modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-07-15 00:43:56
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 521
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-07-15 00:40:56
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
csocsci/mt5-base-multi-label-all-cs-iv | csocsci | 2023-09-24T05:14:00Z | 117 | 0 | transformers | [
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"multilingual",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-09-22T13:25:13Z | ---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
license: mit
language:
- multilingual
---
# Model Card for mt5-base-multi-label-all-cs-iv
<!-- Provide a quick summary of what the model is/does. -->
This model is fine-tuned for multi-label seq2seq text classification of Supportive Interactions in Instant Messenger dialogs of Adolescents.
## Model Description
The model was fine-tuned on a dataset of Czech Instant Messenger dialogs of Adolescents. The classification is multi-label. For each of the utterances in the input, the model outputs any combination of the tags:'NO TAG', 'Informační podpora', 'Emocionální podpora', 'Začlenění do skupiny', 'Uznání', 'Nabídka pomoci': as a string joined with ', ' (ordered alphabetically). Each label indicates the presence of that category of Supportive Interactions: 'no tag', 'informational support', 'emocional support', 'social companionship', 'appraisal', 'instrumental support' in each of the utterances of the input. The inputs of the model is a sequence of utterances joined with ';'. The outputs are a sequence of per-utterance labels such as: 'NO TAG; Informační podpora, Uznání; NO TAG'
- **Developed by:** Anonymous
- **Language(s):** multilingual
- **Finetuned from:** mt5-base
## Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/chi2024submission
- **Paper:** Stay tuned!
## Usage
Here is how to use this model to classify a context-window of a dialogue:
```python
import itertools
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import torch
# Target dialog context window
test_texts = ['Utterance1;Utterance2;Utterance3']
# Load the model and tokenizer
checkpoint_path = "chi2024/mt5-base-multi-label-all-cs-iv"
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint_path)\
.to("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained(checkpoint_path)
# Define helper functions
def predict_one(text):
inputs = tokenizer(text, return_tensors="pt", padding=True,
truncation=True, max_length=256).to(model.device)
outputs = model.generate(**inputs)
decoded = [text.split(",")[0].strip() for text in
tokenizer.batch_decode(outputs, skip_special_tokens=True)]
predicted_sequence = list(
itertools.chain(*(pred_one.split("; ") for pred_one in decoded)))
return predicted_sequence
# Run the prediction
dec = predict_one(test_texts[0])
print(dec)
``` |
GRPUI/model-667 | GRPUI | 2023-09-24T05:07:06Z | 94 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"longformer",
"text-classification",
"autotrain",
"unk",
"dataset:GRPUI/autotrain-data-fdsdfsdf",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-09-24T05:02:43Z | ---
tags:
- autotrain
- text-classification
language:
- unk
widget:
- text: "I love AutoTrain"
datasets:
- GRPUI/autotrain-data-fdsdfsdf
co2_eq_emissions:
emissions: 2.6373045356411247
---
# Model Trained Using AutoTrain
- Problem type: Multi-class Classification
- Model ID: 91139144447
- CO2 Emissions (in grams): 2.6373
## Validation Metrics
- Loss: 2.596
- Accuracy: 0.834
- Macro F1: 0.776
- Micro F1: 0.834
- Weighted F1: 0.803
- Macro Precision: 0.815
- Micro Precision: 0.834
- Weighted Precision: 0.820
- Macro Recall: 0.791
- Micro Recall: 0.834
- Weighted Recall: 0.834
## Usage
You can use cURL to access this model:
```
$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/GRPUI/autotrain-fdsdfsdf-91139144447
```
Or Python API:
```
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("GRPUI/autotrain-fdsdfsdf-91139144447", use_auth_token=True)
tokenizer = AutoTokenizer.from_pretrained("GRPUI/autotrain-fdsdfsdf-91139144447", use_auth_token=True)
inputs = tokenizer("I love AutoTrain", return_tensors="pt")
outputs = model(**inputs)
``` |
wangrongsheng/careinternlm-20B-Chat-sft-multi | wangrongsheng | 2023-09-24T05:05:31Z | 3 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-24T05:04:30Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
CyberHarem/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord | CyberHarem | 2023-09-24T04:57:40Z | 0 | 0 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-24T04:33:23Z | ---
license: mit
datasets:
- CyberHarem/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord
pipeline_tag: text-to-image
tags:
- art
---
# Lora of tamaki_iroha_puellamagimadokamagicasidestorymagiarecord
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 9800, you need to download `9800/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.pt` as the embedding and `9800/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 9800**, with the score of 0.987. The trigger words are:
1. `tamaki_iroha_puellamagimadokamagicasidestorymagiarecord`
2. `pink_hair, pink_eyes, bangs, blunt_bangs, braid, sidelocks, blush, bow, long_hair`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:-------------------------------------------|:---------------------------------------------------|:---------------------------------------|:---------------------------------------|:---------------------------------------|:------------------------------------------------|:-------------------------------------------------|:---------------------------------------|:-------------------------------------------|
| 10500 | 0.986 | [Download](10500/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](10500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](10500/previews/nude.png) | [<NSFW, click to see>](10500/previews/nude2.png) |  |  |
| **9800** | **0.987** | [**Download**](9800/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9800/previews/nude.png) | [<NSFW, click to see>](9800/previews/nude2.png) |  |  |
| 9100 | 0.984 | [Download](9100/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9100/previews/nude.png) | [<NSFW, click to see>](9100/previews/nude2.png) |  |  |
| 8400 | 0.985 | [Download](8400/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8400/previews/nude.png) | [<NSFW, click to see>](8400/previews/nude2.png) |  |  |
| 7700 | 0.983 | [Download](7700/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7700/previews/nude.png) | [<NSFW, click to see>](7700/previews/nude2.png) |  |  |
| 7000 | 0.981 | [Download](7000/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7000/previews/nude.png) | [<NSFW, click to see>](7000/previews/nude2.png) |  |  |
| 6300 | 0.985 | [Download](6300/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6300/previews/nude.png) | [<NSFW, click to see>](6300/previews/nude2.png) |  |  |
| 5600 | 0.982 | [Download](5600/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5600/previews/nude.png) | [<NSFW, click to see>](5600/previews/nude2.png) |  |  |
| 4900 | 0.977 | [Download](4900/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4900/previews/nude.png) | [<NSFW, click to see>](4900/previews/nude2.png) |  |  |
| 4200 | 0.932 | [Download](4200/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4200/previews/nude.png) | [<NSFW, click to see>](4200/previews/nude2.png) |  |  |
| 3500 | 0.976 | [Download](3500/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3500/previews/nude.png) | [<NSFW, click to see>](3500/previews/nude2.png) |  |  |
| 2800 | 0.967 | [Download](2800/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2800/previews/nude.png) | [<NSFW, click to see>](2800/previews/nude2.png) |  |  |
| 2100 | 0.955 | [Download](2100/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2100/previews/nude.png) | [<NSFW, click to see>](2100/previews/nude2.png) |  |  |
| 1400 | 0.925 | [Download](1400/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1400/previews/nude.png) | [<NSFW, click to see>](1400/previews/nude2.png) |  |  |
| 700 | 0.889 | [Download](700/tamaki_iroha_puellamagimadokamagicasidestorymagiarecord.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](700/previews/nude.png) | [<NSFW, click to see>](700/previews/nude2.png) |  |  |
|
dyaminda/image_classification | dyaminda | 2023-09-24T04:53:00Z | 5 | 0 | transformers | [
"transformers",
"pytorch",
"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 | 2023-09-13T20:43:19Z | ---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: image_classification
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: 0.53125
---
<!-- 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. -->
# image_classification
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: 1.2727
- Accuracy: 0.5312
## 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
- 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.0804 | 1.0 | 10 | 2.0714 | 0.1625 |
| 2.0428 | 2.0 | 20 | 2.0324 | 0.2313 |
| 1.9463 | 3.0 | 30 | 1.8978 | 0.3438 |
| 1.7768 | 4.0 | 40 | 1.7234 | 0.375 |
| 1.6163 | 5.0 | 50 | 1.6029 | 0.4188 |
| 1.509 | 6.0 | 60 | 1.5122 | 0.5 |
| 1.4118 | 7.0 | 70 | 1.4839 | 0.4375 |
| 1.3381 | 8.0 | 80 | 1.4268 | 0.475 |
| 1.2653 | 9.0 | 90 | 1.4095 | 0.4813 |
| 1.1979 | 10.0 | 100 | 1.3504 | 0.5375 |
| 1.1219 | 11.0 | 110 | 1.3293 | 0.4875 |
| 1.0858 | 12.0 | 120 | 1.3023 | 0.4875 |
| 1.0214 | 13.0 | 130 | 1.3063 | 0.5188 |
| 1.0085 | 14.0 | 140 | 1.3306 | 0.5312 |
| 0.9615 | 15.0 | 150 | 1.2838 | 0.5 |
| 0.9277 | 16.0 | 160 | 1.3073 | 0.5125 |
| 0.898 | 17.0 | 170 | 1.2606 | 0.5437 |
| 0.8747 | 18.0 | 180 | 1.3116 | 0.5437 |
| 0.8657 | 19.0 | 190 | 1.3171 | 0.5375 |
| 0.8462 | 20.0 | 200 | 1.2619 | 0.525 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
alreadyamar/ludwig-llama2-coder | alreadyamar | 2023-09-24T04:51:02Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T13:15:11Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
sulthanbasha/my-thar | sulthanbasha | 2023-09-24T04:48:11Z | 7 | 0 | diffusers | [
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-09-24T04:44:23Z | ---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### MY-THAR Dreambooth model trained by sulthanbasha following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: DSIT-91
Sample pictures of this concept:
.png)
.jpg)
.jpg)
.jpg)
.jpg)
|
ccore/Llama-2-8k-2m-rethink | ccore | 2023-09-24T04:24:15Z | 137 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-23T08:42:07Z | ---
base_model: ./model
tags:
- generated_from_trainer
model-index:
- name: output6
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. -->
# output6
This model is a fine-tuned version of [./model](https://huggingface.co/./model) 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: 0.001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0
|
fredchung/ppo-LunarLander-v2 | fredchung | 2023-09-24T04:02:01Z | 1 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T21:46:08Z | ---
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: 277.86 +/- 11.59
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
repo_id = "fredchung/ppo-LunarLander-v2" # The repo_id
filename = "ppo-LunarLander-v2.zip" # The model filename.zip
# For compatibility between pickle protocol 5 vs. 4.
custom_objects = {
"learning_rate": 0.0,
"lr_schedule": lambda _: 0.0,
"clip_range": lambda _: 0.0,
}
checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)
...
```
|
TohidA/LlamaInstructMona | TohidA | 2023-09-24T03:48:20Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-18T23:57:31Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
ZinengTang/CoDi | ZinengTang | 2023-09-24T03:40:08Z | 0 | 53 | null | [
"arxiv:2305.11846",
"license:mit",
"region:us"
]
| null | 2023-05-30T05:30:05Z | ---
license: mit
---
<h1 align="center">CoDi: Any-to-Any Generation via Composable Diffusion</h1>
<div align="center">
<span class="author-block">
<a href="https://zinengtang.github.io/">Zineng Tang</a><sup>1*</sup>,</span>
<span class="author-block">
<a href="https://ziyi-yang.github.io/">Ziyi Yang</a><sup>2†</sup>,</span>
<span class="author-block">
<a href="https://www.microsoft.com/en-us/research/people/chezhu/">Chenguang Zhu</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://www.microsoft.com/en-us/research/people/nzeng/">Michael Zeng</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://www.cs.unc.edu/~mbansal/">Mohit Bansal</a><sup>1†</sup>
</span>
</div>
<div align="center">
<span class="author-block"><sup>1</sup>University of North Carolina at Chapel Hill,</span>
<span class="author-block"><sup>2</sup>Microsoft Azure Cognitive Services Research</span>
<span class="author-block"><sup>*</sup> Work done at Microsoft internship and UNC. <sup>†</sup>Corresponding Authors</span>
</div>
---
Paper link:
[https://arxiv.org/abs/2305.11846](https://arxiv.org/abs/2305.11846)
Open Source Checklist:
- [x] Release Code Structure
- [x] Release Multi-Condition \& Single-Condition Scripts and Checkpoints
- [x] Release Joint-Generation Scripts and Checkpoints
- [ ] Release Web Demo
## Introduction
We present Composable Diffusion (CoDi), a novel generative model capable of generating any combination of output modalities, such as language, image, video, or audio, from any combination of input modalities. Unlike existing generative AI systems, CoDi can generate multiple modalities in parallel and its input is not limited to a subset of modalities like text or image. Despite the absence of training datasets for many combinations of modalities, we propose to align modalities in both the input and output space. This allows CoDi to freely condition on any input combination and generate any group of modalities, even if they are not present in the training data. CoDi employs a novel composable generation strategy which involves building a shared multimodal space by bridging alignment in the diffusion process, enabling the synchronized generation of intertwined modalities, such as temporally aligned video and audio. Highly customizable and flexible, CoDi achieves strong joint-modality generation quality, and outperforms or is on par with the unimodal state-of-the-art for single-modality synthesis.
## Citation
If you find our work useful, please consider citing:
```
@article{tang2023any,
title={Any-to-Any Generation via Composable Diffusion},
author={Tang, Zineng and Yang, Ziyi and Zhu, Chenguang and Zeng, Michael and Bansal, Mohit},
journal={arXiv preprint arXiv:2305.11846},
year={2023}
}
```
## Contact
Zineng Tang ([email protected])
|
fastbond/llama-2-7b-finetune-GEM_viggo-packed594-2 | fastbond | 2023-09-24T03:33:05Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-24T03:33:01Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
|
felixquinihildebet/Reinforce-PixelCopter | felixquinihildebet | 2023-09-24T03:19:56Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-24T03:19:45Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-PixelCopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 70.40 +/- 66.69
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
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
|
lancewilhelm/distilbert-finetune-sentiment | lancewilhelm | 2023-09-24T03:08:45Z | 105 | 0 | transformers | [
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-09-23T00:09:21Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-finetune-sentiment
results: []
datasets:
- imdb
---
<!-- 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-finetune-sentiment
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: 0.2222
- Accuracy: 0.9414
- F1: 0.9429
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3 |
TohidA/LlamaMona | TohidA | 2023-09-24T02:34:42Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-18T22:34:21Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
fastbond/llama-2-7b-finetune-GEM_viggo-packed594 | fastbond | 2023-09-24T02:01:56Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-24T02:01:52Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
|
pnm/Taxi-v3 | pnm | 2023-09-24T01:58:31Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-24T00:34:53Z | ---
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="pnm/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"])
```
|
CzarnyRycerz/rl_course_vizdoom_health_gathering_supreme | CzarnyRycerz | 2023-09-24T01:24:03Z | 0 | 0 | sample-factory | [
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-24T01:23:55Z | ---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 9.39 +/- 3.90
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r CzarnyRycerz/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
natrajanv/distilbert-base-uncased-finetuned-emotion | natrajanv | 2023-09-24T01:22:33Z | 104 | 0 | transformers | [
"transformers",
"pytorch",
"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 | 2023-09-23T18:13:09Z | ---
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: 0.923
- name: F1
type: f1
value: 0.922772205894511
---
<!-- 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: 0.2124
- Accuracy: 0.923
- F1: 0.9228
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.7972 | 1.0 | 250 | 0.3023 | 0.908 | 0.9071 |
| 0.2441 | 2.0 | 500 | 0.2124 | 0.923 | 0.9228 |
### Framework versions
- Transformers 4.33.2
- Pytorch 1.12.1
- Datasets 2.14.1
- Tokenizers 0.13.3
|
Axel578/phi-1_5-finetuned-dialogstudio | Axel578 | 2023-09-23T22:59:53Z | 0 | 0 | null | [
"generated_from_trainer",
"base_model:microsoft/phi-1_5",
"base_model:finetune:microsoft/phi-1_5",
"license:other",
"region:us"
]
| null | 2023-09-23T22:22:14Z | ---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-dialogstudio
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-dialogstudio
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2118
## 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: cosine
- num_epochs: 12
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
schnabear/DialoGPT-medium-FinalFantasyDialogue | schnabear | 2023-09-23T22:53:52Z | 137 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:microsoft/DialoGPT-medium",
"base_model:finetune:microsoft/DialoGPT-medium",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-23T19:12:25Z | ---
license: mit
base_model: microsoft/DialoGPT-medium
tags:
- generated_from_trainer
model-index:
- name: DialoGPT-medium-FinalFantasyDialogue
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. -->
# DialoGPT-medium-FinalFantasyDialogue
This model is a fine-tuned version of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3830
## 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: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.5572 | 1.0 | 282 | 2.2660 |
| 1.9013 | 2.0 | 565 | 1.7536 |
| 1.6648 | 3.0 | 847 | 1.5819 |
| 1.3933 | 4.0 | 1130 | 1.2777 |
| 0.8024 | 5.0 | 1413 | 0.8038 |
| 0.5416 | 6.0 | 1695 | 0.5897 |
| 0.3418 | 7.0 | 1978 | 0.4679 |
| 0.224 | 8.0 | 2261 | 0.4045 |
| 0.1648 | 9.0 | 2543 | 0.3789 |
| 0.1342 | 9.98 | 2820 | 0.3830 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Koshti10/BART_large_Synthetic_Gameplan | Koshti10 | 2023-09-23T22:30:50Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:Koshti10/BART-large-ET-Synthetic",
"base_model:finetune:Koshti10/BART-large-ET-Synthetic",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-09-23T19:21:35Z | ---
license: apache-2.0
base_model: Koshti10/BART-large-ET-Synthetic
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: BART_large_Synthetic_Gameplan
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. -->
# BART_large_Synthetic_Gameplan
This model is a fine-tuned version of [Koshti10/BART-large-ET-Synthetic](https://huggingface.co/Koshti10/BART-large-ET-Synthetic) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2557
- Rouge1: 38.2255
- Rouge2: 27.7473
- Rougel: 35.4392
- Rougelsum: 35.414
- Gen Len: 19.2554
## 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- label_smoothing_factor: 0.1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
felixquinihildebet/Reinforce-CartPole | felixquinihildebet | 2023-09-23T22:29:28Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T22:29:09Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 336.18 +/- 141.64
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
|
Crataco/AID-Neo-125M | Crataco | 2023-09-23T22:08:02Z | 242 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neo",
"text-generation",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2022-04-28T03:48:27Z | ---
language: en
license: mit
pipeline_tag: text-generation
---
# **UPDATE (2023-09-23):**
This model is obsolete. Thanks to quantization you can run AI Dungeon 2 Classic (a 1.5B model) under equivalent hardware. [See here](https://huggingface.co/Crataco/ggml-ai-dungeon-2-classic).
***
# AID-Neo-125M
## Model description
This model was inspired by -- and finetuned on the same dataset of -- [KoboldAI's GPT-Neo-125M-AID (Mia) model](https://huggingface.co/KoboldAI/GPT-Neo-125M-AID): the AI Dungeon dataset (`text_adventures.txt`). This was to fix a possible oversight in the original model, which was trained with [an unfortunate bug](https://github.com/EricFillion/happy-transformer/issues/283). You could technically consider it a "retraining" of the same model using different software.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0 |
ayoubkirouane/BERT-Emotions-Classifier | ayoubkirouane | 2023-09-23T21:35:59Z | 389,797 | 9 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"en",
"dataset:sem_eval_2018_task_1",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-09-23T18:47:29Z | ---
datasets:
- sem_eval_2018_task_1
language:
- en
library_name: transformers
pipeline_tag: text-classification
---
## Description
The **BERT-Emotions-Classifier** is a fine-tuned **BERT-based** model designed for multi-label emotion classification. It has been trained on the sem_eval_2018_task_1 dataset, which includes text samples labeled with a variety of emotions, including anger, anticipation, disgust, fear, joy, love, optimism, pessimism, sadness, surprise, and trust. The model is capable of classifying text inputs into one or more of these emotion categories.
## Overview
+ **Model Name**: BERT-Emotions-Classifier
+ **Task**: Multi-label emotion classification
+ **Dataset**: sem_eval_2018_task_1
+ **Labels**: ['anger', 'anticipation', 'disgust', 'fear', 'joy', 'love', 'optimism', 'pessimism', 'sadness', 'surprise', 'trust']
+ **Base Model**: BERT (Bidirectional Encoder Representations from Transformers)
### Input Format
The model expects text input in the form of a string.
### Output Format
+ The model provides a list of labels and associated scores, indicating the predicted emotions and their confidence scores.
### Example Applications
+ Emotion analysis in social media posts
+ Sentiment analysis in customer reviews
+ Content recommendation based on emotional context
## Limitations
+ **Limited Emotion Categories**: The BERT-Emotions-Classifier model is trained on a specific set of emotion categories. It may not accurately classify emotions that do not fall within these predefined categories.
+ **Model Performance**: The accuracy of emotion classification depends on the quality and diversity of the training data. The model's performance may vary for text inputs with uncommon or complex emotional expressions.
+ **Bias and Fairness**: Like any machine learning model, the BERT-Emotions-Classifier may exhibit bias in its predictions. Care should be taken to address and mitigate bias in real-world applications to ensure fairness and inclusivity.
+ **Input Length**: The model has limitations on the maximum input text length it can process effectively. Very long texts may be truncated or may not receive accurate classifications.
## Ethical Considerations
When using this model, it's essential to consider the ethical implications of emotion analysis. Ensure that the use of emotional data respects privacy and consent, and avoid making decisions that could have adverse effects based solely on emotion analysis.
## Inference
```python
from transformers import pipeline
# Load the BERT-Emotions-Classifier
classifier = pipeline("text-classification", model="ayoubkirouane/BERT-Emotions-Classifier")
# Input text
text = "Your input text here"
# Perform emotion classification
results = classifier(text)
# Display the classification results
print(results)
``` |
RakoszTv/BakaExcelsior | RakoszTv | 2023-09-23T21:28:31Z | 0 | 2 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2023-09-14T13:42:30Z | ---
license: creativeml-openrail-m
---
|
bisslam/BHN | bisslam | 2023-09-23T21:21:09Z | 0 | 0 | null | [
"license:bigcode-openrail-m",
"region:us"
]
| null | 2023-09-23T21:21:09Z | ---
license: bigcode-openrail-m
---
|
trieudemo11/llama_7b_attrb_cate_4m_12 | trieudemo11 | 2023-09-23T21:12:16Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T21:12:00Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
|
llmcode/whisper-large-v2-polish-100steps | llmcode | 2023-09-23T20:57:14Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T20:57:04Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Thaweewat/wangchanberta-hyperopt-sentiment-01 | Thaweewat | 2023-09-23T20:47:10Z | 172 | 0 | transformers | [
"transformers",
"pytorch",
"camembert",
"text-classification",
"generated_from_trainer",
"th",
"dataset:wisesight_sentiment",
"base_model:airesearch/wangchanberta-base-att-spm-uncased",
"base_model:finetune:airesearch/wangchanberta-base-att-spm-uncased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-09-23T19:58:22Z | ---
base_model: airesearch/wangchanberta-base-att-spm-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_dir
results: []
datasets:
- wisesight_sentiment
language:
- th
---
<!-- 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. -->
# wangchanberta-hyperopt-sentiment-01
This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the Wisesight Sentiment dataset.
The model is optimized for binary sentiment classification tasks, targeting two labels: positive and negative.
It achieves the following results on the evaluation set:
- Loss: 0.3595
- Accuracy: 0.9103
## Model description
This model is intended for Thai language sentiment analysis, specifically designed to classify text as either positive or negative.
## Intended uses & limitations
- The model is only trained to recognize positive and negative sentiments and may not perform well on nuanced or multi-class sentiment tasks.
- The model is specialized for the Thai language and is not intended for multi-language or code-switching scenarios.
## Training and evaluation data
The model is trained on the Wisesight Sentiment dataset, which is a widely-used dataset for Thai NLP tasks.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2.5692051845867925e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 7
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.55 | 250 | 0.3128 | 0.8859 |
| 0.3913 | 1.09 | 500 | 0.2672 | 0.8942 |
| 0.3913 | 1.64 | 750 | 0.2860 | 0.9025 |
| 0.2172 | 2.19 | 1000 | 0.4044 | 0.9060 |
| 0.2172 | 2.74 | 1250 | 0.3738 | 0.9076 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3 |
stacked-summaries/flan-t5-large-samsum | stacked-summaries | 2023-09-23T20:44:24Z | 135 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"summarization",
"en",
"dataset:samsum",
"base_model:google/flan-t5-large",
"base_model:finetune:google/flan-t5-large",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| summarization | 2023-02-20T11:03:01Z | ---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
pipeline_tag: summarization
base_model: google/flan-t5-large
model-index:
- name: stacked-summaries/flan-t5-large-samsum
results:
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: test
metrics:
- type: rouge
value: 49.0095
name: ROUGE-1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGNhY2RhOTg5ZmU4ZGJiMjI1NjUyYWMwYmM2Mzk4MGEwMjk0NDg2OWYxZDdmM2I4NzBmODNiM2JmNTg1MDJhYSIsInZlcnNpb24iOjF9.YinJDLeqzoU_x5uJbGIgq8ZEs36oC3Pzre_vk2juxngBoXCEw54XWjpvVhKKZXeIgc47otucJFtFwAOPEmt9Bw
- type: rouge
value: 25.681
name: ROUGE-2
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDBmNDc4NGMzZGEzYzMzMTFiNzliNjUyYmY0MzNjMmRlMTk4ZTRmZmUxODE0MmY1MjEzOWQ2MGQxMmZmZmQ5MSIsInZlcnNpb24iOjF9.UmRHCmQR5CR-JklBTY1JnjD_Gqz_qMYwdVXhMMvnAynMwAgXkoJZeoxT--usUfdkbqaQ-mLeEvLw7mgNE-NQAw
- type: rouge
value: 41.4474
name: ROUGE-L
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODdiM2IxZTU4NTEyMzlmZDEzYTliZWNjMjM1NTAzMjE5MDY1MDZiZDc2YmE2NzUxOWJhMmQ0NTM5MjRjZjQyMSIsInZlcnNpb24iOjF9.PeJ41sirLWf3HTiJXlSMNoleENJT_X2u4VMkgQTmXMmGkbrONTFbUYwO4qjoQkvyjy8pLA2eQ3Fjm5yAvKrTCQ
- type: rouge
value: 45.1556
name: ROUGE-LSUM
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGFiMGNkZDYxZmVhMDFlNDRlNmQ4YWVlMTk3ODI0ZWQ2MmIzNWFkYjkwOWRlNzkyNGVmYmY5ZTczZDAxYTk3NiIsInZlcnNpb24iOjF9.dsicHh5W4ba8t8eBBcSRUm-HLPlMoRc57XixiOHBCk-82De5u8hH8fsRWbMmaLpobdJ7b3xlIaVfTfMMRoLvBw
- type: loss
value: 1.2201015949249268
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzliODE2YzY2MzMyZDQ4YzdjZmFjNTc2NDU3ZjQwNjYwNTdhZjY1NWViM2VhNDc1MjQzNDkxMDI2MTM5ZjFkYiIsInZlcnNpb24iOjF9.2QdP4Zj2oHCo0HCoGgZy6YdqNJaQ0ri0E2kD7lzYbVmyg35wyGutvRUaXVR6O833gTbsCvM86Gp77qNT9CTyDA
- type: gen_len
value: 17.326
name: gen_len
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWJlNjhjMmUxNWU3MDZlMTUzOWRmM2UwNmU3MjBjODhmMGYxZTUyMmFmMmE0MmU3ZTVkYWY0MDhkMWQ3NTk2MSIsInZlcnNpb24iOjF9.wFaw7DOpESjPu_uW6liHc4XaTwF36ReLLYd-BBFhnZXemE_lGQxmp0O0Vl2DgZz3SSbXonyS4D01G2hYze8qCA
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flan-t5-large-samsum
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1754
- Rouge1: 54.1595
- Rouge2: 29.1081
- Rougel: 45.4989
- Rougelsum: 49.1026
- Gen Len: 28.72
> Note: the stacked version of this model technically does evaluation on a **different** validation set (the stacked one) while this just uses `samsum`.
## Model description
More information needed
## Intended uses & limitations
- Intended for comparison(s) to the [stacked version of this model](https://huggingface.co/stacked-summaries/flan-t5-large-stacked-samsum-1024)
- 1024 token input max
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 17868
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.04
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.2106 | 0.43 | 50 | 1.1889 | 52.5898 | 26.9967 | 43.6944 | 47.9656 | 24.5167 |
| 1.213 | 0.87 | 100 | 1.1760 | 52.4279 | 27.4689 | 43.7873 | 48.0581 | 25.0533 |
| 1.0726 | 1.3 | 150 | 1.1731 | 52.8246 | 26.9524 | 43.7429 | 48.0345 | 25.55 |
| 1.0784 | 1.74 | 200 | 1.1708 | 53.1291 | 27.9056 | 44.2609 | 48.6883 | 26.03 |
| 1.0215 | 2.17 | 250 | 1.1755 | 53.1512 | 27.9475 | 44.1442 | 48.4619 | 27.57 |
| 1.0294 | 2.61 | 300 | 1.1711 | 53.4402 | 28.0126 | 44.5454 | 48.6432 | 25.9033 |
| 1.0016 | 3.04 | 350 | 1.1718 | 53.9395 | 28.3087 | 45.191 | 49.2773 | 26.6133 |
| 0.9576 | 3.48 | 400 | 1.1741 | 53.9004 | 28.3243 | 45.0911 | 48.9182 | 26.33 |
| 0.9739 | 3.91 | 450 | 1.1754 | 53.7049 | 28.419 | 44.8946 | 48.8708 | 27.2433 |
| 0.9505 | 4.35 | 500 | 1.1781 | 53.7142 | 28.1758 | 44.8324 | 48.9498 | 26.8667 |
| 0.9993 | 4.78 | 550 | 1.1784 | 53.87 | 28.2211 | 44.893 | 49.1074 | 27.2167 |
|
stacked-summaries/flan-t5-large-stacked-samsum-1024 | stacked-summaries | 2023-09-23T20:43:51Z | 41 | 10 | transformers | [
"transformers",
"pytorch",
"onnx",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"summarization",
"stacked summaries",
"prompt engineering",
"en",
"dataset:stacked-summaries/stacked-samsum-1024",
"base_model:google/flan-t5-large",
"base_model:quantized:google/flan-t5-large",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| summarization | 2022-12-06T04:53:32Z | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- generated_from_trainer
- summarization
- stacked summaries
- prompt engineering
datasets:
- stacked-summaries/stacked-samsum-1024
metrics:
- rouge
pipeline_tag: summarization
base_model: google/flan-t5-large
model-index:
- name: flan-t5-large-stacked-samsum1024-WIP3
results:
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: test
metrics:
- type: rouge
value: 47.6682
name: ROUGE-1
verified: true
- type: rouge
value: 23.3053
name: ROUGE-2
verified: true
- type: rouge
value: 39.7678
name: ROUGE-L
verified: true
- type: rouge
value: 43.259
name: ROUGE-LSUM
verified: true
- type: loss
value: 2.372586965560913
name: loss
verified: true
- type: gen_len
value: 17.4237
name: gen_len
verified: true
---
# flan-t5-large-stacked-samsum-1024
<a href="https://colab.research.google.com/gist/pszemraj/a4bf61f593ebda9a8db6dc58839d9de4/brief-demo-flan-t5-stacked-samsum.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the `stacked-summaries/stacked-samsum-1024` dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1846
- Rouge1: 57.9637
- Rouge2: 28.7446
- Rougel: 44.3826
- Rougelsum: 54.0399
- Gen Len: 122.77
## Model description
This model card presents a model trained on a stacked dataset that aims to improve summarization by testing the benefits of "task-oriented pretraining". The model is designed to learn how to effectively condense and distill information from text by stacking summaries and separating them into independent concepts. In this way, the model can learn to identify essential information without simply mimicking the style of the dataset summaries.
The token used to identify a new concept in the summary is `[NEXT_CONCEPT]`. You can split an output summary based on this token to see how it split the input text information: `summary_text.split("[NEXT_CONCEPT]")` etc.
## Intended uses & limitations
- max input/output is 1024 tokens
- this is mostly a test because `samsum` is not exactly the best dataset for general-purpose summarization
## Training and evaluation data
See the dataset card linked on this page for info
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 24915
- distributed_type: multi-GPU
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 1.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 0.1195 | 0.17 | 20 | 2.0635 | 57.8829 | 28.7887 | 44.4256 | 54.1299 | 121.8 |
| 0.1084 | 0.35 | 40 | 2.1178 | 58.0416 | 28.6487 | 44.3905 | 54.1557 | 122.893 |
| 0.1019 | 0.52 | 60 | 2.1576 | 57.816 | 28.7069 | 44.4242 | 53.9598 | 120.524 |
| 0.0975 | 0.7 | 80 | 2.1821 | 57.9597 | 28.8178 | 44.4854 | 54.068 | 121.793 |
| 0.0947 | 0.87 | 100 | 2.1846 | 57.9637 | 28.7446 | 44.3826 | 54.0399 | 122.77 |
### Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1 |
pszemraj/long-t5-tglobal-base-sci-simplify | pszemraj | 2023-09-23T20:42:40Z | 166 | 10 | transformers | [
"transformers",
"pytorch",
"onnx",
"safetensors",
"longt5",
"text2text-generation",
"lay summaries",
"paper summaries",
"biology",
"medical",
"summarization",
"en",
"dataset:pszemraj/scientific_lay_summarisation-plos-norm",
"base_model:google/long-t5-tglobal-base",
"base_model:quantized:google/long-t5-tglobal-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| summarization | 2023-04-06T23:40:30Z | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- lay summaries
- paper summaries
- biology
- medical
datasets:
- pszemraj/scientific_lay_summarisation-plos-norm
widget:
- text: large earthquakes along a given fault segment do not occur at random intervals
because it takes time to accumulate the strain energy for the rupture. The rates
at which tectonic plates move and accumulate strain at their boundaries are approximately
uniform. Therefore, in first approximation, one may expect that large ruptures
of the same fault segment will occur at approximately constant time intervals.
If subsequent main shocks have different amounts of slip across the fault, then
the recurrence time may vary, and the basic idea of periodic mainshocks must be
modified. For great plate boundary ruptures the length and slip often vary by
a factor of 2. Along the southern segment of the San Andreas fault the recurrence
interval is 145 years with variations of several decades. The smaller the standard
deviation of the average recurrence interval, the more specific could be the long
term prediction of a future mainshock.
example_title: earthquakes
- text: ' A typical feed-forward neural field algorithm. Spatiotemporal coordinates
are fed into a neural network that predicts values in the reconstructed domain.
Then, this domain is mapped to the sensor domain where sensor measurements are
available as supervision. Class and Section Problems Addressed Generalization
(Section 2) Inverse problems, ill-posed problems, editability; symmetries. Hybrid
Representations (Section 3) Computation & memory efficiency, representation capacity,
editability: Forward Maps (Section 4) Inverse problems Network Architecture (Section
5) Spectral bias, integration & derivatives. Manipulating Neural Fields (Section
6) Edit ability, constraints, regularization. Table 2: The five classes of techniques
in the neural field toolbox each addresses problems that arise in learning, inference,
and control. (Section 3). We can supervise reconstruction via differentiable forward
maps that transform Or project our domain (e.g, 3D reconstruction via 2D images;
Section 4) With appropriate network architecture choices, we can overcome neural
network spectral biases (blurriness) and efficiently compute derivatives and integrals
(Section 5). Finally, we can manipulate neural fields to add constraints and regularizations,
and to achieve editable representations (Section 6). Collectively, these classes
constitute a ''toolbox'' of techniques to help solve problems with neural fields
There are three components in a conditional neural field: (1) An encoder or inference
function € that outputs the conditioning latent variable 2 given an observation
0 E(0) =2. 2 is typically a low-dimensional vector, and is often referred to aS
a latent code Or feature code_ (2) A mapping function 4 between Z and neural field
parameters O: Y(z) = O; (3) The neural field itself $. The encoder € finds the
most probable z given the observations O: argmaxz P(2/0). The decoder maximizes
the inverse conditional probability to find the most probable 0 given Z: arg-
max P(Olz). We discuss different encoding schemes with different optimality guarantees
(Section 2.1.1), both global and local conditioning (Section 2.1.2), and different
mapping functions Y (Section 2.1.3) 2. Generalization Suppose we wish to estimate
a plausible 3D surface shape given a partial or noisy point cloud. We need a suitable
prior over the sur- face in its reconstruction domain to generalize to the partial
observations. A neural network expresses a prior via the function space of its
architecture and parameters 0, and generalization is influenced by the inductive
bias of this function space (Section 5).'
example_title: scientific paper
- text: 'Is a else or outside the cob and tree written being of early client rope
and you have is for good reasons. On to the ocean in Orange for time. By''s the
aggregate we can bed it yet. Why this please pick up on a sort is do and also
M Getoi''s nerocos and do rain become you to let so is his brother is made in
use and Mjulia''s''s the lay major is aging Masastup coin present sea only of
Oosii rooms set to you We do er do we easy this private oliiishs lonthen might
be okay. Good afternoon everybody. Welcome to this lecture of Computational Statistics.
As you can see, I''m not socially my name is Michael Zelinger. I''m one of the
task for this class and you might have already seen me in the first lecture where
I made a quick appearance. I''m also going to give the tortillas in the last third
of this course. So to give you a little bit about me, I''m a old student here
with better Bulman and my research centres on casual inference applied to biomedical
disasters, so that could be genomics or that could be hospital data. If any of
you is interested in writing a bachelor thesis, a semester paper may be mastathesis
about this topic feel for reach out to me. you have my name on models and my email
address you can find in the directory I''d Be very happy to talk about it. you
do not need to be sure about it, we can just have a chat. So with that said, let''s
get on with the lecture. There''s an exciting topic today I''m going to start
by sharing some slides with you and later on during the lecture we''ll move to
the paper. So bear with me for a few seconds. Well, the projector is starting
up. Okay, so let''s get started. Today''s topic is a very important one. It''s
about a technique which really forms one of the fundamentals of data science,
machine learning, and any sort of modern statistics. It''s called cross validation.
I know you really want to understand this topic I Want you to understand this
and frankly, nobody''s gonna leave Professor Mineshousen''s class without understanding
cross validation. So to set the stage for this, I Want to introduce you to the
validation problem in computational statistics. So the problem is the following:
You trained a model on available data. You fitted your model, but you know the
training data you got could always have been different and some data from the
environment. Maybe it''s a random process. You do not really know what it is,
but you know that somebody else who gets a different batch of data from the same
environment they would get slightly different training data and you do not care
that your method performs as well. On this training data. you want to to perform
well on other data that you have not seen other data from the same environment.
So in other words, the validation problem is you want to quantify the performance
of your model on data that you have not seen. So how is this even possible? How
could you possibly measure the performance on data that you do not know The solution
to? This is the following realization is that given that you have a bunch of data,
you were in charge. You get to control how much that your model sees. It works
in the following way: You can hide data firms model. Let''s say you have a training
data set which is a bunch of doubtless so X eyes are the features those are typically
hide and national vector. It''s got more than one dimension for sure. And the
why why eyes. Those are the labels for supervised learning. As you''ve seen before,
it''s the same set up as we have in regression. And so you have this training
data and now you choose that you only use some of those data to fit your model.
You''re not going to use everything, you only use some of it the other part you
hide from your model. And then you can use this hidden data to do validation from
the point of you of your model. This hidden data is complete by unseen. In other
words, we solve our problem of validation.'
example_title: transcribed audio - lecture
- text: 'Transformer-based models have shown to be very useful for many NLP tasks.
However, a major limitation of transformers-based models is its O(n^2)O(n 2) time
& memory complexity (where nn is sequence length). Hence, it''s computationally
very expensive to apply transformer-based models on long sequences n > 512n>512.
Several recent papers, e.g. Longformer, Performer, Reformer, Clustered attention
try to remedy this problem by approximating the full attention matrix. You can
checkout 🤗''s recent blog post in case you are unfamiliar with these models.
BigBird (introduced in paper) is one of such recent models to address this issue.
BigBird relies on block sparse attention instead of normal attention (i.e. BERT''s
attention) and can handle sequences up to a length of 4096 at a much lower computational
cost compared to BERT. It has achieved SOTA on various tasks involving very long
sequences such as long documents summarization, question-answering with long contexts.
BigBird RoBERTa-like model is now available in 🤗Transformers. The goal of this
post is to give the reader an in-depth understanding of big bird implementation
& ease one''s life in using BigBird with 🤗Transformers. But, before going into
more depth, it is important to remember that the BigBird''s attention is an approximation
of BERT''s full attention and therefore does not strive to be better than BERT''s
full attention, but rather to be more efficient. It simply allows to apply transformer-based
models to much longer sequences since BERT''s quadratic memory requirement quickly
becomes unbearable. Simply put, if we would have ∞ compute & ∞ time, BERT''s attention
would be preferred over block sparse attention (which we are going to discuss
in this post).
If you wonder why we need more compute when working with longer sequences, this
blog post is just right for you!
Some of the main questions one might have when working with standard BERT-like
attention include:
Do all tokens really have to attend to all other tokens? Why not compute attention
only over important tokens? How to decide what tokens are important? How to attend
to just a few tokens in a very efficient way? In this blog post, we will try to
answer those questions.
What tokens should be attended to? We will give a practical example of how attention
works by considering the sentence ''BigBird is now available in HuggingFace for
extractive question answering''. In BERT-like attention, every word would simply
attend to all other tokens.
Let''s think about a sensible choice of key tokens that a queried token actually
only should attend to by writing some pseudo-code. Will will assume that the token
available is queried and build a sensible list of key tokens to attend to.
>>> # let''s consider following sentence as an example >>> example = [''BigBird'',
''is'', ''now'', ''available'', ''in'', ''HuggingFace'', ''for'', ''extractive'',
''question'', ''answering'']
>>> # further let''s assume, we''re trying to understand the representation of
''available'' i.e. >>> query_token = ''available'' >>> # We will initialize an
empty `set` and fill up the tokens of our interest as we proceed in this section.
>>> key_tokens = [] # => currently ''available'' token doesn''t have anything
to attend Nearby tokens should be important because, in a sentence (sequence of
words), the current word is highly dependent on neighboring past & future tokens.
This intuition is the idea behind the concept of sliding attention.'
example_title: bigbird blog intro
- text: 'To be fair, you have to have a very high IQ to understand Rick and Morty.
The humour is extremely subtle, and without a solid grasp of theoretical physics
most of the jokes will go over a typical viewer''s head. There''s also Rick''s
nihilistic outlook, which is deftly woven into his characterisation- his personal
philosophy draws heavily from Narodnaya Volya literature, for instance. The fans
understand this stuff; they have the intellectual capacity to truly appreciate
the depths of these jokes, to realise that they''re not just funny- they say something
deep about LIFE. As a consequence people who dislike Rick & Morty truly ARE idiots-
of course they wouldn''t appreciate, for instance, the humour in Rick''s existential
catchphrase ''Wubba Lubba Dub Dub,'' which itself is a cryptic reference to Turgenev''s
Russian epic Fathers and Sons. I''m smirking right now just imagining one of those
addlepated simpletons scratching their heads in confusion as Dan Harmon''s genius
wit unfolds itself on their television screens. What fools.. how I pity them.
😂
And yes, by the way, i DO have a Rick & Morty tattoo. And no, you cannot see it.
It''s for the ladies'' eyes only- and even then they have to demonstrate that
they''re within 5 IQ points of my own (preferably lower) beforehand. Nothin personnel
kid 😎'
example_title: Richard & Mortimer
- text: The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey
building, and the tallest structure in Paris. Its base is square, measuring 125
metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed
the Washington Monument to become the tallest man-made structure in the world,
a title it held for 41 years until the Chrysler Building in New York City was
finished in 1930. It was the first structure to reach a height of 300 metres.
Due to the addition of a broadcasting aerial at the top of the tower in 1957,
it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters,
the Eiffel Tower is the second tallest free-standing structure in France after
the Millau Viaduct.
example_title: eiffel
parameters:
max_length: 64
min_length: 8
no_repeat_ngram_size: 3
early_stopping: true
repetition_penalty: 3.5
encoder_no_repeat_ngram_size: 4
length_penalty: 0.4
num_beams: 4
pipeline_tag: summarization
base_model: google/long-t5-tglobal-base
---
# long-t5-tglobal-base-sci-simplify
<a href="https://colab.research.google.com/gist/pszemraj/f0dc02c4d4a5c7ad1d5bf3953251145d/long-t5-tglobal-base-sci-simplify-plos-example-with-textsum.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
Exploring how well long-document models trained on "lay summaries" of scientific papers generalize.
> A lay summary is a summary of a research paper or scientific study that is written in plain language, without the use of technical jargon, and is designed to be easily understood by non-experts.
## Model description
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the `pszemraj/scientific_lay_summarisation-plos-norm` dataset for two epochs.
- The variant trained on the ELIFE subset can be found [here](https://huggingface.co/pszemraj/long-t5-tglobal-base-sci-simplify-elife)
## Usage
It's recommended to use this model with [beam search decoding](https://huggingface.co/docs/transformers/generation_strategies#beamsearch-decoding). If you are interested, you can also use the `textsum` util repo to have most of this abstracted for you:
Install with `pip`:
```bash
pip install -U textsum
```
Use in python:
```python
from textsum.summarize import Summarizer
summarizer = Summarizer('pszemraj/long-t5-tglobal-base-sci-simplify')
text = "put the text you don't want to read here"
summary = summarizer.summarize_string(text)
print(summary)
```
## Intended uses & limitations
- Ability to generalize outside of the dataset domain (pubmed/bioscience type papers) has to be evaluated.
## Training procedure
### Eval results
It achieves the following results on the evaluation set:
- Loss: 1.6778
- Rouge1: 49.1475
- Rouge2: 18.9281
- Rougel: 26.9893
- Rougelsum: 45.0973
- Gen Len: 399.4125
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
| 1.966 | 0.52 | 200 | 1.7171 | 48.6521 | 18.427 | 26.7726 | 44.3947 | 376.335 |
| 1.877 | 1.03 | 400 | 1.6909 | 49.3263 | 18.7945 | 27.0741 | 45.1737 | 382.205 |
| 1.9007 | 1.55 | 600 | 1.6778 | 49.1475 | 18.9281 | 26.9893 | 45.0973 | 399.4125 |
|
CyberHarem/yokoyama_nao_theidolmstermillionlive | CyberHarem | 2023-09-23T20:41:44Z | 0 | 0 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/yokoyama_nao_theidolmstermillionlive",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-23T20:28:46Z | ---
license: mit
datasets:
- CyberHarem/yokoyama_nao_theidolmstermillionlive
pipeline_tag: text-to-image
tags:
- art
---
# Lora of yokoyama_nao_theidolmstermillionlive
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 3500, you need to download `3500/yokoyama_nao_theidolmstermillionlive.pt` as the embedding and `3500/yokoyama_nao_theidolmstermillionlive.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3500**, with the score of 0.985. The trigger words are:
1. `yokoyama_nao_theidolmstermillionlive`
2. `brown_hair, ahoge, purple_eyes, side_ponytail, bangs, drill_hair, smile, side_drill, medium_hair, sidelocks, blush, hair_ornament, open_mouth, breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7500 | 0.980 | [Download](7500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7500/previews/nude.png) | [<NSFW, click to see>](7500/previews/nude2.png) |  |  |
| 7000 | 0.982 | [Download](7000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7000/previews/nude.png) | [<NSFW, click to see>](7000/previews/nude2.png) |  |  |
| 6500 | 0.981 | [Download](6500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6500/previews/nude.png) | [<NSFW, click to see>](6500/previews/nude2.png) |  |  |
| 6000 | 0.982 | [Download](6000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6000/previews/nude.png) | [<NSFW, click to see>](6000/previews/nude2.png) |  |  |
| 5500 | 0.973 | [Download](5500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5500/previews/nude.png) | [<NSFW, click to see>](5500/previews/nude2.png) |  |  |
| 5000 | 0.982 | [Download](5000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5000/previews/nude.png) | [<NSFW, click to see>](5000/previews/nude2.png) |  |  |
| 4500 | 0.982 | [Download](4500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4500/previews/nude.png) | [<NSFW, click to see>](4500/previews/nude2.png) |  |  |
| 4000 | 0.980 | [Download](4000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4000/previews/nude.png) | [<NSFW, click to see>](4000/previews/nude2.png) |  |  |
| **3500** | **0.985** | [**Download**](3500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3500/previews/nude.png) | [<NSFW, click to see>](3500/previews/nude2.png) |  |  |
| 3000 | 0.981 | [Download](3000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3000/previews/nude.png) | [<NSFW, click to see>](3000/previews/nude2.png) |  |  |
| 2500 | 0.981 | [Download](2500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2500/previews/nude.png) | [<NSFW, click to see>](2500/previews/nude2.png) |  |  |
| 2000 | 0.972 | [Download](2000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2000/previews/nude.png) | [<NSFW, click to see>](2000/previews/nude2.png) |  |  |
| 1500 | 0.959 | [Download](1500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1500/previews/nude.png) | [<NSFW, click to see>](1500/previews/nude2.png) |  |  |
| 1000 | 0.968 | [Download](1000/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1000/previews/nude.png) | [<NSFW, click to see>](1000/previews/nude2.png) |  |  |
| 500 | 0.946 | [Download](500/yokoyama_nao_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](500/previews/bondage.png) |  |  |  | [<NSFW, click to see>](500/previews/nude.png) | [<NSFW, click to see>](500/previews/nude2.png) |  |  |
|
pszemraj/flan-t5-xl-instructiongen | pszemraj | 2023-09-23T20:37:01Z | 5 | 2 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"instruct",
"instructions",
"domain adapt",
"instructiongen",
"dataset:pszemraj/fleece2instructions",
"base_model:google/flan-t5-xl",
"base_model:finetune:google/flan-t5-xl",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-03-23T21:33:53Z | ---
license: apache-2.0
tags:
- generated_from_trainer
- instruct
- instructions
- domain adapt
- instructiongen
datasets:
- pszemraj/fleece2instructions
metrics:
- rouge
widget:
- text: You'll need to start by choosing the right venue. Consider the type of atmosphere
and the size of the area that will be suitable for the number of guests you plan
to invite. Choose the right decorations based on your brother's interests, such
as balloons in his favorite colors, banners, and streamers. Next, decide on the
food and drinks, making sure they are tasty and appropriate for the occasion.
Then decide on the other games, music, and entertainment that will make the party
memorable. Finally, involve your brother's friends and family to help create the
perfect surprise.
example_title: birthday party
- text: 1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo
example_title: ice cream
- text: Start by selecting a scale model of a building that fits the theme. Use a
hobby knife and glue to cut and assemble the model into a ruined or abandoned
version of itself, adding details like broken windows and graffiti. Create a base
for the diorama using foam, plaster, or other materials, and paint it to resemble
a ruined street or sidewalk. Add miniature vehicles, debris, and figures to complete
the scene, and use weathering techniques like dry brushing and rust washes to
add realism. Display the diorama in a shadow box or other protective case to showcase
your work.
example_title: Miniature diorama creation
- text: Start by selecting clothing that is futuristic and edgy, such as leather jackets,
neon-colored accessories, and tech-inspired patterns. Add accessories like goggles,
cybernetic implants, and LED lights to enhance the cyberpunk vibe. Use makeup
and body paint to create a futuristic look, such as metallic skin or neon makeup.
Consider adding functional elements to your costume, such as a built-in backpack
or hidden pockets for your tech gadgets. Finally, practice your confident walk
and embrace your inner cyberpunk for a memorable and immersive costume experience.
example_title: Cyberpunk costume design
- text: Start by creating a base terrain with mountains, valleys, and other natural
features. Use fractal noise and displacement mapping to add texture and detail
to the terrain, and experiment with different materials like rock, grass, and
water. Add surreal elements like floating islands, giant mushrooms, or impossible
geometry to create a dreamlike atmosphere. Use lighting and color grading to enhance
the mood and tone of the scene, and render the final image at a high resolution
for maximum impact. Share your surreal landscape with the world and inspire others
to explore the possibilities of 3D art.
example_title: Surreal 3D landscape creation
- text: Start by setting a realistic goal and creating a training plan. Build up your
mileage gradually over time, and incorporate cross-training and strength exercises
to prevent injury and improve endurance. Be sure to stay hydrated and properly
fuel your body with nutritious foods. Listen to your body and adjust your training
as needed to avoid overexertion or burnout. Finally, taper your training in the
weeks leading up to the race to give your body time to rest and recover before
the big day.
example_title: Marathon training
inference:
parameters:
max_length: 48
num_beams: 4
base_model: google/flan-t5-xl
model-index:
- name: flan-t5-xl-instructiongen
results:
- task:
type: text2text-generation
name: Sequence-to-sequence Language Modeling
dataset:
name: pszemraj/fleece2instructions
type: pszemraj/fleece2instructions
split: validation
metrics:
- type: rouge
value: 65.3297
name: Rouge1
---
# flan-t5-xl-instructiongen
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the pszemraj/fleece2instructions dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8314
- Rouge1: 65.3297
- Rouge2: 48.8475
- Rougel: 63.4183
- Rougelsum: 63.5458
- Gen Len: 13.7474
## Model description
More information needed
## Intended uses & limitations
Generate/recover **instructions** (assumes that there is just an instruction, not `inputs` as well) from arbitrary text.
## Training and evaluation data
Refer to `pszemraj/fleece2instructions`
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 0.9615 | 1.0 | 362 | 0.8353 | 63.9163 | 47.0456 | 61.9554 | 62.0549 | 13.3737 |
| 0.809 | 2.0 | 724 | 0.8251 | 64.5398 | 47.9107 | 62.5928 | 62.7278 | 13.4763 | |
pszemraj/t5-base-askscience-lfqa | pszemraj | 2023-09-23T20:36:41Z | 123 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"qa",
"askscience",
"lfqa",
"information retrieval",
"en",
"dataset:vblagoje/lfqa",
"base_model:google/t5-v1_1-base",
"base_model:finetune:google/t5-v1_1-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2022-03-02T23:29:05Z | ---
language:
- en
license: apache-2.0
tags:
- t5
- qa
- askscience
- lfqa
- information retrieval
datasets:
- vblagoje/lfqa
metrics:
- rouge
widget:
- text: why hasn't humanity expanded to live on other planets in our solar system?
example_title: solar system
- text: 'question: what is a probability distribution? context: I am just learning
about statistics.'
example_title: probability distribution
- text: 'question: What are the underlying physical processes by which exercise helps
us lose weight? context: I started working out two weeks ago and already feel
a lot better, and started to think about it and became deeply confused.'
example_title: pumpen
- text: what is a neural network?
example_title: deep learning
- text: What is the process that computers use to understand human language in deep
learning models?
example_title: NLP
inference:
parameters:
max_length: 64
no_repeat_ngram_size: 2
encoder_no_repeat_ngram_size: 4
repetition_penalty: 3.51
length_penalty: 0.8
num_beams: 4
early_stopping: true
base_model: google/t5-v1_1-base
---
# checkpoints
- This model is a fine-tuned version of [google/t5-v1_1-base](https://huggingface.co/google/t5-v1_1-base) on the `vblagoje/lfqa` dataset, with training duration of 2 epochs, for a (_somewhat_) apples-to-apples comparison with [t5-base](https://huggingface.co/pszemraj/t5-base-askscience) on the standard eli5 dataset.
- This checkpoint does seem to be more coherent than t5-base on the original dataset.
- Compared to [bart on lfqa](https://huggingface.co/vblagoje/bart_lfqa), it seems to be able to respond to some questions independently of retrieval.
> NOTE: the inference API is limited to generating approx. 64 chars for runtime reasons, for longer outputs try using it in python as a transformers pipeline object.
## Intended uses & limitations
- Q&A, information retrieval
- it is probably better to use it with a [retrieval pipeline](https://github.com/deepset-ai/haystack) than alone
## Training and evaluation data
- see linked dataset. the dataset was filtered to only included the `askscience` subreddit in an attempt to focus on academic/technical queries.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0
|
pszemraj/bart-base-code-instructiongen | pszemraj | 2023-09-23T20:36:28Z | 111 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"instruct",
"instructions",
"code",
"instructiongen",
"en",
"dataset:pszemraj/fleece2instructions-codealpaca",
"base_model:facebook/bart-base",
"base_model:finetune:facebook/bart-base",
"license:apache-2.0",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-03-25T03:12:10Z | ---
language:
- en
license:
- apache-2.0
- cc-by-nc-4.0
tags:
- generated_from_trainer
- instruct
- instructions
- code
- instructiongen
datasets: pszemraj/fleece2instructions-codealpaca
metrics:
- rouge
widget:
- text: 'git lfs install
huggingface-cli lfs-enable-largefiles .
git lfs track "*.bin"
git add .
git commit -a -m "add fp32 chkpt"
git push
'
example_title: bash
- text: "export interface DocumentParams {\n pageContent: string;\n\n // eslint-disable-next-line\
\ @typescript-eslint/no-explicit-any\n metadata: Record<string, any>;\n}\n\n\
/**\n * Interface for interacting with a document.\n */\nexport class Document\
\ implements DocumentParams {\n pageContent: string;\n\n // eslint-disable-next-line\
\ @typescript-eslint/no-explicit-any\n metadata: Record<string, any>;\n\n constructor(fields?:\
\ Partial<DocumentParams>) {\n this.pageContent = fields?.pageContent ?? this.pageContent;\n\
\ this.metadata = fields?.metadata ?? {};\n }\n}\n"
example_title: js
- text: "def merge(left, right):\n if len(left) == 0:\n return right\n\n\
\ if len(right) == 0:\n return left\n\n result = []\n index_left\
\ = index_right = 0\n\n while len(result) < len(left) + len(right):\n \
\ if left[index_left] <= right[index_right]:\n result.append(left[index_left])\n\
\ index_left += 1\n else:\n result.append(right[index_right])\n\
\ index_right += 1\n\n if index_right == len(right):\n \
\ result += left[index_left:]\n break\n\n if index_left\
\ == len(left):\n result += right[index_right:]\n break\n\
\n return result\n"
example_title: merge
- text: "import pandas as pd\nimport plotly.graph_objects as go\n\ndf = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2014_apple_stock.csv')\n\
\nfig = go.Figure(go.Scatter(x = df['AAPL_x'], y = df['AAPL_y'],\n \
\ name='Share Prices (in USD)'))\n\nfig.update_layout(title='Apple Share\
\ Prices over time (2014)',\n plot_bgcolor='rgb(230, 230,230)',\n\
\ showlegend=True)\n\nfig.show()\n"
example_title: plot
- text: "from spellchecker import SpellChecker\n\nspell = SpellChecker()\n\ndef check_word_spelling(word:\
\ str):\n misspelled = spell.unknown([word])\n return len(misspelled) ==\
\ 0\n\ndef eval_and_replace(text: str, match_token: str = \"- \"):\n if match_token\
\ not in text:\n return text\n else:\n while True:\n \
\ full_before_text = text.split(match_token, maxsplit=1)[0]\n before_text\
\ = [\n char for char in full_before_text.split()[-1] if char.isalpha()\n\
\ ]\n before_text = \"\".join(before_text)\n \
\ full_after_text = text.split(match_token, maxsplit=1)[-1]\n after_text\
\ = [char for char in full_after_text.split()[0] if char.isalpha()]\n \
\ after_text = \"\".join(after_text)\n full_text = before_text +\
\ after_text\n if check_word_spelling(full_text):\n \
\ text = full_before_text + full_after_text\n else:\n \
\ text = full_before_text + \" \" + full_after_text\n if match_token\
\ not in text:\n break\n return text\n\ntext = \"I- am-\
\ a go- od- boy\"\neval_and_replace(text)\n"
example_title: spell check
- text: 'import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
sequences = ["I''ve been waiting for a HuggingFace course my whole life.", "So
have I!"]
tokens = tokenizer(sequences, padding=True, truncation=True, return_tensors="pt")
output = model(**tokens)
'
example_title: model inference
inference:
parameters:
max_length: 96
num_beams: 4
base_model: facebook/bart-base
---
# bart-base-code-instructiongen
Use this text2text model to find out what LLM instructions might be able to generate an arbitary piece of code!
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the `pszemraj/fleece2instructions-codealpaca` dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0136
- Rouge1: 59.9513
- Rouge2: 33.9118
- Rougel: 55.7815
- Rougelsum: 56.9064
- Gen Len: 29.7146
## Intended uses & limitations
🚨 **note:** as the authors elected to release the [original dataset](https://github.com/sahil280114/codealpaca) under `cc-by-nc`, the license carries over to this model and **cannot be used for commercial activity**.
> This is just a `base` size model, which does a decent job for its size, but is not perfect. For better quality instructions, check out [bart-large](https://huggingface.co/pszemraj/bart-large-code-instructiongen) or fine tune your own larger model on the dataset :)
Intended use: Research on domain adaptation and/or other improvements to LLMs by extending instruction:text data pairs.
## Training and evaluation data
Refer to the linked dataset card for `pszemraj/fleece2instructions-codealpaca` or the [original dataset](https://github.com/sahil280114/codealpaca) repo.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 8e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.1165 | 1.0 | 281 | 1.1090 | 57.9239 | 31.9259 | 53.8737 | 54.9811 | 28.2924 |
| 1.0763 | 2.0 | 563 | 1.0267 | 59.9605 | 34.0298 | 55.7523 | 56.8021 | 29.6966 |
| 0.9595 | 2.99 | 843 | 1.0136 | 59.9513 | 33.9118 | 55.7815 | 56.9064 | 29.7146 | |
ad019el/wav2vec2-large-xlsr-53-Tamasheq | ad019el | 2023-09-23T20:24:05Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| automatic-speech-recognition | 2023-09-23T17:11:11Z | ---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-xlsr-53-Tamasheq
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. -->
# wav2vec2-large-xlsr-53-Tamasheq
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8053
- Wer: 1.0
## 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:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 9.4002 | 17.65 | 300 | 3.3014 | 1.0 |
| 3.0514 | 35.29 | 600 | 2.8053 | 1.0 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Martins6/ppo-LunarLander-v2 | Martins6 | 2023-09-23T20:18:41Z | 3 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T20:18:14Z | ---
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: 231.72 +/- 34.59
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
...
```
|
danielivanov/embedding-model-it-mmarco | danielivanov | 2023-09-23T20:02:12Z | 2 | 0 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"it",
"dataset:unicamp-dl/mmarco",
"license:mit",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
]
| sentence-similarity | 2023-09-23T19:19:55Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
license: mit
datasets:
- unicamp-dl/mmarco
language:
- it
library_name: sentence-transformers
region: Italy
---
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 6250 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": 10,
"evaluation_steps": 500,
"evaluator": "sentence_transformers.evaluation.TripletEvaluator.TripletEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 1500,
"warmup_steps": 6250,
"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})
)
``` |
hadongz/Llama-2-13b-orca-v1-gguf | hadongz | 2023-09-23T20:00:44Z | 40 | 1 | null | [
"gguf",
"text-generation",
"license:mit",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-23T09:59:47Z | ---
license: mit
pipeline_tag: text-generation
--- |
rghosh8/supportGPT-v7 | rghosh8 | 2023-09-23T19:46:04Z | 5 | 0 | peft | [
"peft",
"falcon",
"text-generation",
"custom_code",
"en",
"region:us"
]
| text-generation | 2023-09-23T19:06:50Z | ---
library_name: peft
language:
- en
pipeline_tag: text-generation
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0 |
KaiMilo/distilhubert-finetuned-gtzan | KaiMilo | 2023-09-23T19:33:58Z | 163 | 0 | transformers | [
"transformers",
"pytorch",
"hubert",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:ntu-spml/distilhubert",
"base_model:finetune:ntu-spml/distilhubert",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
]
| audio-classification | 2023-09-20T02:20:59Z | ---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.83
---
<!-- 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. -->
# distilhubert-finetuned-gtzan
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6371
- Accuracy: 0.83
## 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.0249 | 1.0 | 113 | 1.8360 | 0.43 |
| 1.3024 | 2.0 | 226 | 1.2179 | 0.61 |
| 0.9782 | 3.0 | 339 | 0.9286 | 0.74 |
| 0.8263 | 4.0 | 452 | 0.8332 | 0.76 |
| 0.7515 | 5.0 | 565 | 0.6887 | 0.82 |
| 0.4177 | 6.0 | 678 | 0.6159 | 0.83 |
| 0.4822 | 7.0 | 791 | 0.5960 | 0.84 |
| 0.2312 | 8.0 | 904 | 0.5989 | 0.85 |
| 0.3513 | 9.0 | 1017 | 0.6024 | 0.82 |
| 0.1244 | 10.0 | 1130 | 0.6371 | 0.83 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
vamsidulam/graphcorevqa_03 | vamsidulam | 2023-09-23T19:21:15Z | 59 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"vilt",
"visual-question-answering",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| visual-question-answering | 2023-09-23T17:31:33Z | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: graphcorevqa_03
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. -->
# graphcorevqa_03
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) 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: 5e-05
- 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: linear
- num_epochs: 20
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Koshti10/BART_large_Gameplan | Koshti10 | 2023-09-23T19:14:02Z | 3 | 0 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-large",
"base_model:finetune:facebook/bart-large",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-09-23T15:28:40Z | ---
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
model-index:
- name: BART_large_Gameplan
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. -->
# BART_large_Gameplan
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) 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: 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- label_smoothing_factor: 0.1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
LarryAIDraw/nezuko-08 | LarryAIDraw | 2023-09-23T19:11:02Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2023-09-23T19:01:33Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/149998/nezuko-kamado-demon-slayer-lora |
zongxiao/wav2vec2-base-finetuned-gtzan | zongxiao | 2023-09-23T19:07:33Z | 159 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:facebook/wav2vec2-base",
"base_model:finetune:facebook/wav2vec2-base",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
]
| audio-classification | 2023-09-23T16:08:57Z | ---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.92
---
<!-- 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. -->
# wav2vec2-base-finetuned-gtzan
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4965
- Accuracy: 0.92
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1429 | 1.0 | 224 | 0.6629 | 0.9 |
| 0.0037 | 2.0 | 449 | 0.5910 | 0.92 |
| 0.0041 | 3.0 | 674 | 0.5544 | 0.91 |
| 0.003 | 4.0 | 899 | 0.5046 | 0.92 |
| 0.1445 | 4.98 | 1120 | 0.4965 | 0.92 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
CyberHarem/miki_sayaka_puellamagimadokamagica | CyberHarem | 2023-09-23T19:02:54Z | 0 | 0 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/miki_sayaka_puellamagimadokamagica",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-23T18:46:09Z | ---
license: mit
datasets:
- CyberHarem/miki_sayaka_puellamagimadokamagica
pipeline_tag: text-to-image
tags:
- art
---
# Lora of miki_sayaka_puellamagimadokamagica
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 8060, you need to download `8060/miki_sayaka_puellamagimadokamagica.pt` as the embedding and `8060/miki_sayaka_puellamagimadokamagica.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 8060**, with the score of 0.875. The trigger words are:
1. `miki_sayaka_puellamagimadokamagica`
2. `short_hair, blue_hair, blue_eyes, hair_ornament, bow, hairclip, parody`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9300 | 0.836 | [Download](9300/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9300/previews/nude.png) | [<NSFW, click to see>](9300/previews/nude2.png) |  |  |
| 8680 | 0.866 | [Download](8680/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8680/previews/nude.png) | [<NSFW, click to see>](8680/previews/nude2.png) |  |  |
| **8060** | **0.875** | [**Download**](8060/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8060/previews/nude.png) | [<NSFW, click to see>](8060/previews/nude2.png) |  |  |
| 7440 | 0.861 | [Download](7440/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7440/previews/nude.png) | [<NSFW, click to see>](7440/previews/nude2.png) |  |  |
| 6820 | 0.816 | [Download](6820/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6820/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6820/previews/nude.png) | [<NSFW, click to see>](6820/previews/nude2.png) |  |  |
| 6200 | 0.802 | [Download](6200/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6200/previews/nude.png) | [<NSFW, click to see>](6200/previews/nude2.png) |  |  |
| 5580 | 0.811 | [Download](5580/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5580/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5580/previews/nude.png) | [<NSFW, click to see>](5580/previews/nude2.png) |  |  |
| 4960 | 0.771 | [Download](4960/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4960/previews/nude.png) | [<NSFW, click to see>](4960/previews/nude2.png) |  |  |
| 4340 | 0.824 | [Download](4340/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4340/previews/nude.png) | [<NSFW, click to see>](4340/previews/nude2.png) |  |  |
| 3720 | 0.740 | [Download](3720/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3720/previews/nude.png) | [<NSFW, click to see>](3720/previews/nude2.png) |  |  |
| 3100 | 0.767 | [Download](3100/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3100/previews/nude.png) | [<NSFW, click to see>](3100/previews/nude2.png) |  |  |
| 2480 | 0.786 | [Download](2480/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2480/previews/nude.png) | [<NSFW, click to see>](2480/previews/nude2.png) |  |  |
| 1860 | 0.697 | [Download](1860/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1860/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1860/previews/nude.png) | [<NSFW, click to see>](1860/previews/nude2.png) |  |  |
| 1240 | 0.705 | [Download](1240/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1240/previews/nude.png) | [<NSFW, click to see>](1240/previews/nude2.png) |  |  |
| 620 | 0.518 | [Download](620/miki_sayaka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](620/previews/bondage.png) |  |  |  | [<NSFW, click to see>](620/previews/nude.png) | [<NSFW, click to see>](620/previews/nude2.png) |  |  |
|
LarryAIDraw/Amy | LarryAIDraw | 2023-09-23T19:00:12Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2023-09-23T18:42:32Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/150254/amy-karmis-or-manhwa-or-infinite-mage |
LarryAIDraw/kairi_v1 | LarryAIDraw | 2023-09-23T18:59:24Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2023-09-23T18:41:42Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/150222/kairi-kingdom-hearts |
LarryAIDraw/Musashi_azur_ | LarryAIDraw | 2023-09-23T18:58:49Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2023-09-23T18:41:18Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/150143/musashi-azur-lane |
santif/codellama2-qlora-finetuned-guanaco | santif | 2023-09-23T18:57:13Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T18:56:56Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
keshav5196/RL-taxi | keshav5196 | 2023-09-23T18:52:54Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T18:52:52Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: RL-taxi
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="keshav5196/RL-taxi", 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"])
```
|
vazha72/bert-finetuned-ner-1 | vazha72 | 2023-09-23T18:52:50Z | 118 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-09-23T18:38:38Z | ---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-1
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9294311624072548
- name: Recall
type: recall
value: 0.9486704813194211
- name: F1
type: f1
value: 0.9389522778379279
- name: Accuracy
type: accuracy
value: 0.9867545770294931
---
<!-- 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. -->
# bert-finetuned-ner-1
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0559
- Precision: 0.9294
- Recall: 0.9487
- F1: 0.9390
- Accuracy: 0.9868
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.077 | 1.0 | 1756 | 0.0678 | 0.9085 | 0.9357 | 0.9219 | 0.9815 |
| 0.0402 | 2.0 | 3512 | 0.0539 | 0.9241 | 0.9468 | 0.9353 | 0.9864 |
| 0.0254 | 3.0 | 5268 | 0.0559 | 0.9294 | 0.9487 | 0.9390 | 0.9868 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/ibuki_tsubasa_theidolmstermillionlive | CyberHarem | 2023-09-23T18:47:33Z | 0 | 0 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/ibuki_tsubasa_theidolmstermillionlive",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-23T18:28:45Z | ---
license: mit
datasets:
- CyberHarem/ibuki_tsubasa_theidolmstermillionlive
pipeline_tag: text-to-image
tags:
- art
---
# Lora of ibuki_tsubasa_theidolmstermillionlive
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 6720, you need to download `6720/ibuki_tsubasa_theidolmstermillionlive.pt` as the embedding and `6720/ibuki_tsubasa_theidolmstermillionlive.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 6720**, with the score of 0.770. The trigger words are:
1. `ibuki_tsubasa_theidolmstermillionlive`
2. `short_hair, ahoge, blush, blonde_hair, smile, breasts, bangs, open_mouth, pink_eyes, red_eyes, hair_between_eyes, hair_flaps, medium_breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-----------------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 8400 | 0.748 | [Download](8400/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8400/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](8400/previews/pattern_16.png) |  | [<NSFW, click to see>](8400/previews/bondage.png) | [<NSFW, click to see>](8400/previews/free.png) |  |  | [<NSFW, click to see>](8400/previews/nude.png) | [<NSFW, click to see>](8400/previews/nude2.png) |  |  |
| 7840 | 0.652 | [Download](7840/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7840/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](7840/previews/pattern_16.png) |  | [<NSFW, click to see>](7840/previews/bondage.png) | [<NSFW, click to see>](7840/previews/free.png) |  |  | [<NSFW, click to see>](7840/previews/nude.png) | [<NSFW, click to see>](7840/previews/nude2.png) |  |  |
| 7280 | 0.641 | [Download](7280/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](7280/previews/pattern_16.png) |  | [<NSFW, click to see>](7280/previews/bondage.png) | [<NSFW, click to see>](7280/previews/free.png) |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| **6720** | **0.770** | [**Download**](6720/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](6720/previews/pattern_16.png) |  | [<NSFW, click to see>](6720/previews/bondage.png) | [<NSFW, click to see>](6720/previews/free.png) |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6160 | 0.718 | [Download](6160/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6160/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](6160/previews/pattern_16.png) |  | [<NSFW, click to see>](6160/previews/bondage.png) | [<NSFW, click to see>](6160/previews/free.png) |  |  | [<NSFW, click to see>](6160/previews/nude.png) | [<NSFW, click to see>](6160/previews/nude2.png) |  |  |
| 5600 | 0.662 | [Download](5600/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5600/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](5600/previews/pattern_16.png) |  | [<NSFW, click to see>](5600/previews/bondage.png) | [<NSFW, click to see>](5600/previews/free.png) |  |  | [<NSFW, click to see>](5600/previews/nude.png) | [<NSFW, click to see>](5600/previews/nude2.png) |  |  |
| 5040 | 0.643 | [Download](5040/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5040/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](5040/previews/pattern_16.png) |  | [<NSFW, click to see>](5040/previews/bondage.png) | [<NSFW, click to see>](5040/previews/free.png) |  |  | [<NSFW, click to see>](5040/previews/nude.png) | [<NSFW, click to see>](5040/previews/nude2.png) |  |  |
| 4480 | 0.752 | [Download](4480/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4480/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](4480/previews/pattern_16.png) |  | [<NSFW, click to see>](4480/previews/bondage.png) | [<NSFW, click to see>](4480/previews/free.png) |  |  | [<NSFW, click to see>](4480/previews/nude.png) | [<NSFW, click to see>](4480/previews/nude2.png) |  |  |
| 3920 | 0.733 | [Download](3920/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3920/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](3920/previews/pattern_16.png) |  | [<NSFW, click to see>](3920/previews/bondage.png) | [<NSFW, click to see>](3920/previews/free.png) |  |  | [<NSFW, click to see>](3920/previews/nude.png) | [<NSFW, click to see>](3920/previews/nude2.png) |  |  |
| 3360 | 0.745 | [Download](3360/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](3360/previews/pattern_16.png) |  | [<NSFW, click to see>](3360/previews/bondage.png) | [<NSFW, click to see>](3360/previews/free.png) |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2800 | 0.764 | [Download](2800/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2800/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](2800/previews/pattern_16.png) |  | [<NSFW, click to see>](2800/previews/bondage.png) | [<NSFW, click to see>](2800/previews/free.png) |  |  | [<NSFW, click to see>](2800/previews/nude.png) | [<NSFW, click to see>](2800/previews/nude2.png) |  |  |
| 2240 | 0.776 | [Download](2240/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2240/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](2240/previews/pattern_16.png) |  | [<NSFW, click to see>](2240/previews/bondage.png) | [<NSFW, click to see>](2240/previews/free.png) |  |  | [<NSFW, click to see>](2240/previews/nude.png) | [<NSFW, click to see>](2240/previews/nude2.png) |  |  |
| 1680 | 0.787 | [Download](1680/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1680/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](1680/previews/pattern_16.png) |  | [<NSFW, click to see>](1680/previews/bondage.png) | [<NSFW, click to see>](1680/previews/free.png) |  |  | [<NSFW, click to see>](1680/previews/nude.png) | [<NSFW, click to see>](1680/previews/nude2.png) |  |  |
| 1120 | 0.815 | [Download](1120/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1120/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](1120/previews/pattern_16.png) |  | [<NSFW, click to see>](1120/previews/bondage.png) | [<NSFW, click to see>](1120/previews/free.png) |  |  | [<NSFW, click to see>](1120/previews/nude.png) | [<NSFW, click to see>](1120/previews/nude2.png) |  |  |
| 560 | 0.782 | [Download](560/ibuki_tsubasa_theidolmstermillionlive.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](560/previews/pattern_11.png) |  |  |  |  | [<NSFW, click to see>](560/previews/pattern_16.png) |  | [<NSFW, click to see>](560/previews/bondage.png) | [<NSFW, click to see>](560/previews/free.png) |  |  | [<NSFW, click to see>](560/previews/nude.png) | [<NSFW, click to see>](560/previews/nude2.png) |  |  |
|
keshav5196/q-FrozenLake-v1-4x4-noSlippery | keshav5196 | 2023-09-23T18:45:44Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T18:45:41Z | ---
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="keshav5196/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"])
```
|
RocioUrquijo/clasificador-muchocine | RocioUrquijo | 2023-09-23T18:36:11Z | 108 | 0 | transformers | [
"transformers",
"pytorch",
"electra",
"text-classification",
"classification",
"generated_from_trainer",
"base_model:mrm8488/electricidad-base-discriminator",
"base_model:finetune:mrm8488/electricidad-base-discriminator",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-02-08T10:22:32Z | ---
base_model: mrm8488/electricidad-base-discriminator
tags:
- classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: clasificador-muchocine
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. -->
# clasificador-muchocine
This model is a fine-tuned version of [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4367
- Accuracy: 0.4206
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 388 | 1.3247 | 0.4090 |
| 1.3945 | 2.0 | 776 | 1.3297 | 0.4413 |
| 1.0081 | 3.0 | 1164 | 1.4367 | 0.4206 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
InvokeAI/ip_adapter_sdxl_image_encoder | InvokeAI | 2023-09-23T18:34:05Z | 7,813 | 14 | transformers | [
"transformers",
"safetensors",
"clip_vision_model",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2023-09-14T22:13:05Z | ---
license: apache-2.0
---
This is the Image Encoder required for SDXL IP Adapter models to function correctly. It is compatible with version 3.2+ of Invoke AI.
IP Adapter allows for users to input an Image Prompt, which is interpreted by the system, and passed in as conditioning for the image generation process.
The Community Edition of Invoke AI can be found at invoke.ai or on GitHub at https://github.com/invoke-ai/InvokeAI
This model is a copy of https://huggingface.co/h94/IP-Adapter/tree/5c2eae7d8a9c3365ba4745f16b94eb0293e319d3/sdxl_models/image_encoder. It is hosted here for compatibility with InvokeAI.
|
badokorach/bert-finetuned-squad-7-finetuned-newqa | badokorach | 2023-09-23T18:30:05Z | 122 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"question-answering",
"generated_from_trainer",
"base_model:badokorach/bert-finetuned-squad-7",
"base_model:finetune:badokorach/bert-finetuned-squad-7",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| question-answering | 2023-09-23T17:36:36Z | ---
license: apache-2.0
base_model: badokorach/bert-finetuned-squad-7
tags:
- generated_from_trainer
model-index:
- name: bert-finetuned-squad-7-finetuned-newqa
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. -->
# bert-finetuned-squad-7-finetuned-newqa
This model is a fine-tuned version of [badokorach/bert-finetuned-squad-7](https://huggingface.co/badokorach/bert-finetuned-squad-7) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.6437
## 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: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 66 | 4.8867 |
| No log | 2.0 | 132 | 5.1511 |
| No log | 3.0 | 198 | 5.8491 |
| No log | 4.0 | 264 | 5.5515 |
| No log | 5.0 | 330 | 5.5515 |
| No log | 6.0 | 396 | 5.2236 |
| No log | 7.0 | 462 | 5.4818 |
| 0.0076 | 8.0 | 528 | 5.3132 |
| 0.0076 | 9.0 | 594 | 5.4253 |
| 0.0076 | 10.0 | 660 | 5.5527 |
| 0.0076 | 11.0 | 726 | 5.4605 |
| 0.0076 | 12.0 | 792 | 5.3987 |
| 0.0076 | 13.0 | 858 | 5.5341 |
| 0.0076 | 14.0 | 924 | 5.4277 |
| 0.0076 | 15.0 | 990 | 5.5373 |
| 0.001 | 16.0 | 1056 | 6.0537 |
| 0.001 | 17.0 | 1122 | 5.5327 |
| 0.001 | 18.0 | 1188 | 5.7127 |
| 0.001 | 19.0 | 1254 | 5.5445 |
| 0.001 | 20.0 | 1320 | 5.5626 |
| 0.001 | 21.0 | 1386 | 5.6203 |
| 0.001 | 22.0 | 1452 | 5.6869 |
| 0.0014 | 23.0 | 1518 | 5.7155 |
| 0.0014 | 24.0 | 1584 | 5.7069 |
| 0.0014 | 25.0 | 1650 | 5.6417 |
| 0.0014 | 26.0 | 1716 | 5.6183 |
| 0.0014 | 27.0 | 1782 | 5.6824 |
| 0.0014 | 28.0 | 1848 | 5.6416 |
| 0.0014 | 29.0 | 1914 | 5.6474 |
| 0.0014 | 30.0 | 1980 | 5.6437 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
fowlart99/hihi | fowlart99 | 2023-09-23T18:29:49Z | 0 | 0 | null | [
"license:bigscience-openrail-m",
"region:us"
]
| null | 2023-09-23T18:29:49Z | ---
license: bigscience-openrail-m
---
|
Kiwihead15/bert-finetuned-ner | Kiwihead15 | 2023-09-23T18:15:32Z | 106 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-09-23T17:50:48Z | ---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9319907560250907
- name: Recall
type: recall
value: 0.9501851228542578
- name: F1
type: f1
value: 0.941
- name: Accuracy
type: accuracy
value: 0.9863277800671102
---
<!-- 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. -->
# bert-finetuned-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0594
- Precision: 0.9320
- Recall: 0.9502
- F1: 0.941
- Accuracy: 0.9863
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0798 | 1.0 | 1756 | 0.0771 | 0.9016 | 0.9342 | 0.9176 | 0.9797 |
| 0.0404 | 2.0 | 3512 | 0.0595 | 0.9242 | 0.9478 | 0.9359 | 0.9851 |
| 0.0247 | 3.0 | 5268 | 0.0594 | 0.9320 | 0.9502 | 0.941 | 0.9863 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
felixquinihildebet/spaceinvaders5 | felixquinihildebet | 2023-09-23T17:57:33Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T17:57:17Z | ---
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: 526.00 +/- 121.22
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 felixquinihildebet -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 felixquinihildebet -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 felixquinihildebet
```
## 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'}
```
|
AyushChothe/fashion-clip-embedding | AyushChothe | 2023-09-23T17:46:19Z | 0 | 1 | generic | [
"generic",
"feature-extraction",
"license:mit",
"region:us"
]
| feature-extraction | 2023-08-05T08:09:00Z | ---
license: mit
tags:
- feature-extraction
library_name: generic
--- |
learn3r/longt5_xl_summ_screen_20 | learn3r | 2023-09-23T17:40:48Z | 10 | 0 | transformers | [
"transformers",
"pytorch",
"longt5",
"text2text-generation",
"generated_from_trainer",
"dataset:tau/scrolls",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-09-18T14:06:25Z | ---
base_model: /exports/eddie/scratch/s1970716/models/summarization/longt5_xl_summ_screen/checkpoint-140
tags:
- generated_from_trainer
datasets:
- tau/scrolls
metrics:
- rouge
model-index:
- name: longt5_xl_summ_screen_20
results:
- task:
name: Summarization
type: summarization
dataset:
name: tau/scrolls summ_screen_fd
type: tau/scrolls
config: summ_screen_fd
split: validation
args: summ_screen_fd
metrics:
- name: Rouge1
type: rouge
value: 28.1708
---
<!-- 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. -->
# longt5_xl_summ_screen_20
This model is a fine-tuned version of [/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_summ_screen/checkpoint-140](https://huggingface.co//exports/eddie/scratch/s1970716/models/summarization/longt5_xl_summ_screen/checkpoint-140) on the tau/scrolls summ_screen_fd dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1917
- Rouge1: 28.1708
- Rouge2: 6.6895
- Rougel: 18.1637
- Rougelsum: 24.3987
- Gen Len: 96.2041
## 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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 10.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:--------:|
| 0.4063 | 0.97 | 14 | 3.7385 | 27.9171 | 6.7215 | 17.9315 | 24.363 | 71.9083 |
| 0.3125 | 1.95 | 28 | 3.1917 | 28.1708 | 6.6895 | 18.1637 | 24.3987 | 96.2041 |
| 0.2177 | 2.99 | 43 | 3.9998 | 29.3167 | 5.9 | 17.3608 | 25.6945 | 198.0473 |
| 0.1753 | 3.97 | 57 | 4.2287 | 29.0605 | 6.2534 | 17.5744 | 25.6415 | 158.6509 |
| 0.2747 | 4.94 | 71 | 4.1027 | 31.2245 | 6.5663 | 18.1588 | 26.8996 | 118.4438 |
| 0.1045 | 5.98 | 86 | 5.0581 | 30.6056 | 6.8892 | 18.4933 | 26.4027 | 92.9882 |
| 0.0875 | 6.96 | 100 | 4.5941 | 32.5234 | 7.3736 | 18.8958 | 28.4738 | 160.8964 |
| 0.1572 | 8.0 | 115 | 4.9386 | 31.4658 | 7.2592 | 18.4796 | 27.6047 | 121.0178 |
| 0.0867 | 8.97 | 129 | 4.5565 | 32.0531 | 7.0692 | 18.5551 | 27.3373 | 160.4793 |
| 0.0748 | 9.74 | 140 | 5.0866 | 32.2717 | 7.7004 | 18.9107 | 28.3874 | 124.1893 |
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
eugene6/q-Taxi-v3 | eugene6 | 2023-09-23T17:39:58Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T17:39:56Z | ---
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: 7.44 +/- 2.77
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="eugene6/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"])
```
|
SABARINATHKR777/my-pet-parot-sxh | SABARINATHKR777 | 2023-09-23T17:14:36Z | 1 | 0 | diffusers | [
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-09-23T17:09:37Z | ---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-PAROT-SXH Dreambooth model trained by SABARINATHKR777 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: VAST-306
Sample pictures of this concept:
.jpg)
|
npvinHnivqn/opt-6.7b-lora | npvinHnivqn | 2023-09-23T17:10:34Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T17:10:31Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Phando/fairseq-dense-125m | Phando | 2023-09-23T17:04:17Z | 59 | 0 | transformers | [
"transformers",
"pytorch",
"text-generation",
"en",
"arxiv:2112.10684",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-22T17:09:35Z | ---
language: en
---
This is a Hugging Face transformers-style conversion of the original dense 125M-parameter model from the paper "[Efficient Large Scale Language Modeling with Mixtures of Experts](https://arxiv.org/abs/2112.10684)" from Artetxe et al. The original model card can be found at https://github.com/facebookresearch/fairseq/blob/main/examples/moe_lm/model_card.md.
The usage example and modeling code can be found at https://github.com/pingzhili/light-fairseq
|
Phando/fairseq-moe-15b | Phando | 2023-09-23T17:03:37Z | 16 | 1 | transformers | [
"transformers",
"pytorch",
"text-generation",
"en",
"arxiv:2112.10684",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-23T08:07:54Z | ---
language: en
---
This is a Hugging Face transformers-style conversion of the original SMoE 15B-parameter model from the paper "[Efficient Large Scale Language Modeling with Mixtures of Experts](https://arxiv.org/abs/2112.10684)" from Artetxe et al. The original model card can be found at https://github.com/facebookresearch/fairseq/blob/main/examples/moe_lm/model_card.md.
The usage example and modeling code can be found at https://github.com/pingzhili/light-fairseq
|
Kushala/falcon | Kushala | 2023-09-23T16:52:53Z | 1 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T16:52:31Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
|
Undi95/MXLewd-L2-20B-GGUF | Undi95 | 2023-09-23T16:52:39Z | 12 | 7 | null | [
"gguf",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2023-09-22T17:29:56Z | ---
license: cc-by-nc-4.0
---
Merge:
```shell
layer_slices:
- model: ./MXLewd-L2-20B-part2
start: 0
end: 16
- model: ./MXLewd-L2-20B-part1
start: 8
end: 20
- model: ./MXLewd-L2-20B-part2
start: 17
end: 32
- model: ./MXLewd-L2-20B-part1
start: 21
end: 40
```
Part 2 is ReMM (0.33) and Xwin (0.66)
Part 1 is Xwin (0.33) and MLewd (0.66)
<!-- description start -->
## Models used
- Undi95/MLewd-L2-13B-v2-3
- Undi95/ReMM-v2.1-L2-13B
- Xwin-LM/Xwin-LM-13B-V0.1
<!-- description end -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that completes the request.
### Instruction:
{prompt}
### Response:
``` |
LTC-AI-Labs/L2-7b-Base-WVG-Uncensored | LTC-AI-Labs | 2023-09-23T16:51:14Z | 1,583 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"text generation",
"conversational",
"en",
"dataset:DanFosing/wizardlm-vicuna-guanaco-uncensored",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-23T16:34:05Z | ---
datasets:
- DanFosing/wizardlm-vicuna-guanaco-uncensored
language:
- en
tags:
- text generation
- conversational
---
|
CyberHarem/kaname_madoka_puellamagimadokamagica | CyberHarem | 2023-09-23T16:44:49Z | 0 | 0 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/kaname_madoka_puellamagimadokamagica",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-23T16:27:55Z | ---
license: mit
datasets:
- CyberHarem/kaname_madoka_puellamagimadokamagica
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kaname_madoka_puellamagimadokamagica
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7920, you need to download `7920/kaname_madoka_puellamagimadokamagica.pt` as the embedding and `7920/kaname_madoka_puellamagimadokamagica.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7920**, with the score of 0.956. The trigger words are:
1. `kaname_madoka_puellamagimadokamagica`
2. `pink_hair, short_hair, twintails, short_twintails, pink_eyes, ribbon, hair_ribbon, bow, blush`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | pattern_18 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9900 | 0.922 | [Download](9900/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9900/previews/nude.png) | [<NSFW, click to see>](9900/previews/nude2.png) |  |  |
| 9240 | 0.899 | [Download](9240/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9240/previews/nude.png) | [<NSFW, click to see>](9240/previews/nude2.png) |  |  |
| 8580 | 0.950 | [Download](8580/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8580/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8580/previews/nude.png) | [<NSFW, click to see>](8580/previews/nude2.png) |  |  |
| **7920** | **0.956** | [**Download**](7920/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7920/previews/nude.png) | [<NSFW, click to see>](7920/previews/nude2.png) |  |  |
| 7260 | 0.943 | [Download](7260/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7260/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7260/previews/nude.png) | [<NSFW, click to see>](7260/previews/nude2.png) |  |  |
| 6600 | 0.942 | [Download](6600/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6600/previews/nude.png) | [<NSFW, click to see>](6600/previews/nude2.png) |  |  |
| 5940 | 0.868 | [Download](5940/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5940/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5940/previews/nude.png) | [<NSFW, click to see>](5940/previews/nude2.png) |  |  |
| 5280 | 0.908 | [Download](5280/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4620 | 0.904 | [Download](4620/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4620/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4620/previews/nude.png) | [<NSFW, click to see>](4620/previews/nude2.png) |  |  |
| 3960 | 0.900 | [Download](3960/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3960/previews/nude.png) | [<NSFW, click to see>](3960/previews/nude2.png) |  |  |
| 3300 | 0.840 | [Download](3300/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3300/previews/nude.png) | [<NSFW, click to see>](3300/previews/nude2.png) |  |  |
| 2640 | 0.923 | [Download](2640/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2640/previews/nude.png) | [<NSFW, click to see>](2640/previews/nude2.png) |  |  |
| 1980 | 0.888 | [Download](1980/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1980/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1980/previews/nude.png) | [<NSFW, click to see>](1980/previews/nude2.png) |  |  |
| 1320 | 0.865 | [Download](1320/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1320/previews/nude.png) | [<NSFW, click to see>](1320/previews/nude2.png) |  |  |
| 660 | 0.672 | [Download](660/kaname_madoka_puellamagimadokamagica.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](660/previews/bondage.png) |  |  |  | [<NSFW, click to see>](660/previews/nude.png) | [<NSFW, click to see>](660/previews/nude2.png) |  |  |
|
ldhldh/7b_8bit_qlora_kvdown_longprom | ldhldh | 2023-09-23T16:43:34Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T16:43:30Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
glukas/smd-audio-diffusion-256 | glukas | 2023-09-23T16:30:26Z | 0 | 0 | null | [
"license:openrail",
"region:us"
]
| null | 2023-09-23T15:57:14Z | ---
license: openrail
---
DDPM Model (https://github.com/teticio/audio-diffusion) trained on the Saarland Music Data (SMD):
Meinard Müller, Verena Konz, Wolfgang Bogler, and Vlora Arifi-Müller
Saarland Music Data (SMD)
In Late-Breaking and Demo Session of the International Conference on Music Information Retrieval (ISMIR), 2011.
https://resources.mpi-inf.mpg.de/SMD/SMD_MIDI-Audio-Piano-Music.html. |
CyberHarem/nanao_yuriko_theidolmstermillionlive | CyberHarem | 2023-09-23T16:26:09Z | 0 | 1 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/nanao_yuriko_theidolmstermillionlive",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-23T16:10:57Z | ---
license: mit
datasets:
- CyberHarem/nanao_yuriko_theidolmstermillionlive
pipeline_tag: text-to-image
tags:
- art
---
# Lora of nanao_yuriko_theidolmstermillionlive
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 6760, you need to download `6760/nanao_yuriko_theidolmstermillionlive.pt` as the embedding and `6760/nanao_yuriko_theidolmstermillionlive.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 6760**, with the score of 0.952. The trigger words are:
1. `nanao_yuriko_theidolmstermillionlive`
2. `blue_hair, yellow_eyes, blush, short_hair, braid, smile, bangs, breasts, open_mouth, medium_breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-----------------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7800 | 0.915 | [Download](7800/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](7800/previews/pattern_12.png) |  | [<NSFW, click to see>](7800/previews/bikini.png) | [<NSFW, click to see>](7800/previews/bondage.png) | [<NSFW, click to see>](7800/previews/free.png) |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7280 | 0.916 | [Download](7280/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](7280/previews/pattern_12.png) |  | [<NSFW, click to see>](7280/previews/bikini.png) | [<NSFW, click to see>](7280/previews/bondage.png) | [<NSFW, click to see>](7280/previews/free.png) |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| **6760** | **0.952** | [**Download**](6760/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](6760/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](6760/previews/pattern_12.png) |  | [<NSFW, click to see>](6760/previews/bikini.png) | [<NSFW, click to see>](6760/previews/bondage.png) | [<NSFW, click to see>](6760/previews/free.png) |  |  | [<NSFW, click to see>](6760/previews/nude.png) | [<NSFW, click to see>](6760/previews/nude2.png) |  |  |
| 6240 | 0.941 | [Download](6240/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](6240/previews/pattern_12.png) |  | [<NSFW, click to see>](6240/previews/bikini.png) | [<NSFW, click to see>](6240/previews/bondage.png) | [<NSFW, click to see>](6240/previews/free.png) |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5720 | 0.932 | [Download](5720/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](5720/previews/pattern_12.png) |  | [<NSFW, click to see>](5720/previews/bikini.png) | [<NSFW, click to see>](5720/previews/bondage.png) | [<NSFW, click to see>](5720/previews/free.png) |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5200 | 0.920 | [Download](5200/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](5200/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](5200/previews/pattern_12.png) |  | [<NSFW, click to see>](5200/previews/bikini.png) | [<NSFW, click to see>](5200/previews/bondage.png) | [<NSFW, click to see>](5200/previews/free.png) |  |  | [<NSFW, click to see>](5200/previews/nude.png) | [<NSFW, click to see>](5200/previews/nude2.png) |  |  |
| 4680 | 0.938 | [Download](4680/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](4680/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](4680/previews/pattern_12.png) |  | [<NSFW, click to see>](4680/previews/bikini.png) | [<NSFW, click to see>](4680/previews/bondage.png) | [<NSFW, click to see>](4680/previews/free.png) |  |  | [<NSFW, click to see>](4680/previews/nude.png) | [<NSFW, click to see>](4680/previews/nude2.png) |  |  |
| 4160 | 0.900 | [Download](4160/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](4160/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](4160/previews/pattern_12.png) |  | [<NSFW, click to see>](4160/previews/bikini.png) | [<NSFW, click to see>](4160/previews/bondage.png) | [<NSFW, click to see>](4160/previews/free.png) |  |  | [<NSFW, click to see>](4160/previews/nude.png) | [<NSFW, click to see>](4160/previews/nude2.png) |  |  |
| 3640 | 0.936 | [Download](3640/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](3640/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](3640/previews/pattern_12.png) |  | [<NSFW, click to see>](3640/previews/bikini.png) | [<NSFW, click to see>](3640/previews/bondage.png) | [<NSFW, click to see>](3640/previews/free.png) |  |  | [<NSFW, click to see>](3640/previews/nude.png) | [<NSFW, click to see>](3640/previews/nude2.png) |  |  |
| 3120 | 0.897 | [Download](3120/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](3120/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](3120/previews/pattern_12.png) |  | [<NSFW, click to see>](3120/previews/bikini.png) | [<NSFW, click to see>](3120/previews/bondage.png) | [<NSFW, click to see>](3120/previews/free.png) |  |  | [<NSFW, click to see>](3120/previews/nude.png) | [<NSFW, click to see>](3120/previews/nude2.png) |  |  |
| 2600 | 0.877 | [Download](2600/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](2600/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](2600/previews/pattern_12.png) |  | [<NSFW, click to see>](2600/previews/bikini.png) | [<NSFW, click to see>](2600/previews/bondage.png) | [<NSFW, click to see>](2600/previews/free.png) |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2080 | 0.922 | [Download](2080/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](2080/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](2080/previews/pattern_12.png) |  | [<NSFW, click to see>](2080/previews/bikini.png) | [<NSFW, click to see>](2080/previews/bondage.png) | [<NSFW, click to see>](2080/previews/free.png) |  |  | [<NSFW, click to see>](2080/previews/nude.png) | [<NSFW, click to see>](2080/previews/nude2.png) |  |  |
| 1560 | 0.902 | [Download](1560/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](1560/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](1560/previews/pattern_12.png) |  | [<NSFW, click to see>](1560/previews/bikini.png) | [<NSFW, click to see>](1560/previews/bondage.png) | [<NSFW, click to see>](1560/previews/free.png) |  |  | [<NSFW, click to see>](1560/previews/nude.png) | [<NSFW, click to see>](1560/previews/nude2.png) |  |  |
| 1040 | 0.920 | [Download](1040/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](1040/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](1040/previews/pattern_12.png) |  | [<NSFW, click to see>](1040/previews/bikini.png) | [<NSFW, click to see>](1040/previews/bondage.png) | [<NSFW, click to see>](1040/previews/free.png) |  |  | [<NSFW, click to see>](1040/previews/nude.png) | [<NSFW, click to see>](1040/previews/nude2.png) |  |  |
| 520 | 0.843 | [Download](520/nanao_yuriko_theidolmstermillionlive.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](520/previews/pattern_8.png) |  |  |  | [<NSFW, click to see>](520/previews/pattern_12.png) |  | [<NSFW, click to see>](520/previews/bikini.png) | [<NSFW, click to see>](520/previews/bondage.png) | [<NSFW, click to see>](520/previews/free.png) |  |  | [<NSFW, click to see>](520/previews/nude.png) | [<NSFW, click to see>](520/previews/nude2.png) |  |  |
|
FilipKubis/ppo-LunarLander-v2 | FilipKubis | 2023-09-23T16:20:20Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T16:20:01Z | ---
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: 240.38 +/- 45.01
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
...
```
|
HassanMahmood/my_awesome_asr_mind_model | HassanMahmood | 2023-09-23T16:18:54Z | 99 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:facebook/wav2vec2-base",
"base_model:finetune:facebook/wav2vec2-base",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| automatic-speech-recognition | 2023-09-22T06:32:32Z | ---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: my_awesome_asr_mind_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_asr_mind_model
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Wer: 1.0
## 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:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 50
- training_steps: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 0.0 | 100.0 | 100 | nan | 1.0 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Tiabet/bert-base-uncased-finetuned-Tiabet | Tiabet | 2023-09-23T16:18:35Z | 161 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"text classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-09-23T14:59:17Z | ---
license: apache-2.0
base_model: bert-base-uncased
tags:
- text classification
- generated_from_trainer
model-index:
- name: bert-base-uncased-finetuned-Tiabet
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. -->
# bert-base-uncased-finetuned-Tiabet
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) 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: 1e-05
- 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: linear
- num_epochs: 3
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3
|
eisenjulian/viz-wiz-bert-base-uncased_f32 | eisenjulian | 2023-09-23T16:04:53Z | 117 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2023-09-21T15:35:01Z | ---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: viz-wiz-bert-base-uncased_f32
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. -->
# viz-wiz-bert-base-uncased_f32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0723
## 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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 321 | 1.1645 |
| 1.344 | 2.0 | 642 | 1.0789 |
| 1.344 | 3.0 | 963 | 1.0537 |
| 1.1234 | 4.0 | 1284 | 1.0195 |
| 1.065 | 5.0 | 1605 | 1.0723 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
eisenjulian/viz-wiz-bert-base-uncased_f16 | eisenjulian | 2023-09-23T15:46:40Z | 109 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| fill-mask | 2023-09-21T21:27:56Z | ---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: viz-wiz-bert-base-uncased_f16
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. -->
# viz-wiz-bert-base-uncased_f16
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0723
## 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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 321 | 1.1645 |
| 1.344 | 2.0 | 642 | 1.0789 |
| 1.344 | 3.0 | 963 | 1.0537 |
| 1.1234 | 4.0 | 1284 | 1.0195 |
| 1.065 | 5.0 | 1605 | 1.0723 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
stevenbowler/MedChatBotAdapted | stevenbowler | 2023-09-23T15:44:15Z | 85 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2023-09-23T14:26:50Z | # created from
# adapter_model_name = "stevenbowler/MedChatBot4" which is based on bigbio/med_qa dataset
# model_name = "TinyPixel/Llama-2-7B-bf16-sharded"
[Colab Notebook](https://github.com/stevenbowler/LamdaLabsTest/blob/master/colabs/AutoTrain_LLM.ipynb) |
jmoney54378256438905/jondurbin_airoboros-c34b-2.2.1-3.75bpw | jmoney54378256438905 | 2023-09-23T15:26:54Z | 6 | 0 | transformers | [
"transformers",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-23T15:20:08Z | ---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-c34b-2.2](https://hf.co/jondurbin/airoboros-c34b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- 5 epochs instead of 3
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-c34b-2.2.1/runs/07b08z7m?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me. |
Koshti10/BART_base_Gameplan | Koshti10 | 2023-09-23T15:21:35Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"generated_from_trainer",
"base_model:facebook/bart-base",
"base_model:finetune:facebook/bart-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-09-23T14:02:06Z | ---
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: BART_base_Gameplan
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. -->
# BART_base_Gameplan
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) 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: 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- label_smoothing_factor: 0.1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/shiraishi_tsumugi_theidolmstermillionlive | CyberHarem | 2023-09-23T15:20:16Z | 0 | 0 | null | [
"art",
"text-to-image",
"dataset:CyberHarem/shiraishi_tsumugi_theidolmstermillionlive",
"license:mit",
"region:us"
]
| text-to-image | 2023-09-23T15:09:26Z | ---
license: mit
datasets:
- CyberHarem/shiraishi_tsumugi_theidolmstermillionlive
pipeline_tag: text-to-image
tags:
- art
---
# Lora of shiraishi_tsumugi_theidolmstermillionlive
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7000, you need to download `7000/shiraishi_tsumugi_theidolmstermillionlive.pt` as the embedding and `7000/shiraishi_tsumugi_theidolmstermillionlive.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7000**, with the score of 0.883. The trigger words are:
1. `shiraishi_tsumugi_theidolmstermillionlive`
2. `long_hair, blue_eyes, bangs, blush, hair_ornament, blue_hair, hairclip, breasts`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-----------------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7500 | 0.879 | [Download](7500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](7500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](7500/previews/bondage.png) | [<NSFW, click to see>](7500/previews/free.png) |  |  | [<NSFW, click to see>](7500/previews/nude.png) | [<NSFW, click to see>](7500/previews/nude2.png) |  |  |
| **7000** | **0.883** | [**Download**](7000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](7000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](7000/previews/bondage.png) | [<NSFW, click to see>](7000/previews/free.png) |  |  | [<NSFW, click to see>](7000/previews/nude.png) | [<NSFW, click to see>](7000/previews/nude2.png) |  |  |
| 6500 | 0.866 | [Download](6500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](6500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](6500/previews/bondage.png) | [<NSFW, click to see>](6500/previews/free.png) |  |  | [<NSFW, click to see>](6500/previews/nude.png) | [<NSFW, click to see>](6500/previews/nude2.png) |  |  |
| 6000 | 0.821 | [Download](6000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](6000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](6000/previews/bondage.png) | [<NSFW, click to see>](6000/previews/free.png) |  |  | [<NSFW, click to see>](6000/previews/nude.png) | [<NSFW, click to see>](6000/previews/nude2.png) |  |  |
| 5500 | 0.864 | [Download](5500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](5500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](5500/previews/bondage.png) | [<NSFW, click to see>](5500/previews/free.png) |  |  | [<NSFW, click to see>](5500/previews/nude.png) | [<NSFW, click to see>](5500/previews/nude2.png) |  |  |
| 5000 | 0.862 | [Download](5000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](5000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](5000/previews/bondage.png) | [<NSFW, click to see>](5000/previews/free.png) |  |  | [<NSFW, click to see>](5000/previews/nude.png) | [<NSFW, click to see>](5000/previews/nude2.png) |  |  |
| 4500 | 0.824 | [Download](4500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](4500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](4500/previews/bondage.png) | [<NSFW, click to see>](4500/previews/free.png) |  |  | [<NSFW, click to see>](4500/previews/nude.png) | [<NSFW, click to see>](4500/previews/nude2.png) |  |  |
| 4000 | 0.797 | [Download](4000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](4000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](4000/previews/bondage.png) | [<NSFW, click to see>](4000/previews/free.png) |  |  | [<NSFW, click to see>](4000/previews/nude.png) | [<NSFW, click to see>](4000/previews/nude2.png) |  |  |
| 3500 | 0.847 | [Download](3500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](3500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](3500/previews/bondage.png) | [<NSFW, click to see>](3500/previews/free.png) |  |  | [<NSFW, click to see>](3500/previews/nude.png) | [<NSFW, click to see>](3500/previews/nude2.png) |  |  |
| 3000 | 0.857 | [Download](3000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](3000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](3000/previews/bondage.png) | [<NSFW, click to see>](3000/previews/free.png) |  |  | [<NSFW, click to see>](3000/previews/nude.png) | [<NSFW, click to see>](3000/previews/nude2.png) |  |  |
| 2500 | 0.859 | [Download](2500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](2500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](2500/previews/bondage.png) | [<NSFW, click to see>](2500/previews/free.png) |  |  | [<NSFW, click to see>](2500/previews/nude.png) | [<NSFW, click to see>](2500/previews/nude2.png) |  |  |
| 2000 | 0.787 | [Download](2000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](2000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](2000/previews/bondage.png) | [<NSFW, click to see>](2000/previews/free.png) |  |  | [<NSFW, click to see>](2000/previews/nude.png) | [<NSFW, click to see>](2000/previews/nude2.png) |  |  |
| 1500 | 0.814 | [Download](1500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](1500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](1500/previews/bondage.png) | [<NSFW, click to see>](1500/previews/free.png) |  |  | [<NSFW, click to see>](1500/previews/nude.png) | [<NSFW, click to see>](1500/previews/nude2.png) |  |  |
| 1000 | 0.822 | [Download](1000/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](1000/previews/pattern_6.png) |  |  | [<NSFW, click to see>](1000/previews/bondage.png) | [<NSFW, click to see>](1000/previews/free.png) |  |  | [<NSFW, click to see>](1000/previews/nude.png) | [<NSFW, click to see>](1000/previews/nude2.png) |  |  |
| 500 | 0.630 | [Download](500/shiraishi_tsumugi_theidolmstermillionlive.zip) |  |  |  |  |  | [<NSFW, click to see>](500/previews/pattern_6.png) |  |  | [<NSFW, click to see>](500/previews/bondage.png) | [<NSFW, click to see>](500/previews/free.png) |  |  | [<NSFW, click to see>](500/previews/nude.png) | [<NSFW, click to see>](500/previews/nude2.png) |  |  |
|
SakataHalmi/dqn-SpaceInvadersNoFrameskip-v4 | SakataHalmi | 2023-09-23T15:19:00Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T15:13:57Z | ---
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: 807.50 +/- 304.12
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 SakataHalmi -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 SakataHalmi -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 SakataHalmi
```
## 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', 10000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
milaidy/snowfro | milaidy | 2023-09-23T15:15:43Z | 2 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-09-23T15:03:18Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### snowfro Dreambooth model trained by milaidy with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
Atheer174/Products_NER3 | Atheer174 | 2023-09-23T14:54:52Z | 108 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:dslim/bert-base-NER",
"base_model:finetune:dslim/bert-base-NER",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-09-23T12:51:23Z | ---
license: mit
base_model: dslim/bert-base-NER
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Products_NER3
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. -->
# Products_NER3
This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1094
- Precision: 0.8738
- Recall: 0.9052
- F1: 0.8892
- Accuracy: 0.9365
## 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.1207 | 1.0 | 2470 | 0.1094 | 0.8738 | 0.9052 | 0.8892 | 0.9365 |
### Framework versions
- Transformers 4.33.2
- Pytorch 1.13.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
chanmuzi/flan-t5-large-financial-phrasebank-lora | chanmuzi | 2023-09-23T14:31:54Z | 1 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T13:58:47Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Ashyyy167/Kaeya | Ashyyy167 | 2023-09-23T14:05:50Z | 0 | 0 | null | [
"music",
"text-to-video",
"ja",
"en",
"dataset:b-mc2/sql-create-context",
"region:us"
]
| text-to-video | 2023-09-23T14:01:20Z | ---
datasets:
- b-mc2/sql-create-context
language:
- ja
- en
metrics:
- character
pipeline_tag: text-to-video
tags:
- music
--- |
chabir78/ppo-Huggy | chabir78 | 2023-09-23T14:01:00Z | 1 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
]
| reinforcement-learning | 2023-09-23T14:00:55Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
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: chabir78/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
arjunssat/Llama-2-7b-chat-finetune | arjunssat | 2023-09-23T13:55:39Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-09-09T12:05:55Z | ---
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **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 Data 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 Data 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]
|
lortigas/xlm-roberta-base-finetuned-panx-fr | lortigas | 2023-09-23T13:49:32Z | 106 | 0 | transformers | [
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-09-22T02:57:42Z | ---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-fr
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
args: PAN-X.fr
metrics:
- name: F1
type: f1
value: 0.927423283000487
---
<!-- 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. -->
# xlm-roberta-base-finetuned-panx-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1052
- F1: 0.9274
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.596 | 1.0 | 191 | 0.2408 | 0.8329 |
| 0.2555 | 2.0 | 382 | 0.1503 | 0.8932 |
| 0.1718 | 3.0 | 573 | 0.1052 | 0.9274 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1
- Datasets 1.16.1
- Tokenizers 0.13.3
|
pzpupu/chatglm2-6b-lora_version | pzpupu | 2023-09-23T13:48:22Z | 1 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T13:48:19Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
zineddine/ppo-LunarLander-v2 | zineddine | 2023-09-23T13:40:55Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-09-23T13:40:36Z | ---
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: 276.12 +/- 11.71
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
...
```
|
csocsci/mt5-base-multi-label-cs-iiib-02c | csocsci | 2023-09-23T13:40:51Z | 112 | 0 | transformers | [
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"cs",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-09-22T13:29:45Z | ---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
license: mit
language:
- cs
---
# Model Card for mt5-base-multi-label-cs-iiib-02c
<!-- Provide a quick summary of what the model is/does. -->
This model is fine-tuned for multi-label text classification of Supportive Interactions in Instant Messenger dialogs of Adolescents in Czech.
## Model Description
The model was fine-tuned on a dataset of Czech Instant Messenger dialogs of Adolescents. The classification is multi-label and the model outputs any combination of the tags:'NO TAG', 'Informační podpora', 'Emocionální podpora', 'Začlenění do skupiny', 'Uznání', 'Nabídka pomoci': as a string joined with ', ' (ordered alphabetically). Each label indicates the presence of that category of Supportive Interactions: 'no tag', 'informational support', 'emocional support', 'social companionship', 'appraisal', 'instrumental support'. The inputs of the model are: a target utterance and its bi-directional context; the label of the example is determined by the label of the target utterance.
- **Developed by:** Anonymous
- **Language(s):** multilingual
- **Finetuned from:** mt5-base
## Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/chi2024submission
- **Paper:** Stay tuned!
## Usage
Here is how to use this model to classify a context-window of a dialogue:
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import torch
test_texts = ['Utterance2']
test_text_pairs = ['Utterance1;Utterance2;Utterance3']
checkpoint_path = "chi2024/mt5-base-multi-label-cs-iiib-02c"
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint_path)\
.to("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained(checkpoint_path)
def verbalize_input(text: str, text_pair: str) -> str:
return "Utterance: %s\nContext: %s" % (text, text_pair)
def predict_one(text, pair):
input_pair = verbalize_input(text, pair)
inputs = tokenizer(input_pair, return_tensors="pt", padding=True,
truncation=True, max_length=256).to(model.device)
outputs = model.generate(**inputs)
decoded = [text.split(",")[0].strip() for text in
tokenizer.batch_decode(outputs, skip_special_tokens=True)]
return decoded
dec = predict_one(test_texts[0], test_text_pairs[0])
print(dec)
``` |
Yntec/GOLDFish | Yntec | 2023-09-23T13:35:34Z | 349 | 5 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"OLDFish",
"RMHF",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-17T10:26:48Z | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
- OLDFish
- RMHF
---
# GOLDFish
A mix between the models OLDFIsh by timevisitor and RMHF_2.5D_v2 by TkskKurumi.
Preview image by Digiplay:
Original pages:
https://civitai.com/models/14978?modelVersionId=40101
https://civitai.com/models/101518?modelVersionId=110456 |
Ori/llama-2-13b-peft-2wikihop-no-ret | Ori | 2023-09-23T13:34:03Z | 3 | 0 | peft | [
"peft",
"safetensors",
"region:us"
]
| null | 2023-09-23T13:31:57Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0.dev0
|
xueTr54/vit-base-patch16-224-in21k-finetuned-lora-food101 | xueTr54 | 2023-09-23T13:32:46Z | 6 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-09-23T13:24:23Z | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
mychen76/donut-receipt_v1 | mychen76 | 2023-09-23T13:07:23Z | 50 | 0 | transformers | [
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
]
| image-text-to-text | 2023-09-23T13:02:17Z | ---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
model-index:
- name: donut-receipt_v1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-receipt_v1
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
|
Subsets and Splits