MiniBOB
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown 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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T02:18:15Z
| 60
| 0
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"lcw99/zephykor-ko-beta-7b-chang",
"ko",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"license:apache-2.0",
"base_model:MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T02:09:24Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- lcw99/zephykor-ko-beta-7b-chang
- ko
- en
- autotrain_compatible
- endpoints_compatible
- region:us
- license:apache-2.0
model_name: zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./zephykor-ko-beta-7b-chang-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T02:00:41Z
| 57
| 1
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"CobraMamba/mamba-gpt-7b-v1",
"pytorch",
"gpt",
"llm",
"large language model",
"en",
"license:apache-2.0",
"autotrain_compatible",
"region:us",
"endpoints_compatible",
"base_model:MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T01:51:51Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- CobraMamba/mamba-gpt-7b-v1
- pytorch
- gpt
- llm
- large language model
- en
- license:apache-2.0
- autotrain_compatible
- region:us
- endpoints_compatible
model_name: mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./mamba-gpt-7b-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
Crystalcareai/NeuralPipe-7B-slerp
|
Crystalcareai
| 2024-01-27T01:56:12Z
| 0
| 0
| null |
[
"merge",
"mergekit",
"lazymergekit",
"OpenPipe/mistral-ft-optimized-1218",
"mlabonne/NeuralHermes-2.5-Mistral-7B",
"base_model:OpenPipe/mistral-ft-optimized-1218",
"base_model:merge:OpenPipe/mistral-ft-optimized-1218",
"base_model:mlabonne/NeuralHermes-2.5-Mistral-7B",
"base_model:merge:mlabonne/NeuralHermes-2.5-Mistral-7B",
"region:us"
] | null | 2024-01-27T01:56:12Z
|
---
tags:
- merge
- mergekit
- lazymergekit
- OpenPipe/mistral-ft-optimized-1218
- mlabonne/NeuralHermes-2.5-Mistral-7B
base_model:
- OpenPipe/mistral-ft-optimized-1218
- mlabonne/NeuralHermes-2.5-Mistral-7B
---
# NeuralPipe-7B-slerp
NeuralPipe-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
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
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Crystalcareai/NeuralPipe-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
shamalshaikh/LunarLander
|
shamalshaikh
| 2024-01-27T01:54:39Z
| 0
| 0
|
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T01:54:13Z
|
---
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: 247.17 +/- 21.84
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
...
```
|
phaeeza/whisper-small-ha
|
phaeeza
| 2024-01-27T01:47:22Z
| 61
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_16_1",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-26T23:34:55Z
|
---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_16_1
metrics:
- wer
model-index:
- name: whisper-small-ha
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_16_1
type: common_voice_16_1
config: ha
split: test
args: ha
metrics:
- name: Wer
type: wer
value: 44.116527037319116
---
<!-- 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. -->
# whisper-small-ha
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_16_1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7536
- Wer Ortho: 47.2867
- Wer: 44.1165
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
| 0.0713 | 3.18 | 500 | 0.6989 | 49.6836 | 46.2300 |
| 0.0145 | 6.37 | 1000 | 0.7536 | 47.2867 | 44.1165 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
not-lain/whisper-small-dv
|
not-lain
| 2024-01-27T01:47:16Z
| 92
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:PolyAI/minds14",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-26T22:20:18Z
|
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-small-dv
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
config: en-US
split: train
args: en-US
metrics:
- name: Wer
type: wer
value: 0.27390791027154666
---
<!-- 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. -->
# whisper-small-dv
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5904
- Wer Ortho: 0.267119
- Wer: 0.273908
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
| 0.0002 | 17.24 | 500 | 0.5904 | 0.267119 | 0.273908 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
andrewatef/MyBloggerV0.20-GGUF
|
andrewatef
| 2024-01-27T01:47:00Z
| 2
| 0
|
transformers
|
[
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"mistral",
"en",
"base_model:unsloth/zephyr-sft-bnb-4bit",
"base_model:quantized:unsloth/zephyr-sft-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-01-27T01:23:05Z
|
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
base_model: unsloth/zephyr-sft-bnb-4bit
---
# Uploaded model
- **Developed by:** andrewatef
- **License:** apache-2.0
- **Finetuned from model :** unsloth/zephyr-sft-bnb-4bit
This mistral 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)
|
MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T01:45:00Z
| 54
| 0
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"OpenBuddy/openbuddy-zephyr-7b-v14.1",
"pytorch",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"ru",
"license:apache-2.0",
"autotrain_compatible",
"region:us",
"endpoints_compatible",
"base_model:MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T01:36:15Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- OpenBuddy/openbuddy-zephyr-7b-v14.1
- pytorch
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
- license:apache-2.0
- autotrain_compatible
- region:us
- endpoints_compatible
model_name: openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./openbuddy-zephyr-7b-v14.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
sqiangcao/sd-class-butterflies-64
|
sqiangcao
| 2024-01-27T01:43:38Z
| 45
| 0
|
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2024-01-27T01:42:39Z
|
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('sqiangcao/sd-class-butterflies-64')
image = pipeline().images[0]
image
```
|
MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T01:29:05Z
| 47
| 1
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"bofenghuang/vigostral-7b-chat",
"pytorch",
"LLM",
"finetuned",
"fr",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"base_model:MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T01:20:22Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- bofenghuang/vigostral-7b-chat
- pytorch
- LLM
- finetuned
- fr
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- region:us
model_name: vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./vigostral-7b-chat-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
ntc-ai/SDXL-LoRA-slider.cinematic-lighting
|
ntc-ai
| 2024-01-27T01:28:52Z
| 76
| 9
|
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion-xl",
"lora",
"template:sd-lora",
"template:sdxl-lora",
"sdxl-sliders",
"ntcai.xyz-sliders",
"concept",
"en",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:mit",
"region:us"
] |
text-to-image
| 2024-01-27T01:28:49Z
|
---
language:
- en
thumbnail: "images/evaluate/cinematic lighting.../cinematic lighting_17_3.0.png"
widget:
- text: cinematic lighting
output:
url: images/cinematic lighting_17_3.0.png
- text: cinematic lighting
output:
url: images/cinematic lighting_19_3.0.png
- text: cinematic lighting
output:
url: images/cinematic lighting_20_3.0.png
- text: cinematic lighting
output:
url: images/cinematic lighting_21_3.0.png
- text: cinematic lighting
output:
url: images/cinematic lighting_22_3.0.png
tags:
- text-to-image
- stable-diffusion-xl
- lora
- template:sd-lora
- template:sdxl-lora
- sdxl-sliders
- ntcai.xyz-sliders
- concept
- diffusers
license: "mit"
inference: false
instance_prompt: "cinematic lighting"
base_model: "stabilityai/stable-diffusion-xl-base-1.0"
---
# ntcai.xyz slider - cinematic lighting (SDXL LoRA)
| Strength: -3 | Strength: 0 | Strength: 3 |
| --- | --- | --- |
| <img src="images/cinematic lighting_17_-3.0.png" width=256 height=256 /> | <img src="images/cinematic lighting_17_0.0.png" width=256 height=256 /> | <img src="images/cinematic lighting_17_3.0.png" width=256 height=256 /> |
| <img src="images/cinematic lighting_19_-3.0.png" width=256 height=256 /> | <img src="images/cinematic lighting_19_0.0.png" width=256 height=256 /> | <img src="images/cinematic lighting_19_3.0.png" width=256 height=256 /> |
| <img src="images/cinematic lighting_20_-3.0.png" width=256 height=256 /> | <img src="images/cinematic lighting_20_0.0.png" width=256 height=256 /> | <img src="images/cinematic lighting_20_3.0.png" width=256 height=256 /> |
## Download
Weights for this model are available in Safetensors format.
## Trigger words
You can apply this LoRA with trigger words for additional effect:
```
cinematic lighting
```
## Use in diffusers
```python
from diffusers import StableDiffusionXLPipeline
from diffusers import EulerAncestralDiscreteScheduler
import torch
pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors")
pipe.to("cuda")
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
# Load the LoRA
pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.cinematic-lighting', weight_name='cinematic lighting.safetensors', adapter_name="cinematic lighting")
# Activate the LoRA
pipe.set_adapters(["cinematic lighting"], adapter_weights=[2.0])
prompt = "medieval rich kingpin sitting in a tavern, cinematic lighting"
negative_prompt = "nsfw"
width = 512
height = 512
num_inference_steps = 10
guidance_scale = 2
image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0]
image.save('result.png')
```
## Support the Patreon
If you like this model please consider [joining our Patreon](https://www.patreon.com/NTCAI).
By joining our Patreon, you'll gain access to an ever-growing library of over 1140+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities.
Your support on Patreon will allow us to continue developing and refining new models.
## Other resources
- [CivitAI](https://civitai.com/user/ntc) - Follow ntc on Civit for even more LoRAs
- [ntcai.xyz](https://ntcai.xyz) - See ntcai.xyz to find more articles and LoRAs
|
akjindal53244/Arithmo-Mistral-7B
|
akjindal53244
| 2024-01-27T01:15:58Z
| 1,541
| 61
|
transformers
|
[
"transformers",
"pytorch",
"mistral",
"text-generation",
"Mathematical Reasoning",
"en",
"dataset:akjindal53244/Arithmo-Data",
"arxiv:2309.12284",
"arxiv:2309.05653",
"arxiv:2210.17517",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-14T23:56:46Z
|
---
license: apache-2.0
language:
- en
tags:
- Mathematical Reasoning
datasets:
- akjindal53244/Arithmo-Data
---
## [January 2024] New Model Release: Arithmo2-Mistral-7B
**Arithmo2-Mistral-7B** model improves initially released Arithmo-Mistral-7B model on both GSM8K and MATH benchmarks. Specifically, there is **absolute** improvement of:
- +1.7% on GSM8K
- +3.0% on GSM8K PoT
- +1.9% on MATH
<b>Note</b>: <span style="color:red"><b>It is recommended to use Arithmo2-Mistral-7B model</b></span>. Here is the [merged model](https://huggingface.co/upaya07/Arithmo2-Mistral-7B) and corresponding [LoRA Adapter](https://huggingface.co/upaya07/Arithmo2-Mistral-7B-adapter).
# Model Card for Model ID
[](CODE_LICENSE)
[](LICENSE)
[](https://www.python.org/downloads/release/python-390/)
**P.S.:** Please reach out to [Ashvini Jindal](https://www.linkedin.com/in/ashvini-jindal-26653262/) if you would be interested in supporting compute need. We are looking for small-scale support so we'd appreciate any kind of help! :)
## Model Details
Arithmo-Mistral-7B is trained to reason and answer mathematical problems and is also capable of writing a Python program that upon execution prints answer to the question. We used [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base model and used **QLoRA to fine-tune it on a single RTX 4090 GPU**.
### Model Description
- **Project GitHub Page:** https://github.com/akjindal53244/Arithmo-Mistral-7B
- **Developed by:** [Ashvini Kumar Jindal](https://www.linkedin.com/in/ashvini-jindal-26653262/), [Ankur Parikh](https://www.linkedin.com/in/ankurnlpexpert/)
- **Funded by:** self-work
- **Model type:** fine-tuned
- **Language(s) (NLP):** English
- **Finetuned from model:** mistralai/Mistral-7B-v0.1
## Results
Arithmo-Mistral-7B outperforms existing 7B and 13B state-of-the-art Mathematical Reasoning models. Refer to [Comparing Arithmo-Mistral-7B with other LLM models](https://github.com/akjindal53244/Arithmo-Mistral-7B/tree/master#comparing-arithmo-mistral-7b-with-other-llm-models) section for more details.
<table>
<thead>
<tr>
<th>Prompt Approach</th>
<th>GSM8k</th>
<th>MATH</th>
</tr>
</thead>
<tbody>
<tr>
<td>Zero-Shot CoT</td>
<td><b>74.7</b></td>
<td><b>25.3</b></td>
</tr>
<tr>
<td>Zero-Shot PoT</td>
<td><b>71.2</b></td>
<td>-</td>
</tr>
</tbody>
</table>
- **Zero-Shot CoT**: On providing a question as prompt, model generates reasoning steps to solve the question along with answer. We check if answer matches with ground-truth.
- **Zero-Shot PoT**: We prompt the model to generate a Python program for the given question. During inference, we execute the Python program generated by the model and check if the program output matches with ground-truth answer.
## Installation
```
pip install transformers >=4.34.0
pip install accelerate
pip install sentencepiece
pip install protobuf
# If you are GPU poor like me
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
# If you have a GPU.
pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu118
pip install scipy
pip install bitsandbytes
```
## How to query the model
```
# Set `run_model_on_gpu` to `False` if you are running on CPU. Model will generate reasoning steps with answer for your question. If you want to generate Python program, uncomment line-69 that adds a Python prompt.
# This script automatically does formatting for you, so you just need to type question (eg: `What is 2+2?`) without any prefix like `Question:`, etc.**
$ python query_model.py
```
**Note:** Above script automatically does formatting for you, so you just need to type question (eg: `What is 2+2?`) without any prefix like `Question:`, etc. Checkout [query_model.py](https://github.com/akjindal53244/Arithmo-Mistral-7B/blob/master/query_model.py) for more details. <br><br>
##### Sample Input:
```
Question: There are total 10 children. I have to give 1 apple to first child, 2 apples to second child, 3 apples to third child, and so on. How many apples do I need?
```
##### Model Output:
```
Answer: The total number of apples needed is the sum of the first 10 positive integers.
This can be calculated using the formula for the sum of an arithmetic series:
\[S = \frac{n}{2}(a_1 + a_n),\]
where $S$ is the sum, $n$ is the number of terms, $a_1$ is the first term, and $a_n$ is the last term.
In this case, $n = 10$, $a_1 = 1$, and $a_n = 10$.
Plugging these values into the formula, we get:
\[S = \frac{10}{2}(1 + 10) = 5(11) = \boxed{55}.\]
The answer is: 55
```
Arithmo-Mistral-7B is trained with the following format:
#### CoT Format (generate reasoning steps with answer):
```
Question: <question>
Answer:
```
#### PoT Format (generate a python program):
```
Question: <question> <python_prompt>
Answer:
```
It will perform best if queried in this way with your own script.
## Comparing Arithmo-Mistral-7B with other LLM models.
Results for all models except `Arithmo-Mistral-7B` are taken from [MetaMath](https://github.com/meta-math/MetaMath/blob/main/README.MD) repository.
| Model | GSM8k Pass@1 | MATH Pass@1 |
|---------------------|--------------|-------------|
| MPT-7B | 6.8 | 3.0 |
| Falcon-7B | 6.8 | 2.3 |
| LLaMA-1-7B | 11.0 | 2.9 |
| LLaMA-2-7B | 14.6 | 2.5 |
| MPT-30B | 15.2 | 3.1 |
| LLaMA-1-13B | 17.8 | 3.9 |
| GPT-Neo-2.7B | 19.5 | -- |
| Falcon-40B | 19.6 | 2.5 |
| Baichuan-chat-13B | 23.9 | -- |
| Vicuna-v1.3-13B | 27.6 | -- |
| LLaMA-2-13B | 28.7 | 3.9 |
| InternLM-7B | 31.2 | -- |
| ChatGLM-2-6B | 32.4 | -- |
| GPT-J-6B | 34.9 | -- |
| LLaMA-1-33B | 35.6 | 3.9 |
| LLaMA-2-34B | 42.2 | 6.24 |
| RFT-7B | 50.3 | -- |
| LLaMA-1-65B | 50.9 | 10.6 |
| Qwen-7B | 51.6 | -- |
| WizardMath-7B | 54.9 | 10.7 |
| LLaMA-2-70B | 56.8 | 13.5 |
| WizardMath-13B | 63.9 | 14.0 |
| MetaMath-7B | 66.5 | 19.8 |
| MetaMath-13B | 72.3 | 22.4 |
| 🔥 **Arithmo-Mistral-7B Zero-Shot PoT** | **71.2** | -- |
| 🔥 **Arithmo-Mistral-7B Zero-Shot CoT** | **74.7** | **25.3** |
| WizardMath-70B | **81.6** | 22.7 |
| MetaMath-70B | **82.3** | **26.6** |
If you are interested in reproducing the resullts, visit https://github.com/akjindal53244/Arithmo-Mistral-7B#reproducing-results section.
### Support My Work
Building LLMs takes time and resources; if you find my work interesting, your support would be epic!
<a href="https://www.buymeacoffee.com/a_little_learner" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
### Citation
To cite Arithmo models:
```
@misc{jindal_2023_arithmo,
author = {Jindal, Ashvini},
title = {Arithmo-Mistral-7B: Mathematical Reasoning Model},
howpublished = {Hugging Face},
month = {October},
year = {2023},
url = {https://huggingface.co/akjindal53244/Arithmo-Mistral-7B}
}
```
<h2 id="References">References</h2>
```
@article{yu2023metamath,
title={MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models},
author={Yu, Longhui and Jiang, Weisen and Shi, Han and Yu, Jincheng and Liu, Zhengying and Zhang, Yu and Kwok, James T and Li, Zhenguo and Weller, Adrian and Liu, Weiyang},
journal={arXiv preprint arXiv:2309.12284},
year={2023}
}
@article{Yue2023mammoth,
title={MAmmoTH: Building math generalist models through hybrid instruction tuning},
author={Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen},
journal={arXiv preprint arXiv:2309.05653},
year={2023}
}
@article{mishra2022lila,
title={Lila: A unified benchmark for mathematical reasoning},
author={Swaroop Mishra, Matthew Finlayson, Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, and Ashwin Kalyan},
journal={arXiv preprint arXiv:2210.17517},
year={2022}
}
```
|
afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF
|
afrideva
| 2024-01-27T01:10:17Z
| 5
| 0
| null |
[
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_xs",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0",
"text-generation",
"base_model:NickyNicky/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3",
"base_model:quantized:NickyNicky/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3",
"region:us"
] |
text-generation
| 2024-01-27T01:06:52Z
|
---
base_model: NickyNicky/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3
inference: false
model_creator: NickyNicky
model_name: LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- gguf
- ggml
- quantized
- q2_k
- q3_k_xs
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
---
# NickyNicky/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF
Quantized GGUF model files for [LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3](https://huggingface.co/NickyNicky/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3) from [NickyNicky](https://huggingface.co/NickyNicky)
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.fp16.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.fp16.gguf) | fp16 | 496.82 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q2_k.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q2_k.gguf) | q2_k | 105.46 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q3_k_xs.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q3_k_xs.gguf) | q3_k_xs | 115.32 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q3_k_m.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q3_k_m.gguf) | q3_k_m | 129.03 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q4_k_m.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q4_k_m.gguf) | q4_k_m | 155.67 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q5_k_m.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q5_k_m.gguf) | q5_k_m | 179.23 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q6_k.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q6_k.gguf) | q6_k | 204.26 MB |
| [locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q8_0.gguf](https://huggingface.co/afrideva/LocutusqueXFelladrin-TinyMistral248M-Instruct_oasst2_chatML_V1_DPO_V3-GGUF/resolve/main/locutusquexfelladrin-tinymistral248m-instruct_oasst2_chatml_v1_dpo_v3.q8_0.gguf) | q8_0 | 264.33 MB |
## Original Model Card:
|
ambrosfitz/neural-history-chat-v1.5_q8
|
ambrosfitz
| 2024-01-27T01:05:11Z
| 2
| 0
| null |
[
"gguf",
"text-generation",
"en",
"dataset:ambrosfitz/mighty-history-merge",
"dataset:ambrosfitz/textbook-openstax-yawp-merge",
"license:cc",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-27T00:47:19Z
|
---
license: cc
datasets:
- ambrosfitz/mighty-history-merge
- ambrosfitz/textbook-openstax-yawp-merge
language:
- en
pipeline_tag: text-generation
---
|
asun17904/imdb-t5-base-a1b2
|
asun17904
| 2024-01-27T01:01:24Z
| 1
| 0
|
pytorch
|
[
"pytorch",
"t5",
"en",
"license:mit",
"region:us"
] | null | 2024-01-25T19:10:33Z
|
---
language: en
license: mit
library_name: pytorch
---
# Knowledge Continuity Regularized Network
Trainer Hyperparameters:
- `lr` = 5e-05
- `per_device_batch_size` = 8
- `gradient_accumulation_steps` = 2
- `weight_decay` = 1e-09
- `seed` = 42
Regularization Hyperparameters
- `numerical stability denominator constant` = 0.01
- `lambda` = 0.02
- `alpha` = 1.0
- `beta` = 2.0
Extended Logs:
|eval_loss|eval_accuracy|epoch|
|--|--|--|
|11.994|0.936|1.0|
|11.877|0.941|2.0|
|11.963|0.939|3.0|
|11.879|0.941|4.0|
|11.783|0.945|5.0|
|11.723|0.946|6.0|
|11.880|0.941|7.0|
|11.739|0.946|8.0|
|11.663|0.948|9.0|
|11.671|0.948|10.0|
|11.658|0.948|11.0|
|11.637|0.949|12.0|
|11.687|0.948|13.0|
|11.685|0.948|14.0|
|11.804|0.944|15.0|
|11.721|0.947|16.0|
|11.607|0.950|17.0|
|11.713|0.947|18.0|
|11.683|0.948|19.0|
|11.658|0.949|20.0|
|11.636|0.949|21.0|
|11.700|0.947|22.0|
|11.601|0.950|23.0|
|11.821|0.944|24.0|
|11.587|0.951|25.0|
|11.623|0.950|26.0|
|11.640|0.949|27.0|
|11.627|0.950|28.0|
|11.621|0.950|29.0|
|11.651|0.949|30.0|
|11.597|0.951|31.0|
|11.650|0.949|32.0|
|11.651|0.949|33.0|
|11.642|0.949|34.0|
|11.637|0.949|35.0|
|11.593|0.951|36.0|
|11.615|0.950|37.0|
|11.594|0.951|38.0|
|11.646|0.949|39.0|
|11.631|0.950|40.0|
|11.635|0.949|41.0|
|11.605|0.950|42.0|
|11.629|0.949|43.0|
|11.638|0.949|44.0|
|11.586|0.951|45.0|
|11.591|0.951|46.0|
|11.609|0.950|47.0|
|11.607|0.950|48.0|
|11.604|0.950|49.0|
|
andrewatef/MyBloggerV0.20
|
andrewatef
| 2024-01-27T01:00:40Z
| 4
| 0
|
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/zephyr-sft-bnb-4bit",
"base_model:quantized:unsloth/zephyr-sft-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2024-01-27T00:33:39Z
|
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/zephyr-sft-bnb-4bit
---
# Uploaded model
- **Developed by:** andrewatef
- **License:** apache-2.0
- **Finetuned from model :** unsloth/zephyr-sft-bnb-4bit
This mistral 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)
|
Hafeez7000/Talk-ai-small
|
Hafeez7000
| 2024-01-27T00:56:14Z
| 91
| 0
|
transformers
|
[
"transformers",
"safetensors",
"gpt2",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-11-27T21:16:10Z
|
---
license: apache-2.0
pipeline_tag: text-generation
---
|
asun17904/imdb-gpt2-a2b1l1.0
|
asun17904
| 2024-01-27T00:56:06Z
| 1
| 0
|
pytorch
|
[
"pytorch",
"gpt2",
"en",
"license:mit",
"region:us"
] | null | 2024-01-26T06:21:36Z
|
---
language: en
license: mit
library_name: pytorch
---
# Knowledge Continuity Regularized Network
Trainer Hyperparameters:
- `lr` = 5e-05
- `per_device_batch_size` = 8
- `gradient_accumulation_steps` = 2
- `weight_decay` = 1e-09
- `seed` = 42
Regularization Hyperparameters
- `numerical stability denominator constant` = 0.01
- `lambda` = 1.0
- `alpha` = 2.0
- `beta` = 1.0
Extended Logs:
|eval_loss|eval_accuracy|epoch|
|--|--|--|
|7.389|0.892|1.0|
|6.753|0.925|2.0|
|6.567|0.927|3.0|
|6.641|0.926|4.0|
|6.818|0.928|5.0|
|6.492|0.934|6.0|
|6.386|0.932|7.0|
|6.869|0.934|8.0|
|6.730|0.928|9.0|
|6.381|0.927|10.0|
|6.308|0.935|11.0|
|6.305|0.930|12.0|
|6.592|0.931|13.0|
|6.415|0.934|14.0|
|6.477|0.921|15.0|
|6.270|0.933|16.0|
|6.311|0.932|17.0|
|6.255|0.936|18.0|
|6.412|0.935|19.0|
|6.298|0.934|20.0|
|6.390|0.938|21.0|
|6.478|0.933|22.0|
|6.534|0.936|23.0|
|6.919|0.936|24.0|
|6.374|0.933|25.0|
|6.357|0.937|26.0|
|6.519|0.933|27.0|
|6.533|0.926|28.0|
|6.357|0.934|29.0|
|6.197|0.934|30.0|
|6.516|0.934|31.0|
|6.393|0.933|32.0|
|6.099|0.935|33.0|
|6.154|0.936|34.0|
|6.296|0.935|35.0|
|6.204|0.934|36.0|
|6.188|0.938|37.0|
|6.428|0.939|38.0|
|6.397|0.939|39.0|
|6.414|0.940|40.0|
|6.283|0.939|41.0|
|6.351|0.938|42.0|
|6.249|0.940|43.0|
|6.205|0.940|44.0|
|6.125|0.939|45.0|
|6.194|0.941|46.0|
|6.147|0.941|47.0|
|6.219|0.940|48.0|
|6.179|0.941|49.0|
|
mikolaj-mialkowski/q-Taxi-v3
|
mikolaj-mialkowski
| 2024-01-27T00:55:40Z
| 0
| 0
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2024-01-27T00:44:34Z
|
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 382.85 +/- 221.57
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="mikolaj-mialkowski/q-Taxi-v3", 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"])
```
|
MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T00:54:39Z
| 62
| 0
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"CobraMamba/mamba-gpt-7b-v2",
"pytorch",
"gpt",
"llm",
"large language model",
"en",
"license:apache-2.0",
"autotrain_compatible",
"region:us",
"endpoints_compatible",
"base_model:MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T00:45:58Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- CobraMamba/mamba-gpt-7b-v2
- pytorch
- gpt
- llm
- large language model
- en
- license:apache-2.0
- autotrain_compatible
- region:us
- endpoints_compatible
model_name: mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
callum-canavan/whisper-small-ga-1
|
callum-canavan
| 2024-01-27T00:52:44Z
| 62
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"ga",
"dataset:mozilla-foundation/common_voice_13_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2024-01-27T00:52:16Z
|
---
language:
- ga
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
model-index:
- name: Whisper Small Ga 1 - Callum Canavan
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. -->
# Whisper Small Ga 1 - Callum Canavan
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
Hafeez7000/Talk_ai_
|
Hafeez7000
| 2024-01-27T00:52:31Z
| 92
| 0
|
transformers
|
[
"transformers",
"safetensors",
"gpt2",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-26T22:08:46Z
|
---
license: apache-2.0
pipeline_tag: text-generation
---
|
MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T00:23:44Z
| 64
| 1
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"Azure99/blossom-v3-mistral-7b",
"pytorch",
"zh",
"en",
"dataset:Azure99/blossom-chat-v1",
"dataset:Azure99/blossom-math-v2",
"dataset:Azure99/blossom-wizard-v1",
"dataset:Azure99/blossom-orca-v1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"base_model:MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-27T00:11:43Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- Azure99/blossom-v3-mistral-7b
- pytorch
- zh
- en
- dataset:Azure99/blossom-chat-v1
- dataset:Azure99/blossom-math-v2
- dataset:Azure99/blossom-wizard-v1
- dataset:Azure99/blossom-orca-v1
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- region:us
model_name: blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./blossom-v3-mistral-7b-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
Hafeez7000/talkAI
|
Hafeez7000
| 2024-01-27T00:22:53Z
| 90
| 1
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"conversational",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-26T23:19:14Z
|
---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: talkAI
results: []
pipeline_tag: conversational
---
<!-- 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. -->
# talkAI
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown 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-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: 10.0
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.1
|
mimicheng/zephyr-7b-sft-qlora-1ep-25jan
|
mimicheng
| 2024-01-27T00:10:40Z
| 20
| 0
|
peft
|
[
"peft",
"safetensors",
"mixtral",
"dpo-experiment",
"generated_from_trainer",
"trl",
"sft",
"dataset:HuggingFaceH4/ultrachat_200k",
"base_model:mistralai/Mixtral-8x7B-v0.1",
"base_model:adapter:mistralai/Mixtral-8x7B-v0.1",
"license:apache-2.0",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2024-01-26T02:19:25Z
|
---
license: apache-2.0
library_name: peft
tags:
- dpo-experiment
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrachat_200k
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: zephyr-7b-sft-qlora-1ep-25jan
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. -->
# zephyr-7b-sft-qlora-1ep-25jan
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
It achieves the following results on the evaluation set:
- Loss: nan
## 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: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.0 | 1.0 | 17428 | nan |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0
|
MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-27T00:05:18Z
| 54
| 0
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"ignos/Mistral-T5-7B-v1",
"pytorch",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"base_model:MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-26T23:56:28Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- ignos/Mistral-T5-7B-v1
- pytorch
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- region:us
model_name: Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./Mistral-T5-7B-v1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
Bytes512/Queen
|
Bytes512
| 2024-01-26T23:57:45Z
| 5
| 0
|
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:01-ai/Yi-34B-200K",
"base_model:merge:01-ai/Yi-34B-200K",
"base_model:NousResearch/Nous-Hermes-2-Yi-34B",
"base_model:merge:NousResearch/Nous-Hermes-2-Yi-34B",
"base_model:abacusai/Smaug-34B-v0.1",
"base_model:merge:abacusai/Smaug-34B-v0.1",
"base_model:jondurbin/bagel-34b-v0.2",
"base_model:merge:jondurbin/bagel-34b-v0.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-26T23:47:18Z
|
---
base_model:
- abacusai/Smaugv0.1
- NousResearch/Nous-Hermes-2-Yi-34B
- jondurbin/bagel-34b-v0.2
- 01-ai/Yi-34B-200K
tags:
- mergekit
- merge
---
# queen
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) as a base.
### Models Merged
The following models were included in the merge:
* [abacusai/Smaugv0.1](https://huggingface.co/abacusai/Smaugv0.1)
* [NousResearch/Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B)
* [jondurbin/bagel-34b-v0.2](https://huggingface.co/jondurbin/bagel-34b-v0.2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: 01-ai/Yi-34B-200K
# No parameters necessary for base model
- model: abacusai/Smaugv0.1
parameters:
density: 0.53
weight: 0.3
- model: jondurbin/bagel-34b-v0.2
parameters:
density: 0.53
weight: 0.3
- model: NousResearch/Nous-Hermes-2-Yi-34B
parameters:
density: 0.53
weight: 0.4
merge_method: dare_ties
base_model: 01-ai/Yi-34B-200K
parameters:
int8_mask: true
dtype: bfloat16
```
|
MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF
|
MaziyarPanahi
| 2024-01-26T23:50:36Z
| 57
| 0
|
transformers
|
[
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"Safetensors",
"text-generation-inference",
"merge",
"7b",
"mistralai/Mistral-7B-Instruct-v0.1",
"WizardLM/WizardMath-7B-V1.1",
"pytorch",
"en",
"arxiv:2304.12244",
"arxiv:2306.08568",
"arxiv:2308.09583",
"autotrain_compatible",
"region:us",
"license:apache-2.0",
"endpoints_compatible",
"base_model:MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1",
"base_model:quantized:MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1",
"conversational"
] |
text-generation
| 2024-01-26T23:39:09Z
|
---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- Safetensors
- text-generation-inference
- merge
- 7b
- mistralai/Mistral-7B-Instruct-v0.1
- WizardLM/WizardMath-7B-V1.1
- pytorch
- en
- arxiv:2304.12244
- arxiv:2306.08568
- arxiv:2308.09583
- autotrain_compatible
- region:us
- license:apache-2.0
- endpoints_compatible
model_name: WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF
base_model: MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1)
## Description
[MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### 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.
* [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.
* [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.
* [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.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [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.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF) and below it, a specific filename to download, such as: WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./WizardMath-7B-V1.1-Mistral-7B-Instruct-v0.1-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
|
varun-v-rao/t5-large-bn-adapter-6.34M-snli
|
varun-v-rao
| 2024-01-26T23:49:09Z
| 0
| 0
|
adapter-transformers
|
[
"adapter-transformers",
"tensorboard",
"t5",
"dataset:snli",
"region:us"
] | null | 2024-01-26T07:06:06Z
|
---
tags:
- adapter-transformers
- t5
datasets:
- snli
---
# Adapter `varun-v-rao/t5-large-bn-adapter-6.34M-snli` for t5-large
An [adapter](https://adapterhub.ml) for the `t5-large` model that was trained on the [snli](https://huggingface.co/datasets/snli/) dataset.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("t5-large")
adapter_name = model.load_adapter("varun-v-rao/t5-large-bn-adapter-6.34M-snli", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here -->
|
izh97/zephyr-climate-change-assistant
|
izh97
| 2024-01-26T23:35:16Z
| 0
| 0
| null |
[
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TheBloke/zephyr-7B-alpha-GPTQ",
"base_model:finetune:TheBloke/zephyr-7B-alpha-GPTQ",
"license:mit",
"region:us"
] | null | 2024-01-24T16:49:10Z
|
---
license: mit
base_model: TheBloke/zephyr-7B-alpha-GPTQ
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: zephyr-climate-change-assistant
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. -->
# zephyr-climate-change-assistant
This model is a fine-tuned version of [TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ) on the None 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 17190
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
yihang7/phi-2-dpo-full-hydrox-safe
|
yihang7
| 2024-01-26T23:28:09Z
| 37
| 0
|
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"phi",
"text-generation",
"generated_from_trainer",
"conversational",
"custom_code",
"base_model:microsoft/phi-2",
"base_model:finetune:microsoft/phi-2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2024-01-25T18:44:24Z
|
---
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: phi-2-dpo-full-hydrox-safe
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-dpo-full-hydrox-safe
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0050
- Rewards/chosen: -0.0996
- Rewards/rejected: -19.3989
- Rewards/accuracies: 0.9992
- Rewards/margins: 19.2993
- Logps/rejected: -644.0859
- Logps/chosen: -275.4780
- Logits/rejected: 0.2021
- Logits/chosen: -0.3196
## 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-07
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6535 | 0.03 | 100 | 0.6404 | 0.0912 | -0.0433 | 0.6936 | 0.1345 | -450.5297 | -273.5692 | 0.6266 | 0.1056 |
| 0.4293 | 0.07 | 200 | 0.4021 | 0.4957 | -0.4032 | 0.8998 | 0.8989 | -454.1287 | -269.5248 | 0.6425 | 0.1325 |
| 0.2685 | 0.1 | 300 | 0.2464 | 0.8729 | -1.0624 | 0.9386 | 1.9354 | -460.7211 | -265.7526 | 0.6700 | 0.1533 |
| 0.1918 | 0.14 | 400 | 0.1792 | 1.1981 | -1.7756 | 0.9453 | 2.9737 | -467.8528 | -262.5003 | 0.6918 | 0.1719 |
| 0.1409 | 0.17 | 500 | 0.1423 | 1.4079 | -2.4222 | 0.9503 | 3.8301 | -474.3184 | -260.4028 | 0.7139 | 0.1772 |
| 0.1437 | 0.2 | 600 | 0.1232 | 1.6054 | -3.1009 | 0.9537 | 4.7063 | -481.1060 | -258.4279 | 0.7179 | 0.1571 |
| 0.0747 | 0.24 | 700 | 0.1057 | 1.7190 | -3.9721 | 0.9613 | 5.6911 | -489.8179 | -257.2914 | 0.7179 | 0.1325 |
| 0.0848 | 0.27 | 800 | 0.0863 | 1.8540 | -4.3289 | 0.9689 | 6.1829 | -493.3858 | -255.9415 | 0.7047 | 0.1024 |
| 0.0853 | 0.31 | 900 | 0.0744 | 1.8328 | -5.0270 | 0.9722 | 6.8598 | -500.3666 | -256.1535 | 0.6746 | 0.0529 |
| 0.0561 | 0.34 | 1000 | 0.0639 | 1.7736 | -5.4555 | 0.9747 | 7.2291 | -504.6516 | -256.7455 | 0.6517 | 0.0185 |
| 0.0657 | 0.37 | 1100 | 0.0546 | 1.7966 | -5.6453 | 0.9840 | 7.4419 | -506.5500 | -256.5157 | 0.6738 | 0.0168 |
| 0.0445 | 0.41 | 1200 | 0.0499 | 1.7245 | -6.0645 | 0.9823 | 7.7889 | -510.7414 | -257.2369 | 0.6757 | 0.0176 |
| 0.0498 | 0.44 | 1300 | 0.0459 | 1.6804 | -6.6799 | 0.9848 | 8.3603 | -516.8956 | -257.6772 | 0.6719 | 0.0228 |
| 0.0554 | 0.48 | 1400 | 0.0549 | 1.5994 | -6.8731 | 0.9848 | 8.4726 | -518.8279 | -258.4872 | 0.6684 | 0.0151 |
| 0.0368 | 0.51 | 1500 | 0.0365 | 1.3551 | -7.8016 | 0.9865 | 9.1567 | -528.1130 | -260.9311 | 0.6464 | -0.0223 |
| 0.0514 | 0.54 | 1600 | 0.0333 | 1.3431 | -7.5785 | 0.9891 | 8.9215 | -525.8817 | -261.0511 | 0.6617 | -0.0159 |
| 0.0365 | 0.58 | 1700 | 0.0310 | 1.0743 | -8.8130 | 0.9933 | 9.8873 | -538.2264 | -263.7386 | 0.6354 | -0.0234 |
| 0.0214 | 0.61 | 1800 | 0.0300 | 1.1310 | -9.1633 | 0.9924 | 10.2942 | -541.7292 | -263.1721 | 0.6278 | -0.0199 |
| 0.0321 | 0.65 | 1900 | 0.0267 | 0.9514 | -9.9884 | 0.9924 | 10.9399 | -549.9811 | -264.9675 | 0.6044 | -0.0268 |
| 0.0239 | 0.68 | 2000 | 0.0249 | 0.9624 | -10.0608 | 0.9933 | 11.0232 | -550.7047 | -264.8574 | 0.5955 | -0.0628 |
| 0.0484 | 0.71 | 2100 | 0.0222 | 0.9176 | -11.0294 | 0.9941 | 11.9470 | -560.3909 | -265.3055 | 0.6043 | -0.0338 |
| 0.0239 | 0.75 | 2200 | 0.0209 | 0.8247 | -10.5070 | 0.9941 | 11.3317 | -555.1663 | -266.2345 | 0.5913 | -0.0648 |
| 0.0219 | 0.78 | 2300 | 0.0221 | 0.7334 | -10.5131 | 0.9924 | 11.2465 | -555.2272 | -267.1474 | 0.5942 | -0.0808 |
| 0.0168 | 0.82 | 2400 | 0.0200 | 0.8909 | -11.0818 | 0.9966 | 11.9727 | -560.9146 | -265.5724 | 0.6006 | -0.0770 |
| 0.0135 | 0.85 | 2500 | 0.0187 | 0.7273 | -11.3130 | 0.9958 | 12.0403 | -563.2269 | -267.2084 | 0.5948 | -0.0711 |
| 0.0211 | 0.88 | 2600 | 0.0190 | 0.5390 | -11.8492 | 0.9949 | 12.3883 | -568.5890 | -269.0913 | 0.5818 | -0.0719 |
| 0.0209 | 0.92 | 2700 | 0.0170 | 0.4957 | -12.3176 | 0.9949 | 12.8133 | -573.2725 | -269.5249 | 0.5537 | -0.0912 |
| 0.0168 | 0.95 | 2800 | 0.0175 | 0.5850 | -12.2737 | 0.9958 | 12.8587 | -572.8340 | -268.6321 | 0.5471 | -0.0870 |
| 0.0129 | 0.99 | 2900 | 0.0171 | 0.5691 | -12.7785 | 0.9949 | 13.3476 | -577.8817 | -268.7910 | 0.5441 | -0.0810 |
| 0.0134 | 1.02 | 3000 | 0.0188 | 0.3713 | -13.0254 | 0.9966 | 13.3966 | -580.3504 | -270.7691 | 0.5261 | -0.1163 |
| 0.0127 | 1.05 | 3100 | 0.0155 | 0.1769 | -14.3013 | 0.9958 | 14.4782 | -593.1094 | -272.7126 | 0.4928 | -0.1129 |
| 0.0072 | 1.09 | 3200 | 0.0147 | 0.2474 | -13.6499 | 0.9975 | 13.8973 | -586.5952 | -272.0074 | 0.4753 | -0.1479 |
| 0.0068 | 1.12 | 3300 | 0.0179 | 0.2168 | -14.6122 | 0.9958 | 14.8291 | -596.2192 | -272.3131 | 0.4722 | -0.1430 |
| 0.0323 | 1.16 | 3400 | 0.0218 | 0.2536 | -15.9479 | 0.9958 | 16.2015 | -609.5762 | -271.9459 | 0.4159 | -0.1430 |
| 0.0232 | 1.19 | 3500 | 0.0171 | 0.4273 | -14.2304 | 0.9958 | 14.6577 | -592.4003 | -270.2084 | 0.4598 | -0.1410 |
| 0.0112 | 1.22 | 3600 | 0.0165 | 0.3634 | -15.1069 | 0.9966 | 15.4704 | -601.1661 | -270.8472 | 0.4366 | -0.1521 |
| 0.0136 | 1.26 | 3700 | 0.0176 | 0.2922 | -14.4784 | 0.9966 | 14.7706 | -594.8809 | -271.5597 | 0.4553 | -0.1679 |
| 0.0089 | 1.29 | 3800 | 0.0155 | 0.2349 | -14.8970 | 0.9966 | 15.1319 | -599.0669 | -272.1331 | 0.4447 | -0.1721 |
| 0.01 | 1.33 | 3900 | 0.0123 | 0.1309 | -15.3620 | 0.9975 | 15.4930 | -603.7170 | -273.1724 | 0.4180 | -0.1834 |
| 0.0055 | 1.36 | 4000 | 0.0132 | 0.0227 | -16.5037 | 0.9975 | 16.5265 | -615.1339 | -274.2542 | 0.3836 | -0.1899 |
| 0.004 | 1.39 | 4100 | 0.0122 | 0.2637 | -15.2111 | 0.9975 | 15.4748 | -602.2075 | -271.8445 | 0.4087 | -0.1870 |
| 0.0057 | 1.43 | 4200 | 0.0117 | 0.1593 | -16.5411 | 0.9975 | 16.7003 | -615.5074 | -272.8891 | 0.4086 | -0.1518 |
| 0.0041 | 1.46 | 4300 | 0.0113 | -0.0815 | -17.4813 | 0.9975 | 17.3998 | -624.9092 | -275.2963 | 0.3722 | -0.1782 |
| 0.0039 | 1.5 | 4400 | 0.0115 | 0.2051 | -17.4309 | 0.9983 | 17.6359 | -624.4056 | -272.4310 | 0.3445 | -0.1975 |
| 0.0075 | 1.53 | 4500 | 0.0098 | 0.2810 | -15.5168 | 0.9992 | 15.7978 | -605.2650 | -271.6719 | 0.4021 | -0.1980 |
| 0.0034 | 1.56 | 4600 | 0.0123 | 0.2926 | -15.4764 | 0.9992 | 15.7690 | -604.8610 | -271.5560 | 0.4225 | -0.1766 |
| 0.0066 | 1.6 | 4700 | 0.0125 | 0.3192 | -14.8325 | 0.9992 | 15.1517 | -598.4222 | -271.2900 | 0.4068 | -0.2026 |
| 0.0079 | 1.63 | 4800 | 0.0124 | 0.1405 | -15.1594 | 0.9992 | 15.2999 | -601.6904 | -273.0765 | 0.3942 | -0.2089 |
| 0.0063 | 1.67 | 4900 | 0.0108 | -0.1407 | -17.4715 | 0.9975 | 17.3308 | -624.8116 | -275.8886 | 0.3294 | -0.2140 |
| 0.0026 | 1.7 | 5000 | 0.0116 | -0.0520 | -17.9554 | 0.9992 | 17.9034 | -629.6504 | -275.0013 | 0.3361 | -0.2062 |
| 0.0151 | 1.73 | 5100 | 0.0112 | 0.5727 | -14.3495 | 0.9975 | 14.9221 | -593.5914 | -268.7550 | 0.4234 | -0.1897 |
| 0.0049 | 1.77 | 5200 | 0.0083 | 0.2709 | -15.7593 | 0.9975 | 16.0301 | -607.6893 | -271.7730 | 0.3788 | -0.2054 |
| 0.0036 | 1.8 | 5300 | 0.0093 | 0.2336 | -16.3789 | 0.9992 | 16.6125 | -613.8856 | -272.1456 | 0.3798 | -0.1961 |
| 0.0076 | 1.84 | 5400 | 0.0086 | 0.2618 | -16.1654 | 0.9992 | 16.4272 | -611.7511 | -271.8639 | 0.3844 | -0.2090 |
| 0.0028 | 1.87 | 5500 | 0.0079 | 0.3444 | -15.7817 | 0.9983 | 16.1261 | -607.9135 | -271.0378 | 0.3874 | -0.2135 |
| 0.0102 | 1.9 | 5600 | 0.0081 | 0.3276 | -15.7265 | 0.9983 | 16.0541 | -607.3622 | -271.2061 | 0.3713 | -0.2243 |
| 0.0051 | 1.94 | 5700 | 0.0072 | 0.3979 | -15.8670 | 0.9983 | 16.2649 | -608.7670 | -270.5030 | 0.3562 | -0.2429 |
| 0.0068 | 1.97 | 5800 | 0.0069 | 0.2817 | -16.7894 | 0.9992 | 17.0711 | -617.9911 | -271.6647 | 0.3329 | -0.2424 |
| 0.0021 | 2.01 | 5900 | 0.0061 | 0.0725 | -17.3567 | 0.9992 | 17.4292 | -623.6634 | -273.7564 | 0.3142 | -0.2479 |
| 0.0031 | 2.04 | 6000 | 0.0066 | -0.0179 | -18.1905 | 0.9983 | 18.1726 | -632.0013 | -274.6606 | 0.2948 | -0.2445 |
| 0.0032 | 2.07 | 6100 | 0.0064 | 0.0140 | -17.8441 | 0.9992 | 17.8581 | -628.5374 | -274.3414 | 0.3043 | -0.2424 |
| 0.0043 | 2.11 | 6200 | 0.0066 | 0.0216 | -18.5824 | 0.9983 | 18.6041 | -635.9210 | -274.2653 | 0.2863 | -0.2416 |
| 0.0033 | 2.14 | 6300 | 0.0070 | 0.0355 | -18.3245 | 0.9983 | 18.3600 | -633.3419 | -274.1270 | 0.2783 | -0.2691 |
| 0.0036 | 2.18 | 6400 | 0.0065 | 0.1473 | -18.2292 | 0.9983 | 18.3765 | -632.3882 | -273.0083 | 0.2772 | -0.2744 |
| 0.0023 | 2.21 | 6500 | 0.0064 | 0.0450 | -17.9052 | 0.9992 | 17.9502 | -629.1483 | -274.0311 | 0.2750 | -0.2756 |
| 0.0025 | 2.24 | 6600 | 0.0061 | -0.0642 | -17.4265 | 0.9983 | 17.3623 | -624.3619 | -275.1237 | 0.2773 | -0.2881 |
| 0.0008 | 2.28 | 6700 | 0.0058 | 0.0951 | -17.3710 | 0.9992 | 17.4661 | -623.8071 | -273.5309 | 0.2703 | -0.2891 |
| 0.002 | 2.31 | 6800 | 0.0057 | -0.0533 | -18.2744 | 0.9992 | 18.2212 | -632.8410 | -275.0142 | 0.2544 | -0.2823 |
| 0.0052 | 2.35 | 6900 | 0.0073 | 0.0152 | -18.6276 | 0.9983 | 18.6427 | -636.3723 | -274.3301 | 0.2365 | -0.2928 |
| 0.0029 | 2.38 | 7000 | 0.0056 | 0.0321 | -18.4600 | 0.9992 | 18.4921 | -634.6968 | -274.1606 | 0.2366 | -0.2889 |
| 0.0013 | 2.41 | 7100 | 0.0058 | -0.1304 | -19.1740 | 0.9983 | 19.0436 | -641.8367 | -275.7859 | 0.2306 | -0.2898 |
| 0.0011 | 2.45 | 7200 | 0.0059 | -0.0977 | -19.2699 | 0.9992 | 19.1722 | -642.7958 | -275.4590 | 0.2227 | -0.2916 |
| 0.0058 | 2.48 | 7300 | 0.0059 | -0.0938 | -18.8625 | 0.9992 | 18.7687 | -638.7216 | -275.4195 | 0.2314 | -0.2945 |
| 0.004 | 2.52 | 7400 | 0.0067 | -0.1457 | -19.2264 | 0.9992 | 19.0807 | -642.3610 | -275.9389 | 0.2194 | -0.2959 |
| 0.0042 | 2.55 | 7500 | 0.0056 | -0.0100 | -18.6009 | 0.9992 | 18.5909 | -636.1058 | -274.5812 | 0.2398 | -0.3003 |
| 0.0033 | 2.58 | 7600 | 0.0057 | -0.1484 | -19.3114 | 0.9992 | 19.1630 | -643.2104 | -275.9655 | 0.2215 | -0.2965 |
| 0.0012 | 2.62 | 7700 | 0.0051 | -0.1574 | -19.2398 | 0.9992 | 19.0824 | -642.4946 | -276.0552 | 0.2210 | -0.3052 |
| 0.002 | 2.65 | 7800 | 0.0052 | -0.1220 | -19.5223 | 0.9992 | 19.4004 | -645.3201 | -275.7011 | 0.2102 | -0.3165 |
| 0.0053 | 2.69 | 7900 | 0.0051 | -0.1063 | -19.6889 | 0.9992 | 19.5826 | -646.9856 | -275.5444 | 0.2106 | -0.3074 |
| 0.0013 | 2.72 | 8000 | 0.0056 | -0.1357 | -19.8339 | 0.9992 | 19.6982 | -648.4356 | -275.8386 | 0.2029 | -0.3129 |
| 0.002 | 2.75 | 8100 | 0.0050 | -0.1024 | -19.6476 | 0.9992 | 19.5452 | -646.5726 | -275.5056 | 0.1993 | -0.3168 |
| 0.0016 | 2.79 | 8200 | 0.0052 | -0.0378 | -19.4058 | 0.9992 | 19.3680 | -644.1544 | -274.8596 | 0.2152 | -0.3120 |
| 0.0015 | 2.82 | 8300 | 0.0049 | -0.0549 | -19.2544 | 0.9992 | 19.1994 | -642.6404 | -275.0310 | 0.2093 | -0.3168 |
| 0.003 | 2.86 | 8400 | 0.0051 | -0.1218 | -19.2614 | 0.9983 | 19.1396 | -642.7106 | -275.7000 | 0.2057 | -0.3182 |
| 0.0019 | 2.89 | 8500 | 0.0050 | -0.1057 | -19.3041 | 0.9992 | 19.1983 | -643.1373 | -275.5387 | 0.2077 | -0.3151 |
| 0.0039 | 2.92 | 8600 | 0.0052 | -0.0863 | -19.2826 | 0.9992 | 19.1963 | -642.9229 | -275.3445 | 0.2057 | -0.3208 |
| 0.0042 | 2.96 | 8700 | 0.0048 | -0.1111 | -19.3837 | 0.9992 | 19.2726 | -643.9339 | -275.5926 | 0.2008 | -0.3215 |
| 0.0023 | 2.99 | 8800 | 0.0050 | -0.1085 | -19.4076 | 0.9992 | 19.2990 | -644.1723 | -275.5668 | 0.1985 | -0.3228 |
### Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1
|
Professor/CGIAR
|
Professor
| 2024-01-26T23:27:59Z
| 27
| 0
|
transformers
|
[
"transformers",
"safetensors",
"swin",
"image-classification",
"generated_from_trainer",
"base_model:gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease",
"base_model:finetune:gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-12-12T14:13:08Z
|
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease
model-index:
- name: CGIAR
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. -->
# CGIAR
This model is a fine-tuned version of [gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease](https://huggingface.co/gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7888
- Accuracy: 0.6571
## 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: 0.001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.0123 | 1.0 | 652 | 0.8818 | 0.6178 |
| 0.8619 | 2.0 | 1304 | 0.8398 | 0.6346 |
| 0.8324 | 3.0 | 1956 | 0.8233 | 0.6366 |
| 0.7872 | 4.0 | 2608 | 0.7888 | 0.6571 |
### Framework versions
- Transformers 4.37.1
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0
|
Santhoshi29/Checkpoints_prisma
|
Santhoshi29
| 2024-01-26T23:15:23Z
| 0
| 0
| null |
[
"region:us"
] | null | 2024-01-20T17:41:42Z
|
## CIFAR-10 Results
In our CIFAR-10 experiment, we aimed to assess the performance of Mice ViTs on a more complex and diverse dataset, CIFAR-10. We trained mice ViTs on classifying the 10 classes.
## Training Details
For each attention layer setting, we explored two model variants: an attention-only model and a model combining attention with the MLP module. Dropout and layer normalization were not applied for simplicity.
| Size | NumLayers | Attention Only | Attention+MLP |
|--------|-----------|-----------------|---------------|
| tiny | 1 | 0.43 | 0.479 |
| base | 2 | 0.47 | 0.54 |
| small | 3 | 0.47 | 0.51 |
| medium | 4 | 0.47 | 0.52 |
|
hbpkillerX/phi-1_5-finetuned-gsm8k
|
hbpkillerX
| 2024-01-26T22:37:39Z
| 0
| 0
| null |
[
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:Open-Orca/oo-phi-1_5",
"base_model:finetune:Open-Orca/oo-phi-1_5",
"region:us"
] | null | 2024-01-26T22:24:01Z
|
---
base_model: Open-Orca/oo-phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-gsm8k
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-1_5-finetuned-gsm8k
This model is a fine-tuned version of [Open-Orca/oo-phi-1_5](https://huggingface.co/Open-Orca/oo-phi-1_5) on the None 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 1000
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
Seher99/emotion-analysis-with-distilbert
|
Seher99
| 2024-01-26T22:29:20Z
| 47
| 0
|
transformers
|
[
"transformers",
"tf",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2024-01-26T22:19:43Z
|
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Seher99/emotion-analysis-with-distilbert
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Seher99/emotion-analysis-with-distilbert
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:
- Train Loss: 0.3838
- Validation Loss: 0.1765
- Train Accuracy: 0.933
- Epoch: 0
## 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:
- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.3838 | 0.1765 | 0.933 | 0 |
### Framework versions
- Transformers 4.28.0
- TensorFlow 2.10.1
- Datasets 2.16.1
- Tokenizers 0.13.3
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.