modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-07-30 06:28:04
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 536
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-07-30 06:28:00
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
sam030/bert-fine-tuned-cola
|
sam030
| 2023-09-23T06:16:49Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T06:16:35Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_keras_callback
model-index:
- name: bert-fine-tuned-cola
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# bert-fine-tuned-cola
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.4359
- Validation Loss: 0.4255
- Epoch: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 0.4359 | 0.4255 | 0 |
### Framework versions
- Transformers 4.33.1
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.11.0
|
tomdeore/nonymus-llm
|
tomdeore
| 2023-09-23T06:00:09Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:abhishek/llama-2-7b-hf-small-shards",
"base_model:finetune:abhishek/llama-2-7b-hf-small-shards",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-23T03:27:27Z |
---
base_model: abhishek/llama-2-7b-hf-small-shards
tags:
- generated_from_trainer
model-index:
- name: nonymus-llm
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. -->
# nonymus-llm
This model is a fine-tuned version of [abhishek/llama-2-7b-hf-small-shards](https://huggingface.co/abhishek/llama-2-7b-hf-small-shards) 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Tokenizers 0.13.3
|
Sabari206/my_awesome_qa_model
|
Sabari206
| 2023-09-23T05:17:15Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"question-answering",
"generated_from_keras_callback",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-23T05:04:34Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: Sabari206/my_awesome_qa_model
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Sabari206/my_awesome_qa_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.5484
- Validation Loss: 1.6683
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 3.3795 | 2.0411 | 0 |
| 1.7773 | 1.6683 | 1 |
| 1.5484 | 1.6683 | 2 |
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
|
csocsci/mt5-base-binary-en-iiia-02c
|
csocsci
| 2023-09-23T05:12:11Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"multilingual",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-22T13:33:07Z |
---
# 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-binary-en-iiia-02c
<!-- Provide a quick summary of what the model is/does. -->
This model is fine-tuned for binary text classification of Supportive Interactions in Instant Messenger dialogs of Adolescents.
## Model Description
The model was fine-tuned on a dataset of English Instant Messenger dialogs of Adolescents. The classification is binary and the model outputs 'positive' or 'negative': Supportive Interactions present or not. The inputs are a target utterance and its bi-directional context; it's target label that 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
# Target utterance
test_texts = ['Utterance2']
# Bi-directional context of the target utterance
test_text_pairs = ['Utterance1;Utterance2;Utterance3']
# Load the model and tokenizer
checkpoint_path = "chi2024/mt5-base-binary-en-iiia-02c"
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 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.strip() for text in
tokenizer.batch_decode(outputs, skip_special_tokens=True)]
return decoded
# Run the prediction
preds_txt = [predict_one(t,p) for t,p in zip(test_texts, test_text_pairs)]
preds_lbl = [1 if x == 'positive' else 0 for x in preds_txt]
print(preds_lbl)
```
|
csocsci/mt5-base-binary-cs-iiia
|
csocsci
| 2023-09-23T05:02:47Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"cs",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-22T13:14:21Z |
---
# 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-binary-cs-iiia
<!-- Provide a quick summary of what the model is/does. -->
This model is fine-tuned for binary 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 binary and the model outputs 'positive' or 'negative': Supportive Interactions present or not. The inputs are a target utterance and its bi-directional context; it's target label that of the target utterance.
- **Developed by:** Anonymous
- **Language(s):** cs
- **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
# Target utterance
test_texts = ['Utterance2']
# Bi-directional context of the target utterance
test_text_pairs = ['Utterance1;Utterance2;Utterance3']
# Load the model and tokenizer
checkpoint_path = "chi2024/mt5-base-binary-cs-iiia"
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 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.strip() for text in
tokenizer.batch_decode(outputs, skip_special_tokens=True)]
return decoded
# Run the prediction
preds_txt = [predict_one(t,p) for t,p in zip(test_texts, test_text_pairs)]
preds_lbl = [1 if x == 'positive' else 0 for x in preds_txt]
print(preds_lbl)
```
|
ranajithore/stable-diffusion-v2-1-especially-trained-for-plant-cell-diagram
|
ranajithore
| 2023-09-23T04:57:45Z | 39 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-23T04:53:08Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### Stable-Diffusion-V2.1-especially-trained-for-plant-cell-diagram Dreambooth model trained by ranajithore 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:
|
Mahmoud22/TheBlokeRL-llama-7B-chat-gptq
|
Mahmoud22
| 2023-09-23T04:42:26Z | 0 | 0 |
peft
|
[
"peft",
"llama",
"4-bit",
"gptq",
"region:us"
] | null | 2023-09-23T04:33:53Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: gptq
- bits: 4
- tokenizer: None
- dataset: None
- group_size: 128
- damp_percent: 0.01
- desc_act: False
- sym: True
- true_sequential: True
- use_cuda_fp16: False
- model_seqlen: None
- block_name_to_quantize: None
- module_name_preceding_first_block: None
- batch_size: 1
- pad_token_id: None
- disable_exllama: False
### Framework versions
- PEFT 0.5.0
|
LumosD/grass
|
LumosD
| 2023-09-23T04:37:49Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:adapter:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-09-23T04:23:47Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - LumosD/grass
These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
890mari/practicaNLP
|
890mari
| 2023-09-23T04:24:28Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-23T03:06:57Z |
---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: practicaNLP
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8455882352941176
- name: F1
type: f1
value: 0.8930390492359932
---
<!-- 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. -->
# practicaNLP
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6320
- Accuracy: 0.8456
- F1: 0.8930
## 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
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.5255 | 1.09 | 500 | 0.4371 | 0.8431 | 0.8885 |
| 0.3452 | 2.18 | 1000 | 0.6320 | 0.8456 | 0.8930 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
hemanth11/opus-mt-en-fr
|
hemanth11
| 2023-09-23T04:19:27Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"marian",
"text2text-generation",
"translation",
"generated_from_trainer",
"dataset:hind_encorp",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-09-22T13:57:43Z |
---
tags:
- translation
- generated_from_trainer
datasets:
- hind_encorp
model-index:
- name: opus-mt-en-fr
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. -->
# opus-mt-en-fr
This model was trained from scratch on the hind_encorp 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
OpenDILabCommunity/LunarLander-v2-SAC
|
OpenDILabCommunity
| 2023-09-23T03:50:28Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"LunarLander-v2",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-04-14T05:02:58Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- LunarLander-v2
benchmark_name: OpenAI/Gym/Box2d
task_name: LunarLander-v2
pipeline_tag: reinforcement-learning
model-index:
- name: SAC
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Box2d-LunarLander-v2
type: OpenAI/Gym/Box2d-LunarLander-v2
metrics:
- type: mean_reward
value: 277.21 +/- 17.51
name: mean_reward
---
# Play **LunarLander-v2** with **SAC** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **SAC** implementation to OpenAI/Gym/Box2d **LunarLander-v2** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import SACAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
# Instantiate the agent
agent = SACAgent(
env_id="LunarLanderContinuous-v2", exp_name="lunarlander-sac", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import SACAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/LunarLander-v2-SAC")
# Instantiate the agent
agent = SACAgent(
env_id="LunarLanderContinuous-v2",
exp_name="LunarLander-v2-SAC",
cfg=cfg.exp_config,
policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import SACAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = SACAgent(env_id="LunarLanderContinuous-v2", exp_name="LunarLander-v2-SAC")
# Train the agent
return_ = agent.train(step=int(4000000), collector_env_num=8, evaluator_env_num=8)
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Box2d",
task_name="LunarLander-v2",
algo_name="SAC",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/sac.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./sac/lunarlander_sac_deploy.py",
usage_file_by_huggingface_ding="./sac/lunarlander_sac_download.py",
train_file="./sac/lunarlander_sac.py",
repo_id="OpenDILabCommunity/LunarLander-v2-SAC",
create_repo=False
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 260,
'n_evaluator_episode': 8,
'env_id': 'LunarLanderContinuous-v2',
'collector_env_num': 4,
'evaluator_env_num': 8,
'act_scale': True
},
'policy': {
'model': {
'twin_critic': True,
'action_space': 'reparameterization',
'obs_shape': 8,
'action_shape': 2
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 256,
'batch_size': 128,
'learning_rate_q': 0.001,
'learning_rate_policy': 0.0003,
'learning_rate_alpha': 0.0003,
'target_theta': 0.005,
'discount_factor': 0.99,
'alpha': 0.2,
'auto_alpha': True,
'log_space': True,
'target_entropy': None,
'ignore_done': False,
'init_w': 0.003
},
'collect': {
'collector': {},
'n_sample': 256,
'unroll_len': 1,
'collector_logit': False
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'figure_path': None,
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 260,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 100000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'sac',
'priority': False,
'priority_IS_weight': False,
'random_collect_size': 10000,
'transition_with_policy_data': True,
'multi_agent': False,
'cfg_type': 'SACPolicyDict'
},
'exp_name': 'LunarLander-v2-SAC',
'seed': 0,
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
}
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/LunarLander-v2-SAC)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/sac.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-SAC/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-SAC/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 116.05 KB
- **Last Update Date:** 2023-09-23
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Box2d
- **Task:** LunarLander-v2
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.9
- **PyTorch version:** 2.0.1+cu117
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html)
|
jingwora/inswapper_128
|
jingwora
| 2023-09-23T03:25:28Z | 0 | 0 | null |
[
"onnx",
"region:us"
] | null | 2023-09-23T03:20:10Z |
CLONED FROM - https://huggingface.co/deepinsight/inswapper
GITHUB - https://github.com/deepinsight
|
jmbilbao25/falcon-7b-instruct-sharded-finetuned
|
jmbilbao25
| 2023-09-23T02:33:12Z | 39 | 1 |
transformers
|
[
"transformers",
"pytorch",
"falcon",
"text-generation",
"custom_code",
"en",
"dataset:daily_dialog",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-21T09:30:01Z |
---
license: apache-2.0
datasets:
- daily_dialog
language:
- en
---
|
goldenrooster/multilingual-e5-large
|
goldenrooster
| 2023-09-23T02:27:29Z | 12 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"onnx",
"safetensors",
"xlm-roberta",
"mteb",
"Sentence Transformers",
"sentence-similarity",
"feature-extraction",
"multilingual",
"af",
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ug",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"zh",
"arxiv:2212.03533",
"arxiv:2108.08787",
"arxiv:2104.08663",
"arxiv:2210.07316",
"license:mit",
"model-index",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2023-09-23T02:26:33Z |
---
tags:
- mteb
- Sentence Transformers
- sentence-similarity
- feature-extraction
- sentence-transformers
model-index:
- name: multilingual-e5-large
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 79.05970149253731
- type: ap
value: 43.486574390835635
- type: f1
value: 73.32700092140148
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (de)
config: de
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 71.22055674518201
- type: ap
value: 81.55756710830498
- type: f1
value: 69.28271787752661
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en-ext)
config: en-ext
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 80.41979010494754
- type: ap
value: 29.34879922376344
- type: f1
value: 67.62475449011278
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (ja)
config: ja
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 77.8372591006424
- type: ap
value: 26.557560591210738
- type: f1
value: 64.96619417368707
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 93.489875
- type: ap
value: 90.98758636917603
- type: f1
value: 93.48554819717332
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 47.564
- type: f1
value: 46.75122173518047
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (de)
config: de
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 45.400000000000006
- type: f1
value: 44.17195682400632
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (es)
config: es
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 43.068
- type: f1
value: 42.38155696855596
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (fr)
config: fr
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 41.89
- type: f1
value: 40.84407321682663
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (ja)
config: ja
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 40.120000000000005
- type: f1
value: 39.522976223819114
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (zh)
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 38.832
- type: f1
value: 38.0392533394713
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.725
- type: map_at_10
value: 46.055
- type: map_at_100
value: 46.900999999999996
- type: map_at_1000
value: 46.911
- type: map_at_3
value: 41.548
- type: map_at_5
value: 44.297
- type: mrr_at_1
value: 31.152
- type: mrr_at_10
value: 46.231
- type: mrr_at_100
value: 47.07
- type: mrr_at_1000
value: 47.08
- type: mrr_at_3
value: 41.738
- type: mrr_at_5
value: 44.468999999999994
- type: ndcg_at_1
value: 30.725
- type: ndcg_at_10
value: 54.379999999999995
- type: ndcg_at_100
value: 58.138
- type: ndcg_at_1000
value: 58.389
- type: ndcg_at_3
value: 45.156
- type: ndcg_at_5
value: 50.123
- type: precision_at_1
value: 30.725
- type: precision_at_10
value: 8.087
- type: precision_at_100
value: 0.9769999999999999
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 18.54
- type: precision_at_5
value: 13.542000000000002
- type: recall_at_1
value: 30.725
- type: recall_at_10
value: 80.868
- type: recall_at_100
value: 97.653
- type: recall_at_1000
value: 99.57300000000001
- type: recall_at_3
value: 55.619
- type: recall_at_5
value: 67.71000000000001
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 44.30960650674069
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 38.427074197498996
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 60.28270056031872
- type: mrr
value: 74.38332673789738
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 84.05942144105269
- type: cos_sim_spearman
value: 82.51212105850809
- type: euclidean_pearson
value: 81.95639829909122
- type: euclidean_spearman
value: 82.3717564144213
- type: manhattan_pearson
value: 81.79273425468256
- type: manhattan_spearman
value: 82.20066817871039
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (de-en)
config: de-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.46764091858039
- type: f1
value: 99.37717466945023
- type: precision
value: 99.33194154488518
- type: recall
value: 99.46764091858039
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (fr-en)
config: fr-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 98.29407880255337
- type: f1
value: 98.11248073959938
- type: precision
value: 98.02443319392472
- type: recall
value: 98.29407880255337
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (ru-en)
config: ru-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 97.79009352268791
- type: f1
value: 97.5176076665512
- type: precision
value: 97.38136473848286
- type: recall
value: 97.79009352268791
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (zh-en)
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.26276987888363
- type: f1
value: 99.20133403545726
- type: precision
value: 99.17500438827453
- type: recall
value: 99.26276987888363
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 84.72727272727273
- type: f1
value: 84.67672206031433
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 35.34220182511161
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 33.4987096128766
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.558249999999997
- type: map_at_10
value: 34.44425000000001
- type: map_at_100
value: 35.59833333333333
- type: map_at_1000
value: 35.706916666666665
- type: map_at_3
value: 31.691749999999995
- type: map_at_5
value: 33.252916666666664
- type: mrr_at_1
value: 30.252666666666666
- type: mrr_at_10
value: 38.60675
- type: mrr_at_100
value: 39.42666666666666
- type: mrr_at_1000
value: 39.48408333333334
- type: mrr_at_3
value: 36.17441666666665
- type: mrr_at_5
value: 37.56275
- type: ndcg_at_1
value: 30.252666666666666
- type: ndcg_at_10
value: 39.683
- type: ndcg_at_100
value: 44.68541666666667
- type: ndcg_at_1000
value: 46.94316666666668
- type: ndcg_at_3
value: 34.961749999999995
- type: ndcg_at_5
value: 37.215666666666664
- type: precision_at_1
value: 30.252666666666666
- type: precision_at_10
value: 6.904166666666667
- type: precision_at_100
value: 1.0989999999999995
- type: precision_at_1000
value: 0.14733333333333334
- type: precision_at_3
value: 16.037666666666667
- type: precision_at_5
value: 11.413583333333333
- type: recall_at_1
value: 25.558249999999997
- type: recall_at_10
value: 51.13341666666666
- type: recall_at_100
value: 73.08366666666667
- type: recall_at_1000
value: 88.79483333333334
- type: recall_at_3
value: 37.989083333333326
- type: recall_at_5
value: 43.787833333333325
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 10.338
- type: map_at_10
value: 18.360000000000003
- type: map_at_100
value: 19.942
- type: map_at_1000
value: 20.134
- type: map_at_3
value: 15.174000000000001
- type: map_at_5
value: 16.830000000000002
- type: mrr_at_1
value: 23.257
- type: mrr_at_10
value: 33.768
- type: mrr_at_100
value: 34.707
- type: mrr_at_1000
value: 34.766000000000005
- type: mrr_at_3
value: 30.977
- type: mrr_at_5
value: 32.528
- type: ndcg_at_1
value: 23.257
- type: ndcg_at_10
value: 25.733
- type: ndcg_at_100
value: 32.288
- type: ndcg_at_1000
value: 35.992000000000004
- type: ndcg_at_3
value: 20.866
- type: ndcg_at_5
value: 22.612
- type: precision_at_1
value: 23.257
- type: precision_at_10
value: 8.124
- type: precision_at_100
value: 1.518
- type: precision_at_1000
value: 0.219
- type: precision_at_3
value: 15.679000000000002
- type: precision_at_5
value: 12.117
- type: recall_at_1
value: 10.338
- type: recall_at_10
value: 31.154
- type: recall_at_100
value: 54.161
- type: recall_at_1000
value: 75.21900000000001
- type: recall_at_3
value: 19.427
- type: recall_at_5
value: 24.214
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.498
- type: map_at_10
value: 19.103
- type: map_at_100
value: 27.375
- type: map_at_1000
value: 28.981
- type: map_at_3
value: 13.764999999999999
- type: map_at_5
value: 15.950000000000001
- type: mrr_at_1
value: 65.5
- type: mrr_at_10
value: 74.53800000000001
- type: mrr_at_100
value: 74.71799999999999
- type: mrr_at_1000
value: 74.725
- type: mrr_at_3
value: 72.792
- type: mrr_at_5
value: 73.554
- type: ndcg_at_1
value: 53.37499999999999
- type: ndcg_at_10
value: 41.286
- type: ndcg_at_100
value: 45.972
- type: ndcg_at_1000
value: 53.123
- type: ndcg_at_3
value: 46.172999999999995
- type: ndcg_at_5
value: 43.033
- type: precision_at_1
value: 65.5
- type: precision_at_10
value: 32.725
- type: precision_at_100
value: 10.683
- type: precision_at_1000
value: 1.978
- type: precision_at_3
value: 50
- type: precision_at_5
value: 41.349999999999994
- type: recall_at_1
value: 8.498
- type: recall_at_10
value: 25.070999999999998
- type: recall_at_100
value: 52.383
- type: recall_at_1000
value: 74.91499999999999
- type: recall_at_3
value: 15.207999999999998
- type: recall_at_5
value: 18.563
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 46.5
- type: f1
value: 41.93833713984145
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 67.914
- type: map_at_10
value: 78.10000000000001
- type: map_at_100
value: 78.333
- type: map_at_1000
value: 78.346
- type: map_at_3
value: 76.626
- type: map_at_5
value: 77.627
- type: mrr_at_1
value: 72.74199999999999
- type: mrr_at_10
value: 82.414
- type: mrr_at_100
value: 82.511
- type: mrr_at_1000
value: 82.513
- type: mrr_at_3
value: 81.231
- type: mrr_at_5
value: 82.065
- type: ndcg_at_1
value: 72.74199999999999
- type: ndcg_at_10
value: 82.806
- type: ndcg_at_100
value: 83.677
- type: ndcg_at_1000
value: 83.917
- type: ndcg_at_3
value: 80.305
- type: ndcg_at_5
value: 81.843
- type: precision_at_1
value: 72.74199999999999
- type: precision_at_10
value: 10.24
- type: precision_at_100
value: 1.089
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 31.268
- type: precision_at_5
value: 19.706000000000003
- type: recall_at_1
value: 67.914
- type: recall_at_10
value: 92.889
- type: recall_at_100
value: 96.42699999999999
- type: recall_at_1000
value: 97.92
- type: recall_at_3
value: 86.21
- type: recall_at_5
value: 90.036
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 22.166
- type: map_at_10
value: 35.57
- type: map_at_100
value: 37.405
- type: map_at_1000
value: 37.564
- type: map_at_3
value: 30.379
- type: map_at_5
value: 33.324
- type: mrr_at_1
value: 43.519000000000005
- type: mrr_at_10
value: 51.556000000000004
- type: mrr_at_100
value: 52.344
- type: mrr_at_1000
value: 52.373999999999995
- type: mrr_at_3
value: 48.868
- type: mrr_at_5
value: 50.319
- type: ndcg_at_1
value: 43.519000000000005
- type: ndcg_at_10
value: 43.803
- type: ndcg_at_100
value: 50.468999999999994
- type: ndcg_at_1000
value: 53.111
- type: ndcg_at_3
value: 38.893
- type: ndcg_at_5
value: 40.653
- type: precision_at_1
value: 43.519000000000005
- type: precision_at_10
value: 12.253
- type: precision_at_100
value: 1.931
- type: precision_at_1000
value: 0.242
- type: precision_at_3
value: 25.617
- type: precision_at_5
value: 19.383
- type: recall_at_1
value: 22.166
- type: recall_at_10
value: 51.6
- type: recall_at_100
value: 76.574
- type: recall_at_1000
value: 92.192
- type: recall_at_3
value: 34.477999999999994
- type: recall_at_5
value: 41.835
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 39.041
- type: map_at_10
value: 62.961999999999996
- type: map_at_100
value: 63.79899999999999
- type: map_at_1000
value: 63.854
- type: map_at_3
value: 59.399
- type: map_at_5
value: 61.669
- type: mrr_at_1
value: 78.082
- type: mrr_at_10
value: 84.321
- type: mrr_at_100
value: 84.49600000000001
- type: mrr_at_1000
value: 84.502
- type: mrr_at_3
value: 83.421
- type: mrr_at_5
value: 83.977
- type: ndcg_at_1
value: 78.082
- type: ndcg_at_10
value: 71.229
- type: ndcg_at_100
value: 74.10900000000001
- type: ndcg_at_1000
value: 75.169
- type: ndcg_at_3
value: 66.28699999999999
- type: ndcg_at_5
value: 69.084
- type: precision_at_1
value: 78.082
- type: precision_at_10
value: 14.993
- type: precision_at_100
value: 1.7239999999999998
- type: precision_at_1000
value: 0.186
- type: precision_at_3
value: 42.737
- type: precision_at_5
value: 27.843
- type: recall_at_1
value: 39.041
- type: recall_at_10
value: 74.96300000000001
- type: recall_at_100
value: 86.199
- type: recall_at_1000
value: 93.228
- type: recall_at_3
value: 64.105
- type: recall_at_5
value: 69.608
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 90.23160000000001
- type: ap
value: 85.5674856808308
- type: f1
value: 90.18033354786317
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 24.091
- type: map_at_10
value: 36.753
- type: map_at_100
value: 37.913000000000004
- type: map_at_1000
value: 37.958999999999996
- type: map_at_3
value: 32.818999999999996
- type: map_at_5
value: 35.171
- type: mrr_at_1
value: 24.742
- type: mrr_at_10
value: 37.285000000000004
- type: mrr_at_100
value: 38.391999999999996
- type: mrr_at_1000
value: 38.431
- type: mrr_at_3
value: 33.440999999999995
- type: mrr_at_5
value: 35.75
- type: ndcg_at_1
value: 24.742
- type: ndcg_at_10
value: 43.698
- type: ndcg_at_100
value: 49.145
- type: ndcg_at_1000
value: 50.23800000000001
- type: ndcg_at_3
value: 35.769
- type: ndcg_at_5
value: 39.961999999999996
- type: precision_at_1
value: 24.742
- type: precision_at_10
value: 6.7989999999999995
- type: precision_at_100
value: 0.95
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 15.096000000000002
- type: precision_at_5
value: 11.183
- type: recall_at_1
value: 24.091
- type: recall_at_10
value: 65.068
- type: recall_at_100
value: 89.899
- type: recall_at_1000
value: 98.16
- type: recall_at_3
value: 43.68
- type: recall_at_5
value: 53.754999999999995
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 93.66621067031465
- type: f1
value: 93.49622853272142
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (de)
config: de
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 91.94702733164272
- type: f1
value: 91.17043441745282
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (es)
config: es
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.20146764509674
- type: f1
value: 91.98359080555608
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (fr)
config: fr
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 88.99780770435328
- type: f1
value: 89.19746342724068
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (hi)
config: hi
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 89.78486912871998
- type: f1
value: 89.24578823628642
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (th)
config: th
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 88.74502712477394
- type: f1
value: 89.00297573881542
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 77.9046967624259
- type: f1
value: 59.36787125785957
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (de)
config: de
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 74.5280360664976
- type: f1
value: 57.17723440888718
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (es)
config: es
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 75.44029352901934
- type: f1
value: 54.052855531072964
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (fr)
config: fr
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 70.5606013153774
- type: f1
value: 52.62215934386531
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (hi)
config: hi
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 73.11581211903908
- type: f1
value: 52.341291845645465
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (th)
config: th
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 74.28933092224233
- type: f1
value: 57.07918745504911
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (af)
config: af
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.38063214525892
- type: f1
value: 59.46463723443009
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (am)
config: am
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 56.06926698049766
- type: f1
value: 52.49084283283562
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ar)
config: ar
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.74983187626093
- type: f1
value: 56.960640620165904
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (az)
config: az
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.86550100874243
- type: f1
value: 62.47370548140688
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (bn)
config: bn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.971082716879636
- type: f1
value: 61.03812421957381
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (cy)
config: cy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 54.98318762609282
- type: f1
value: 51.51207916008392
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (da)
config: da
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.45527908540686
- type: f1
value: 66.16631905400318
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (de)
config: de
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.32750504371216
- type: f1
value: 66.16755288646591
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (el)
config: el
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.09213180901143
- type: f1
value: 66.95654394661507
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.75588433086752
- type: f1
value: 71.79973779656923
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (es)
config: es
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.49428379287154
- type: f1
value: 68.37494379215734
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fa)
config: fa
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.90921318090115
- type: f1
value: 66.79517376481645
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fi)
config: fi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.12104909213181
- type: f1
value: 67.29448842879584
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fr)
config: fr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.34095494283793
- type: f1
value: 67.01134288992947
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (he)
config: he
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.61264290517822
- type: f1
value: 64.68730512660757
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hi)
config: hi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.79757901815738
- type: f1
value: 65.24938539425598
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hu)
config: hu
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.68728984532616
- type: f1
value: 67.0487169762553
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hy)
config: hy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.07464694014795
- type: f1
value: 59.183532276789286
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (id)
config: id
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.04707464694015
- type: f1
value: 67.66829629003848
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (is)
config: is
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.42434431741762
- type: f1
value: 59.01617226544757
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (it)
config: it
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.53127101546738
- type: f1
value: 68.10033760906255
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ja)
config: ja
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.50504371217215
- type: f1
value: 69.74931103158923
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (jv)
config: jv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 57.91190316072628
- type: f1
value: 54.05551136648796
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ka)
config: ka
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 51.78211163416275
- type: f1
value: 49.874888544058535
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (km)
config: km
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 47.017484868863484
- type: f1
value: 44.53364263352014
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (kn)
config: kn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.16207128446537
- type: f1
value: 59.01185692320829
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ko)
config: ko
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.42501681237391
- type: f1
value: 67.13169450166086
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (lv)
config: lv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.0780094149294
- type: f1
value: 64.41720167850707
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ml)
config: ml
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.57162071284466
- type: f1
value: 62.414138683804424
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (mn)
config: mn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.71149966375252
- type: f1
value: 58.594805125087234
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ms)
config: ms
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.03900470746471
- type: f1
value: 63.87937257883887
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (my)
config: my
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.8776059179556
- type: f1
value: 57.48587618059131
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (nb)
config: nb
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.87895090786819
- type: f1
value: 66.8141299430347
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (nl)
config: nl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.45057162071285
- type: f1
value: 67.46444039673516
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (pl)
config: pl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.546738399462
- type: f1
value: 68.63640876702655
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (pt)
config: pt
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.72965702757229
- type: f1
value: 68.54119560379115
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ro)
config: ro
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.35574983187625
- type: f1
value: 65.88844917691927
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ru)
config: ru
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.70477471418964
- type: f1
value: 69.19665697061978
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sl)
config: sl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.0880968392737
- type: f1
value: 64.76962317666086
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sq)
config: sq
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.18493611297916
- type: f1
value: 62.49984559035371
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sv)
config: sv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.75857431069265
- type: f1
value: 69.20053687623418
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sw)
config: sw
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.500336247478145
- type: f1
value: 55.2972398687929
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ta)
config: ta
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.68997982515132
- type: f1
value: 59.36848202755348
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (te)
config: te
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.01950235373235
- type: f1
value: 60.09351954625423
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (th)
config: th
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.29186281102892
- type: f1
value: 67.57860496703447
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (tl)
config: tl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.77471418964357
- type: f1
value: 61.913983147713836
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (tr)
config: tr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.87222595830532
- type: f1
value: 66.03679033708141
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ur)
config: ur
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.04505716207127
- type: f1
value: 61.28569169817908
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (vi)
config: vi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.38466711499663
- type: f1
value: 67.20532357036844
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-CN)
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.12306657700067
- type: f1
value: 68.91251226588182
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-TW)
config: zh-TW
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.20040349697378
- type: f1
value: 66.02657347714175
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (af)
config: af
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.73907195696032
- type: f1
value: 66.98484521791418
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (am)
config: am
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 60.58843308675185
- type: f1
value: 58.95591723092005
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ar)
config: ar
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.22730329522528
- type: f1
value: 66.0894499712115
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (az)
config: az
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.48285137861465
- type: f1
value: 65.21963176785157
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (bn)
config: bn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.74714189643578
- type: f1
value: 66.8212192745412
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (cy)
config: cy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 59.09213180901143
- type: f1
value: 56.70735546356339
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (da)
config: da
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.05716207128448
- type: f1
value: 74.8413712365364
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (de)
config: de
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.69737726967047
- type: f1
value: 74.7664341963
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (el)
config: el
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.90383322125084
- type: f1
value: 73.59201554448323
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.51176866173503
- type: f1
value: 77.46104434577758
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (es)
config: es
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.31069266980496
- type: f1
value: 74.61048660675635
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fa)
config: fa
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.95225285810356
- type: f1
value: 72.33160006574627
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fi)
config: fi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.12373907195696
- type: f1
value: 73.20921012557481
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fr)
config: fr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.86684599865501
- type: f1
value: 73.82348774610831
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (he)
config: he
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.40215198386012
- type: f1
value: 71.11945183971858
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hi)
config: hi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.12844653665098
- type: f1
value: 71.34450495911766
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hu)
config: hu
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.52252858103566
- type: f1
value: 73.98878711342999
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hy)
config: hy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.93611297915265
- type: f1
value: 63.723200467653385
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (id)
config: id
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.11903160726295
- type: f1
value: 73.82138439467096
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (is)
config: is
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.15198386012105
- type: f1
value: 66.02172193802167
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (it)
config: it
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.32414256893072
- type: f1
value: 74.30943421170574
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ja)
config: ja
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.46805648957633
- type: f1
value: 77.62808409298209
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (jv)
config: jv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.318762609280434
- type: f1
value: 62.094284066075076
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ka)
config: ka
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 58.34902488231338
- type: f1
value: 57.12893860987984
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (km)
config: km
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 50.88433086751849
- type: f1
value: 48.2272350802058
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (kn)
config: kn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.4425016812374
- type: f1
value: 64.61463095996173
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ko)
config: ko
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.04707464694015
- type: f1
value: 75.05099199098998
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (lv)
config: lv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.50437121721586
- type: f1
value: 69.83397721096314
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ml)
config: ml
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.94283792871553
- type: f1
value: 68.8704663703913
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (mn)
config: mn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.79488903833222
- type: f1
value: 63.615424063345436
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ms)
config: ms
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.88231338264963
- type: f1
value: 68.57892302593237
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (my)
config: my
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.248150638870214
- type: f1
value: 61.06680605338809
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (nb)
config: nb
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.84196368527236
- type: f1
value: 74.52566464968763
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (nl)
config: nl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.8285137861466
- type: f1
value: 74.8853197608802
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (pl)
config: pl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.13248150638869
- type: f1
value: 74.3982040999179
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (pt)
config: pt
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.49024882313383
- type: f1
value: 73.82153848368573
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ro)
config: ro
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.72158708809684
- type: f1
value: 71.85049433180541
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ru)
config: ru
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.137861466039
- type: f1
value: 75.37628348188467
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sl)
config: sl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.86953597848016
- type: f1
value: 71.87537624521661
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sq)
config: sq
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.27572293207801
- type: f1
value: 68.80017302344231
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sv)
config: sv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.09952925353059
- type: f1
value: 76.07992707688408
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sw)
config: sw
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.140551445864155
- type: f1
value: 61.73855010331415
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ta)
config: ta
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.27774041694687
- type: f1
value: 64.83664868894539
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (te)
config: te
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.69468728984533
- type: f1
value: 64.76239666920868
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (th)
config: th
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.44653665097512
- type: f1
value: 73.14646052013873
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (tl)
config: tl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.71351714862139
- type: f1
value: 66.67212180163382
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (tr)
config: tr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.9946200403497
- type: f1
value: 73.87348793725525
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ur)
config: ur
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.15400134498992
- type: f1
value: 67.09433241421094
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (vi)
config: vi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.11365164761264
- type: f1
value: 73.59502539433753
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-CN)
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.82582380632145
- type: f1
value: 76.89992945316313
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-TW)
config: zh-TW
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.81237390719569
- type: f1
value: 72.36499770986265
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 31.480506569594695
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 29.71252128004552
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 31.421396787056548
- type: mrr
value: 32.48155274872267
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.595
- type: map_at_10
value: 12.642000000000001
- type: map_at_100
value: 15.726
- type: map_at_1000
value: 17.061999999999998
- type: map_at_3
value: 9.125
- type: map_at_5
value: 10.866000000000001
- type: mrr_at_1
value: 43.344
- type: mrr_at_10
value: 52.227999999999994
- type: mrr_at_100
value: 52.898999999999994
- type: mrr_at_1000
value: 52.944
- type: mrr_at_3
value: 49.845
- type: mrr_at_5
value: 51.115
- type: ndcg_at_1
value: 41.949999999999996
- type: ndcg_at_10
value: 33.995
- type: ndcg_at_100
value: 30.869999999999997
- type: ndcg_at_1000
value: 39.487
- type: ndcg_at_3
value: 38.903999999999996
- type: ndcg_at_5
value: 37.236999999999995
- type: precision_at_1
value: 43.344
- type: precision_at_10
value: 25.480000000000004
- type: precision_at_100
value: 7.672
- type: precision_at_1000
value: 2.028
- type: precision_at_3
value: 36.636
- type: precision_at_5
value: 32.632
- type: recall_at_1
value: 5.595
- type: recall_at_10
value: 16.466
- type: recall_at_100
value: 31.226
- type: recall_at_1000
value: 62.778999999999996
- type: recall_at_3
value: 9.931
- type: recall_at_5
value: 12.884
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 40.414
- type: map_at_10
value: 56.754000000000005
- type: map_at_100
value: 57.457
- type: map_at_1000
value: 57.477999999999994
- type: map_at_3
value: 52.873999999999995
- type: map_at_5
value: 55.175
- type: mrr_at_1
value: 45.278
- type: mrr_at_10
value: 59.192
- type: mrr_at_100
value: 59.650000000000006
- type: mrr_at_1000
value: 59.665
- type: mrr_at_3
value: 56.141
- type: mrr_at_5
value: 57.998000000000005
- type: ndcg_at_1
value: 45.278
- type: ndcg_at_10
value: 64.056
- type: ndcg_at_100
value: 66.89
- type: ndcg_at_1000
value: 67.364
- type: ndcg_at_3
value: 56.97
- type: ndcg_at_5
value: 60.719
- type: precision_at_1
value: 45.278
- type: precision_at_10
value: 9.994
- type: precision_at_100
value: 1.165
- type: precision_at_1000
value: 0.121
- type: precision_at_3
value: 25.512
- type: precision_at_5
value: 17.509
- type: recall_at_1
value: 40.414
- type: recall_at_10
value: 83.596
- type: recall_at_100
value: 95.72
- type: recall_at_1000
value: 99.24
- type: recall_at_3
value: 65.472
- type: recall_at_5
value: 74.039
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 70.352
- type: map_at_10
value: 84.369
- type: map_at_100
value: 85.02499999999999
- type: map_at_1000
value: 85.04
- type: map_at_3
value: 81.42399999999999
- type: map_at_5
value: 83.279
- type: mrr_at_1
value: 81.05
- type: mrr_at_10
value: 87.401
- type: mrr_at_100
value: 87.504
- type: mrr_at_1000
value: 87.505
- type: mrr_at_3
value: 86.443
- type: mrr_at_5
value: 87.10799999999999
- type: ndcg_at_1
value: 81.04
- type: ndcg_at_10
value: 88.181
- type: ndcg_at_100
value: 89.411
- type: ndcg_at_1000
value: 89.507
- type: ndcg_at_3
value: 85.28099999999999
- type: ndcg_at_5
value: 86.888
- type: precision_at_1
value: 81.04
- type: precision_at_10
value: 13.406
- type: precision_at_100
value: 1.5350000000000001
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.31
- type: precision_at_5
value: 24.54
- type: recall_at_1
value: 70.352
- type: recall_at_10
value: 95.358
- type: recall_at_100
value: 99.541
- type: recall_at_1000
value: 99.984
- type: recall_at_3
value: 87.111
- type: recall_at_5
value: 91.643
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 46.54068723291946
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 63.216287629895994
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.023000000000001
- type: map_at_10
value: 10.071
- type: map_at_100
value: 11.892
- type: map_at_1000
value: 12.196
- type: map_at_3
value: 7.234
- type: map_at_5
value: 8.613999999999999
- type: mrr_at_1
value: 19.900000000000002
- type: mrr_at_10
value: 30.516
- type: mrr_at_100
value: 31.656000000000002
- type: mrr_at_1000
value: 31.723000000000003
- type: mrr_at_3
value: 27.400000000000002
- type: mrr_at_5
value: 29.270000000000003
- type: ndcg_at_1
value: 19.900000000000002
- type: ndcg_at_10
value: 17.474
- type: ndcg_at_100
value: 25.020999999999997
- type: ndcg_at_1000
value: 30.728
- type: ndcg_at_3
value: 16.588
- type: ndcg_at_5
value: 14.498
- type: precision_at_1
value: 19.900000000000002
- type: precision_at_10
value: 9.139999999999999
- type: precision_at_100
value: 2.011
- type: precision_at_1000
value: 0.33899999999999997
- type: precision_at_3
value: 15.667
- type: precision_at_5
value: 12.839999999999998
- type: recall_at_1
value: 4.023000000000001
- type: recall_at_10
value: 18.497
- type: recall_at_100
value: 40.8
- type: recall_at_1000
value: 68.812
- type: recall_at_3
value: 9.508
- type: recall_at_5
value: 12.983
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 83.967008785134
- type: cos_sim_spearman
value: 80.23142141101837
- type: euclidean_pearson
value: 81.20166064704539
- type: euclidean_spearman
value: 80.18961335654585
- type: manhattan_pearson
value: 81.13925443187625
- type: manhattan_spearman
value: 80.07948723044424
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 86.94262461316023
- type: cos_sim_spearman
value: 80.01596278563865
- type: euclidean_pearson
value: 83.80799622922581
- type: euclidean_spearman
value: 79.94984954947103
- type: manhattan_pearson
value: 83.68473841756281
- type: manhattan_spearman
value: 79.84990707951822
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 80.57346443146068
- type: cos_sim_spearman
value: 81.54689837570866
- type: euclidean_pearson
value: 81.10909881516007
- type: euclidean_spearman
value: 81.56746243261762
- type: manhattan_pearson
value: 80.87076036186582
- type: manhattan_spearman
value: 81.33074987964402
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 79.54733787179849
- type: cos_sim_spearman
value: 77.72202105610411
- type: euclidean_pearson
value: 78.9043595478849
- type: euclidean_spearman
value: 77.93422804309435
- type: manhattan_pearson
value: 78.58115121621368
- type: manhattan_spearman
value: 77.62508135122033
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 88.59880017237558
- type: cos_sim_spearman
value: 89.31088630824758
- type: euclidean_pearson
value: 88.47069261564656
- type: euclidean_spearman
value: 89.33581971465233
- type: manhattan_pearson
value: 88.40774264100956
- type: manhattan_spearman
value: 89.28657485627835
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 84.08055117917084
- type: cos_sim_spearman
value: 85.78491813080304
- type: euclidean_pearson
value: 84.99329155500392
- type: euclidean_spearman
value: 85.76728064677287
- type: manhattan_pearson
value: 84.87947428989587
- type: manhattan_spearman
value: 85.62429454917464
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (ko-ko)
config: ko-ko
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 82.14190939287384
- type: cos_sim_spearman
value: 82.27331573306041
- type: euclidean_pearson
value: 81.891896953716
- type: euclidean_spearman
value: 82.37695542955998
- type: manhattan_pearson
value: 81.73123869460504
- type: manhattan_spearman
value: 82.19989168441421
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (ar-ar)
config: ar-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 76.84695301843362
- type: cos_sim_spearman
value: 77.87790986014461
- type: euclidean_pearson
value: 76.91981583106315
- type: euclidean_spearman
value: 77.88154772749589
- type: manhattan_pearson
value: 76.94953277451093
- type: manhattan_spearman
value: 77.80499230728604
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-ar)
config: en-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 75.44657840482016
- type: cos_sim_spearman
value: 75.05531095119674
- type: euclidean_pearson
value: 75.88161755829299
- type: euclidean_spearman
value: 74.73176238219332
- type: manhattan_pearson
value: 75.63984765635362
- type: manhattan_spearman
value: 74.86476440770737
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-de)
config: en-de
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 85.64700140524133
- type: cos_sim_spearman
value: 86.16014210425672
- type: euclidean_pearson
value: 86.49086860843221
- type: euclidean_spearman
value: 86.09729326815614
- type: manhattan_pearson
value: 86.43406265125513
- type: manhattan_spearman
value: 86.17740150939994
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.91170098764921
- type: cos_sim_spearman
value: 88.12437004058931
- type: euclidean_pearson
value: 88.81828254494437
- type: euclidean_spearman
value: 88.14831794572122
- type: manhattan_pearson
value: 88.93442183448961
- type: manhattan_spearman
value: 88.15254630778304
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-tr)
config: en-tr
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 72.91390577997292
- type: cos_sim_spearman
value: 71.22979457536074
- type: euclidean_pearson
value: 74.40314008106749
- type: euclidean_spearman
value: 72.54972136083246
- type: manhattan_pearson
value: 73.85687539530218
- type: manhattan_spearman
value: 72.09500771742637
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (es-en)
config: es-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 80.9301067983089
- type: cos_sim_spearman
value: 80.74989828346473
- type: euclidean_pearson
value: 81.36781301814257
- type: euclidean_spearman
value: 80.9448819964426
- type: manhattan_pearson
value: 81.0351322685609
- type: manhattan_spearman
value: 80.70192121844177
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (es-es)
config: es-es
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.13820465980005
- type: cos_sim_spearman
value: 86.73532498758757
- type: euclidean_pearson
value: 87.21329451846637
- type: euclidean_spearman
value: 86.57863198601002
- type: manhattan_pearson
value: 87.06973713818554
- type: manhattan_spearman
value: 86.47534918791499
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (fr-en)
config: fr-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 85.48720108904415
- type: cos_sim_spearman
value: 85.62221757068387
- type: euclidean_pearson
value: 86.1010129512749
- type: euclidean_spearman
value: 85.86580966509942
- type: manhattan_pearson
value: 86.26800938808971
- type: manhattan_spearman
value: 85.88902721678429
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (it-en)
config: it-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 83.98021347333516
- type: cos_sim_spearman
value: 84.53806553803501
- type: euclidean_pearson
value: 84.61483347248364
- type: euclidean_spearman
value: 85.14191408011702
- type: manhattan_pearson
value: 84.75297588825967
- type: manhattan_spearman
value: 85.33176753669242
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (nl-en)
config: nl-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 84.51856644893233
- type: cos_sim_spearman
value: 85.27510748506413
- type: euclidean_pearson
value: 85.09886861540977
- type: euclidean_spearman
value: 85.62579245860887
- type: manhattan_pearson
value: 84.93017860464607
- type: manhattan_spearman
value: 85.5063988898453
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 62.581573200584195
- type: cos_sim_spearman
value: 63.05503590247928
- type: euclidean_pearson
value: 63.652564812602094
- type: euclidean_spearman
value: 62.64811520876156
- type: manhattan_pearson
value: 63.506842893061076
- type: manhattan_spearman
value: 62.51289573046917
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de)
config: de
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 48.2248801729127
- type: cos_sim_spearman
value: 56.5936604678561
- type: euclidean_pearson
value: 43.98149464089
- type: euclidean_spearman
value: 56.108561882423615
- type: manhattan_pearson
value: 43.86880305903564
- type: manhattan_spearman
value: 56.04671150510166
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es)
config: es
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 55.17564527009831
- type: cos_sim_spearman
value: 64.57978560979488
- type: euclidean_pearson
value: 58.8818330154583
- type: euclidean_spearman
value: 64.99214839071281
- type: manhattan_pearson
value: 58.72671436121381
- type: manhattan_spearman
value: 65.10713416616109
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (pl)
config: pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 26.772131864023297
- type: cos_sim_spearman
value: 34.68200792408681
- type: euclidean_pearson
value: 16.68082419005441
- type: euclidean_spearman
value: 34.83099932652166
- type: manhattan_pearson
value: 16.52605949659529
- type: manhattan_spearman
value: 34.82075801399475
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (tr)
config: tr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 54.42415189043831
- type: cos_sim_spearman
value: 63.54594264576758
- type: euclidean_pearson
value: 57.36577498297745
- type: euclidean_spearman
value: 63.111466379158074
- type: manhattan_pearson
value: 57.584543715873885
- type: manhattan_spearman
value: 63.22361054139183
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (ar)
config: ar
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 47.55216762405518
- type: cos_sim_spearman
value: 56.98670142896412
- type: euclidean_pearson
value: 50.15318757562699
- type: euclidean_spearman
value: 56.524941926541906
- type: manhattan_pearson
value: 49.955618528674904
- type: manhattan_spearman
value: 56.37102209240117
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (ru)
config: ru
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 49.20540980338571
- type: cos_sim_spearman
value: 59.9009453504406
- type: euclidean_pearson
value: 49.557749853620535
- type: euclidean_spearman
value: 59.76631621172456
- type: manhattan_pearson
value: 49.62340591181147
- type: manhattan_spearman
value: 59.94224880322436
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 51.508169956576985
- type: cos_sim_spearman
value: 66.82461565306046
- type: euclidean_pearson
value: 56.2274426480083
- type: euclidean_spearman
value: 66.6775323848333
- type: manhattan_pearson
value: 55.98277796300661
- type: manhattan_spearman
value: 66.63669848497175
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (fr)
config: fr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 72.86478788045507
- type: cos_sim_spearman
value: 76.7946552053193
- type: euclidean_pearson
value: 75.01598530490269
- type: euclidean_spearman
value: 76.83618917858281
- type: manhattan_pearson
value: 74.68337628304332
- type: manhattan_spearman
value: 76.57480204017773
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-en)
config: de-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 55.922619099401984
- type: cos_sim_spearman
value: 56.599362477240774
- type: euclidean_pearson
value: 56.68307052369783
- type: euclidean_spearman
value: 54.28760436777401
- type: manhattan_pearson
value: 56.67763566500681
- type: manhattan_spearman
value: 53.94619541711359
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es-en)
config: es-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 66.74357206710913
- type: cos_sim_spearman
value: 72.5208244925311
- type: euclidean_pearson
value: 67.49254562186032
- type: euclidean_spearman
value: 72.02469076238683
- type: manhattan_pearson
value: 67.45251772238085
- type: manhattan_spearman
value: 72.05538819984538
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (it)
config: it
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 71.25734330033191
- type: cos_sim_spearman
value: 76.98349083946823
- type: euclidean_pearson
value: 73.71642838667736
- type: euclidean_spearman
value: 77.01715504651384
- type: manhattan_pearson
value: 73.61712711868105
- type: manhattan_spearman
value: 77.01392571153896
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (pl-en)
config: pl-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 63.18215462781212
- type: cos_sim_spearman
value: 65.54373266117607
- type: euclidean_pearson
value: 64.54126095439005
- type: euclidean_spearman
value: 65.30410369102711
- type: manhattan_pearson
value: 63.50332221148234
- type: manhattan_spearman
value: 64.3455878104313
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh-en)
config: zh-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 62.30509221440029
- type: cos_sim_spearman
value: 65.99582704642478
- type: euclidean_pearson
value: 63.43818859884195
- type: euclidean_spearman
value: 66.83172582815764
- type: manhattan_pearson
value: 63.055779168508764
- type: manhattan_spearman
value: 65.49585020501449
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es-it)
config: es-it
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 59.587830825340404
- type: cos_sim_spearman
value: 68.93467614588089
- type: euclidean_pearson
value: 62.3073527367404
- type: euclidean_spearman
value: 69.69758171553175
- type: manhattan_pearson
value: 61.9074580815789
- type: manhattan_spearman
value: 69.57696375597865
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-fr)
config: de-fr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 57.143220125577066
- type: cos_sim_spearman
value: 67.78857859159226
- type: euclidean_pearson
value: 55.58225107923733
- type: euclidean_spearman
value: 67.80662907184563
- type: manhattan_pearson
value: 56.24953502726514
- type: manhattan_spearman
value: 67.98262125431616
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-pl)
config: de-pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 21.826928900322066
- type: cos_sim_spearman
value: 49.578506634400405
- type: euclidean_pearson
value: 27.939890138843214
- type: euclidean_spearman
value: 52.71950519136242
- type: manhattan_pearson
value: 26.39878683847546
- type: manhattan_spearman
value: 47.54609580342499
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (fr-pl)
config: fr-pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 57.27603854632001
- type: cos_sim_spearman
value: 50.709255283710995
- type: euclidean_pearson
value: 59.5419024445929
- type: euclidean_spearman
value: 50.709255283710995
- type: manhattan_pearson
value: 59.03256832438492
- type: manhattan_spearman
value: 61.97797868009122
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 85.00757054859712
- type: cos_sim_spearman
value: 87.29283629622222
- type: euclidean_pearson
value: 86.54824171775536
- type: euclidean_spearman
value: 87.24364730491402
- type: manhattan_pearson
value: 86.5062156915074
- type: manhattan_spearman
value: 87.15052170378574
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 82.03549357197389
- type: mrr
value: 95.05437645143527
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 57.260999999999996
- type: map_at_10
value: 66.259
- type: map_at_100
value: 66.884
- type: map_at_1000
value: 66.912
- type: map_at_3
value: 63.685
- type: map_at_5
value: 65.35499999999999
- type: mrr_at_1
value: 60.333000000000006
- type: mrr_at_10
value: 67.5
- type: mrr_at_100
value: 68.013
- type: mrr_at_1000
value: 68.038
- type: mrr_at_3
value: 65.61099999999999
- type: mrr_at_5
value: 66.861
- type: ndcg_at_1
value: 60.333000000000006
- type: ndcg_at_10
value: 70.41
- type: ndcg_at_100
value: 73.10600000000001
- type: ndcg_at_1000
value: 73.846
- type: ndcg_at_3
value: 66.133
- type: ndcg_at_5
value: 68.499
- type: precision_at_1
value: 60.333000000000006
- type: precision_at_10
value: 9.232999999999999
- type: precision_at_100
value: 1.0630000000000002
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 25.667
- type: precision_at_5
value: 17.067
- type: recall_at_1
value: 57.260999999999996
- type: recall_at_10
value: 81.94399999999999
- type: recall_at_100
value: 93.867
- type: recall_at_1000
value: 99.667
- type: recall_at_3
value: 70.339
- type: recall_at_5
value: 76.25
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.74356435643564
- type: cos_sim_ap
value: 93.13411948212683
- type: cos_sim_f1
value: 86.80521991300147
- type: cos_sim_precision
value: 84.00374181478017
- type: cos_sim_recall
value: 89.8
- type: dot_accuracy
value: 99.67920792079208
- type: dot_ap
value: 89.27277565444479
- type: dot_f1
value: 83.9276990718124
- type: dot_precision
value: 82.04393505253104
- type: dot_recall
value: 85.9
- type: euclidean_accuracy
value: 99.74257425742574
- type: euclidean_ap
value: 93.17993008259062
- type: euclidean_f1
value: 86.69396110542476
- type: euclidean_precision
value: 88.78406708595388
- type: euclidean_recall
value: 84.7
- type: manhattan_accuracy
value: 99.74257425742574
- type: manhattan_ap
value: 93.14413755550099
- type: manhattan_f1
value: 86.82483594144371
- type: manhattan_precision
value: 87.66564729867483
- type: manhattan_recall
value: 86
- type: max_accuracy
value: 99.74356435643564
- type: max_ap
value: 93.17993008259062
- type: max_f1
value: 86.82483594144371
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 57.525863806168566
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 32.68850574423839
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 49.71580650644033
- type: mrr
value: 50.50971903913081
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 29.152190498799484
- type: cos_sim_spearman
value: 29.686180371952727
- type: dot_pearson
value: 27.248664793816342
- type: dot_spearman
value: 28.37748983721745
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.20400000000000001
- type: map_at_10
value: 1.6209999999999998
- type: map_at_100
value: 9.690999999999999
- type: map_at_1000
value: 23.733
- type: map_at_3
value: 0.575
- type: map_at_5
value: 0.885
- type: mrr_at_1
value: 78
- type: mrr_at_10
value: 86.56700000000001
- type: mrr_at_100
value: 86.56700000000001
- type: mrr_at_1000
value: 86.56700000000001
- type: mrr_at_3
value: 85.667
- type: mrr_at_5
value: 86.56700000000001
- type: ndcg_at_1
value: 76
- type: ndcg_at_10
value: 71.326
- type: ndcg_at_100
value: 54.208999999999996
- type: ndcg_at_1000
value: 49.252
- type: ndcg_at_3
value: 74.235
- type: ndcg_at_5
value: 73.833
- type: precision_at_1
value: 78
- type: precision_at_10
value: 74.8
- type: precision_at_100
value: 55.50000000000001
- type: precision_at_1000
value: 21.836
- type: precision_at_3
value: 78
- type: precision_at_5
value: 78
- type: recall_at_1
value: 0.20400000000000001
- type: recall_at_10
value: 1.894
- type: recall_at_100
value: 13.245999999999999
- type: recall_at_1000
value: 46.373
- type: recall_at_3
value: 0.613
- type: recall_at_5
value: 0.991
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (sqi-eng)
config: sqi-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.89999999999999
- type: f1
value: 94.69999999999999
- type: precision
value: 94.11666666666667
- type: recall
value: 95.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fry-eng)
config: fry-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 68.20809248554913
- type: f1
value: 63.431048720066066
- type: precision
value: 61.69143958161298
- type: recall
value: 68.20809248554913
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kur-eng)
config: kur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 71.21951219512195
- type: f1
value: 66.82926829268293
- type: precision
value: 65.1260162601626
- type: recall
value: 71.21951219512195
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tur-eng)
config: tur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.2
- type: f1
value: 96.26666666666667
- type: precision
value: 95.8
- type: recall
value: 97.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (deu-eng)
config: deu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 99.3
- type: f1
value: 99.06666666666666
- type: precision
value: 98.95
- type: recall
value: 99.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nld-eng)
config: nld-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.39999999999999
- type: f1
value: 96.63333333333333
- type: precision
value: 96.26666666666668
- type: recall
value: 97.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ron-eng)
config: ron-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96
- type: f1
value: 94.86666666666666
- type: precision
value: 94.31666666666668
- type: recall
value: 96
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ang-eng)
config: ang-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 47.01492537313433
- type: f1
value: 40.178867566927266
- type: precision
value: 38.179295828549556
- type: recall
value: 47.01492537313433
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ido-eng)
config: ido-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.5
- type: f1
value: 83.62537480063796
- type: precision
value: 82.44555555555554
- type: recall
value: 86.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (jav-eng)
config: jav-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 80.48780487804879
- type: f1
value: 75.45644599303138
- type: precision
value: 73.37398373983739
- type: recall
value: 80.48780487804879
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (isl-eng)
config: isl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.95666666666666
- type: precision
value: 91.125
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (slv-eng)
config: slv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.73754556500607
- type: f1
value: 89.65168084244632
- type: precision
value: 88.73025516403402
- type: recall
value: 91.73754556500607
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cym-eng)
config: cym-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81.04347826086956
- type: f1
value: 76.2128364389234
- type: precision
value: 74.2
- type: recall
value: 81.04347826086956
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kaz-eng)
config: kaz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 83.65217391304348
- type: f1
value: 79.4376811594203
- type: precision
value: 77.65797101449274
- type: recall
value: 83.65217391304348
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (est-eng)
config: est-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.5
- type: f1
value: 85.02690476190476
- type: precision
value: 83.96261904761904
- type: recall
value: 87.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (heb-eng)
config: heb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.3
- type: f1
value: 86.52333333333333
- type: precision
value: 85.22833333333332
- type: recall
value: 89.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gla-eng)
config: gla-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 65.01809408926418
- type: f1
value: 59.00594446432805
- type: precision
value: 56.827215807915444
- type: recall
value: 65.01809408926418
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mar-eng)
config: mar-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.2
- type: f1
value: 88.58
- type: precision
value: 87.33333333333334
- type: recall
value: 91.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lat-eng)
config: lat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 59.199999999999996
- type: f1
value: 53.299166276284915
- type: precision
value: 51.3383908045977
- type: recall
value: 59.199999999999996
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bel-eng)
config: bel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.2
- type: f1
value: 91.2
- type: precision
value: 90.25
- type: recall
value: 93.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pms-eng)
config: pms-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 64.76190476190476
- type: f1
value: 59.867110667110666
- type: precision
value: 58.07390192653351
- type: recall
value: 64.76190476190476
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gle-eng)
config: gle-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.2
- type: f1
value: 71.48147546897547
- type: precision
value: 69.65409090909091
- type: recall
value: 76.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pes-eng)
config: pes-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.8
- type: f1
value: 92.14
- type: precision
value: 91.35833333333333
- type: recall
value: 93.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nob-eng)
config: nob-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.89999999999999
- type: f1
value: 97.2
- type: precision
value: 96.85000000000001
- type: recall
value: 97.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bul-eng)
config: bul-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 92.93333333333334
- type: precision
value: 92.13333333333333
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cbk-eng)
config: cbk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 74.1
- type: f1
value: 69.14817460317461
- type: precision
value: 67.2515873015873
- type: recall
value: 74.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hun-eng)
config: hun-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.19999999999999
- type: f1
value: 94.01333333333335
- type: precision
value: 93.46666666666667
- type: recall
value: 95.19999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (uig-eng)
config: uig-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.9
- type: f1
value: 72.07523809523809
- type: precision
value: 70.19777777777779
- type: recall
value: 76.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (rus-eng)
config: rus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.1
- type: f1
value: 92.31666666666666
- type: precision
value: 91.43333333333332
- type: recall
value: 94.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (spa-eng)
config: spa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.8
- type: f1
value: 97.1
- type: precision
value: 96.76666666666668
- type: recall
value: 97.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hye-eng)
config: hye-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.85714285714286
- type: f1
value: 90.92093441150045
- type: precision
value: 90.00449236298293
- type: recall
value: 92.85714285714286
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tel-eng)
config: tel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.16239316239316
- type: f1
value: 91.33903133903132
- type: precision
value: 90.56267806267806
- type: recall
value: 93.16239316239316
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (afr-eng)
config: afr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.4
- type: f1
value: 90.25666666666666
- type: precision
value: 89.25833333333334
- type: recall
value: 92.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mon-eng)
config: mon-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.22727272727272
- type: f1
value: 87.53030303030303
- type: precision
value: 86.37121212121211
- type: recall
value: 90.22727272727272
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (arz-eng)
config: arz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 79.03563941299791
- type: f1
value: 74.7349505840072
- type: precision
value: 72.9035639412998
- type: recall
value: 79.03563941299791
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hrv-eng)
config: hrv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97
- type: f1
value: 96.15
- type: precision
value: 95.76666666666668
- type: recall
value: 97
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nov-eng)
config: nov-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.26459143968872
- type: f1
value: 71.55642023346303
- type: precision
value: 69.7544932369835
- type: recall
value: 76.26459143968872
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gsw-eng)
config: gsw-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 58.119658119658126
- type: f1
value: 51.65242165242165
- type: precision
value: 49.41768108434775
- type: recall
value: 58.119658119658126
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nds-eng)
config: nds-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 74.3
- type: f1
value: 69.52055555555555
- type: precision
value: 67.7574938949939
- type: recall
value: 74.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ukr-eng)
config: ukr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.8
- type: f1
value: 93.31666666666666
- type: precision
value: 92.60000000000001
- type: recall
value: 94.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (uzb-eng)
config: uzb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.63551401869158
- type: f1
value: 72.35202492211837
- type: precision
value: 70.60358255451713
- type: recall
value: 76.63551401869158
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lit-eng)
config: lit-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.4
- type: f1
value: 88.4811111111111
- type: precision
value: 87.7452380952381
- type: recall
value: 90.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ina-eng)
config: ina-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95
- type: f1
value: 93.60666666666667
- type: precision
value: 92.975
- type: recall
value: 95
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lfn-eng)
config: lfn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 67.2
- type: f1
value: 63.01595782872099
- type: precision
value: 61.596587301587306
- type: recall
value: 67.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (zsm-eng)
config: zsm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.7
- type: f1
value: 94.52999999999999
- type: precision
value: 94
- type: recall
value: 95.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ita-eng)
config: ita-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 93.28999999999999
- type: precision
value: 92.675
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cmn-eng)
config: cmn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.28333333333333
- type: precision
value: 94.75
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lvs-eng)
config: lvs-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.9
- type: f1
value: 89.83
- type: precision
value: 88.92
- type: recall
value: 91.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (glg-eng)
config: glg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.69999999999999
- type: f1
value: 93.34222222222223
- type: precision
value: 92.75416666666668
- type: recall
value: 94.69999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ceb-eng)
config: ceb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 60.333333333333336
- type: f1
value: 55.31203703703703
- type: precision
value: 53.39971108326371
- type: recall
value: 60.333333333333336
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bre-eng)
config: bre-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 12.9
- type: f1
value: 11.099861903031458
- type: precision
value: 10.589187932631877
- type: recall
value: 12.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ben-eng)
config: ben-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.7
- type: f1
value: 83.0152380952381
- type: precision
value: 81.37833333333333
- type: recall
value: 86.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swg-eng)
config: swg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 63.39285714285714
- type: f1
value: 56.832482993197274
- type: precision
value: 54.56845238095237
- type: recall
value: 63.39285714285714
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (arq-eng)
config: arq-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 48.73765093304062
- type: f1
value: 41.555736920720456
- type: precision
value: 39.06874531737319
- type: recall
value: 48.73765093304062
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kab-eng)
config: kab-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 41.099999999999994
- type: f1
value: 36.540165945165946
- type: precision
value: 35.05175685425686
- type: recall
value: 41.099999999999994
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fra-eng)
config: fra-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.89999999999999
- type: f1
value: 93.42333333333333
- type: precision
value: 92.75833333333333
- type: recall
value: 94.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (por-eng)
config: por-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.89999999999999
- type: f1
value: 93.63333333333334
- type: precision
value: 93.01666666666665
- type: recall
value: 94.89999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tat-eng)
config: tat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.9
- type: f1
value: 73.64833333333334
- type: precision
value: 71.90282106782105
- type: recall
value: 77.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (oci-eng)
config: oci-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 59.4
- type: f1
value: 54.90521367521367
- type: precision
value: 53.432840025471606
- type: recall
value: 59.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pol-eng)
config: pol-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.39999999999999
- type: f1
value: 96.6
- type: precision
value: 96.2
- type: recall
value: 97.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (war-eng)
config: war-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 67.2
- type: f1
value: 62.25926129426129
- type: precision
value: 60.408376623376626
- type: recall
value: 67.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (aze-eng)
config: aze-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.2
- type: f1
value: 87.60666666666667
- type: precision
value: 86.45277777777778
- type: recall
value: 90.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (vie-eng)
config: vie-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.7
- type: f1
value: 97
- type: precision
value: 96.65
- type: recall
value: 97.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nno-eng)
config: nno-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.2
- type: f1
value: 91.39746031746031
- type: precision
value: 90.6125
- type: recall
value: 93.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cha-eng)
config: cha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 32.11678832116788
- type: f1
value: 27.210415386260234
- type: precision
value: 26.20408990846947
- type: recall
value: 32.11678832116788
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mhr-eng)
config: mhr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.5
- type: f1
value: 6.787319277832475
- type: precision
value: 6.3452094433344435
- type: recall
value: 8.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dan-eng)
config: dan-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.1
- type: f1
value: 95.08
- type: precision
value: 94.61666666666667
- type: recall
value: 96.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ell-eng)
config: ell-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.3
- type: f1
value: 93.88333333333333
- type: precision
value: 93.18333333333332
- type: recall
value: 95.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (amh-eng)
config: amh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.11904761904762
- type: f1
value: 80.69444444444444
- type: precision
value: 78.72023809523809
- type: recall
value: 85.11904761904762
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pam-eng)
config: pam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 11.1
- type: f1
value: 9.276381801735853
- type: precision
value: 8.798174603174601
- type: recall
value: 11.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hsb-eng)
config: hsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 63.56107660455487
- type: f1
value: 58.70433569191332
- type: precision
value: 56.896926581464015
- type: recall
value: 63.56107660455487
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (srp-eng)
config: srp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.69999999999999
- type: f1
value: 93.10000000000001
- type: precision
value: 92.35
- type: recall
value: 94.69999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (epo-eng)
config: epo-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.8
- type: f1
value: 96.01222222222222
- type: precision
value: 95.67083333333332
- type: recall
value: 96.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kzj-eng)
config: kzj-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 9.2
- type: f1
value: 7.911555250305249
- type: precision
value: 7.631246556216846
- type: recall
value: 9.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (awa-eng)
config: awa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.48917748917748
- type: f1
value: 72.27375798804371
- type: precision
value: 70.14430014430013
- type: recall
value: 77.48917748917748
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fao-eng)
config: fao-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.09923664122137
- type: f1
value: 72.61541257724463
- type: precision
value: 70.8998380754106
- type: recall
value: 77.09923664122137
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mal-eng)
config: mal-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 98.2532751091703
- type: f1
value: 97.69529354682193
- type: precision
value: 97.42843279961184
- type: recall
value: 98.2532751091703
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ile-eng)
config: ile-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 82.8
- type: f1
value: 79.14672619047619
- type: precision
value: 77.59489247311828
- type: recall
value: 82.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bos-eng)
config: bos-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.35028248587571
- type: f1
value: 92.86252354048965
- type: precision
value: 92.2080979284369
- type: recall
value: 94.35028248587571
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cor-eng)
config: cor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.5
- type: f1
value: 6.282429263935621
- type: precision
value: 5.783274240739785
- type: recall
value: 8.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cat-eng)
config: cat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.7
- type: f1
value: 91.025
- type: precision
value: 90.30428571428571
- type: recall
value: 92.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (eus-eng)
config: eus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81
- type: f1
value: 77.8232380952381
- type: precision
value: 76.60194444444444
- type: recall
value: 81
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (yue-eng)
config: yue-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91
- type: f1
value: 88.70857142857142
- type: precision
value: 87.7
- type: recall
value: 91
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swe-eng)
config: swe-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.3
- type: precision
value: 94.76666666666667
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dtp-eng)
config: dtp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.1
- type: f1
value: 7.001008218834307
- type: precision
value: 6.708329562594269
- type: recall
value: 8.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kat-eng)
config: kat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.1313672922252
- type: f1
value: 84.09070598748882
- type: precision
value: 82.79171454104429
- type: recall
value: 87.1313672922252
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (jpn-eng)
config: jpn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.28333333333333
- type: precision
value: 94.73333333333332
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (csb-eng)
config: csb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 42.29249011857708
- type: f1
value: 36.981018542283365
- type: precision
value: 35.415877813576024
- type: recall
value: 42.29249011857708
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (xho-eng)
config: xho-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 83.80281690140845
- type: f1
value: 80.86854460093896
- type: precision
value: 79.60093896713614
- type: recall
value: 83.80281690140845
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (orv-eng)
config: orv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 45.26946107784431
- type: f1
value: 39.80235464678088
- type: precision
value: 38.14342660001342
- type: recall
value: 45.26946107784431
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ind-eng)
config: ind-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.3
- type: f1
value: 92.9
- type: precision
value: 92.26666666666668
- type: recall
value: 94.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tuk-eng)
config: tuk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 37.93103448275862
- type: f1
value: 33.15192743764172
- type: precision
value: 31.57456528146183
- type: recall
value: 37.93103448275862
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (max-eng)
config: max-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 69.01408450704226
- type: f1
value: 63.41549295774648
- type: precision
value: 61.342778895595806
- type: recall
value: 69.01408450704226
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swh-eng)
config: swh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 76.66666666666667
- type: f1
value: 71.60705960705961
- type: precision
value: 69.60683760683762
- type: recall
value: 76.66666666666667
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hin-eng)
config: hin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.8
- type: f1
value: 94.48333333333333
- type: precision
value: 93.83333333333333
- type: recall
value: 95.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dsb-eng)
config: dsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 52.81837160751566
- type: f1
value: 48.435977731384824
- type: precision
value: 47.11291973845539
- type: recall
value: 52.81837160751566
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ber-eng)
config: ber-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 44.9
- type: f1
value: 38.88962621607783
- type: precision
value: 36.95936507936508
- type: recall
value: 44.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tam-eng)
config: tam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.55374592833876
- type: f1
value: 88.22553125484721
- type: precision
value: 87.26927252985884
- type: recall
value: 90.55374592833876
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (slk-eng)
config: slk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 93.13333333333333
- type: precision
value: 92.45333333333333
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tgl-eng)
config: tgl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.99666666666667
- type: precision
value: 91.26666666666668
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ast-eng)
config: ast-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.03937007874016
- type: f1
value: 81.75853018372703
- type: precision
value: 80.34120734908137
- type: recall
value: 85.03937007874016
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mkd-eng)
config: mkd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.3
- type: f1
value: 85.5
- type: precision
value: 84.25833333333334
- type: recall
value: 88.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (khm-eng)
config: khm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 65.51246537396122
- type: f1
value: 60.02297410192148
- type: precision
value: 58.133467727289236
- type: recall
value: 65.51246537396122
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ces-eng)
config: ces-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96
- type: f1
value: 94.89
- type: precision
value: 94.39166666666667
- type: recall
value: 96
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tzl-eng)
config: tzl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 57.692307692307686
- type: f1
value: 53.162393162393165
- type: precision
value: 51.70673076923077
- type: recall
value: 57.692307692307686
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (urd-eng)
config: urd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.60000000000001
- type: f1
value: 89.21190476190475
- type: precision
value: 88.08666666666667
- type: recall
value: 91.60000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ara-eng)
config: ara-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88
- type: f1
value: 85.47
- type: precision
value: 84.43266233766234
- type: recall
value: 88
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kor-eng)
config: kor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.7
- type: f1
value: 90.64999999999999
- type: precision
value: 89.68333333333332
- type: recall
value: 92.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (yid-eng)
config: yid-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 80.30660377358491
- type: f1
value: 76.33044137466307
- type: precision
value: 74.78970125786164
- type: recall
value: 80.30660377358491
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fin-eng)
config: fin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.39999999999999
- type: f1
value: 95.44
- type: precision
value: 94.99166666666666
- type: recall
value: 96.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tha-eng)
config: tha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.53284671532847
- type: f1
value: 95.37712895377129
- type: precision
value: 94.7992700729927
- type: recall
value: 96.53284671532847
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (wuu-eng)
config: wuu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89
- type: f1
value: 86.23190476190476
- type: precision
value: 85.035
- type: recall
value: 89
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.585
- type: map_at_10
value: 9.012
- type: map_at_100
value: 14.027000000000001
- type: map_at_1000
value: 15.565000000000001
- type: map_at_3
value: 5.032
- type: map_at_5
value: 6.657
- type: mrr_at_1
value: 28.571
- type: mrr_at_10
value: 45.377
- type: mrr_at_100
value: 46.119
- type: mrr_at_1000
value: 46.127
- type: mrr_at_3
value: 41.156
- type: mrr_at_5
value: 42.585
- type: ndcg_at_1
value: 27.551
- type: ndcg_at_10
value: 23.395
- type: ndcg_at_100
value: 33.342
- type: ndcg_at_1000
value: 45.523
- type: ndcg_at_3
value: 25.158
- type: ndcg_at_5
value: 23.427
- type: precision_at_1
value: 28.571
- type: precision_at_10
value: 21.429000000000002
- type: precision_at_100
value: 6.714
- type: precision_at_1000
value: 1.473
- type: precision_at_3
value: 27.211000000000002
- type: precision_at_5
value: 24.490000000000002
- type: recall_at_1
value: 2.585
- type: recall_at_10
value: 15.418999999999999
- type: recall_at_100
value: 42.485
- type: recall_at_1000
value: 79.536
- type: recall_at_3
value: 6.239999999999999
- type: recall_at_5
value: 8.996
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 71.3234
- type: ap
value: 14.361688653847423
- type: f1
value: 54.819068624319044
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 61.97792869269949
- type: f1
value: 62.28965628513728
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 38.90540145385218
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 86.53513739047506
- type: cos_sim_ap
value: 75.27741586677557
- type: cos_sim_f1
value: 69.18792902473774
- type: cos_sim_precision
value: 67.94708725515136
- type: cos_sim_recall
value: 70.47493403693932
- type: dot_accuracy
value: 84.7052512368123
- type: dot_ap
value: 69.36075482849378
- type: dot_f1
value: 64.44688376631296
- type: dot_precision
value: 59.92288500793831
- type: dot_recall
value: 69.70976253298153
- type: euclidean_accuracy
value: 86.60666388508076
- type: euclidean_ap
value: 75.47512772621097
- type: euclidean_f1
value: 69.413872536473
- type: euclidean_precision
value: 67.39562624254472
- type: euclidean_recall
value: 71.55672823218997
- type: manhattan_accuracy
value: 86.52917684925792
- type: manhattan_ap
value: 75.34000110496703
- type: manhattan_f1
value: 69.28489190226429
- type: manhattan_precision
value: 67.24608889992551
- type: manhattan_recall
value: 71.45118733509234
- type: max_accuracy
value: 86.60666388508076
- type: max_ap
value: 75.47512772621097
- type: max_f1
value: 69.413872536473
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 89.01695967710637
- type: cos_sim_ap
value: 85.8298270742901
- type: cos_sim_f1
value: 78.46988128389272
- type: cos_sim_precision
value: 74.86017897091722
- type: cos_sim_recall
value: 82.44533415460425
- type: dot_accuracy
value: 88.19420188613343
- type: dot_ap
value: 83.82679165901324
- type: dot_f1
value: 76.55833777304208
- type: dot_precision
value: 75.6884875846501
- type: dot_recall
value: 77.44841392054204
- type: euclidean_accuracy
value: 89.03054294252338
- type: euclidean_ap
value: 85.89089555185325
- type: euclidean_f1
value: 78.62997658079624
- type: euclidean_precision
value: 74.92329149232914
- type: euclidean_recall
value: 82.72251308900523
- type: manhattan_accuracy
value: 89.0266620095471
- type: manhattan_ap
value: 85.86458997929147
- type: manhattan_f1
value: 78.50685331000291
- type: manhattan_precision
value: 74.5499861534201
- type: manhattan_recall
value: 82.90729904527257
- type: max_accuracy
value: 89.03054294252338
- type: max_ap
value: 85.89089555185325
- type: max_f1
value: 78.62997658079624
language:
- multilingual
- af
- am
- ar
- as
- az
- be
- bg
- bn
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- om
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- th
- tl
- tr
- ug
- uk
- ur
- uz
- vi
- xh
- yi
- zh
license: mit
---
## Multilingual-E5-large
[Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf).
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
This model has 24 layers and the embedding size is 1024.
## Usage
Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
```python
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
# Each input text should start with "query: " or "passage: ", even for non-English texts.
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
'query: 南瓜的家常做法',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右,放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"]
tokenizer = AutoTokenizer.from_pretrained('intfloat/multilingual-e5-large')
model = AutoModel.from_pretrained('intfloat/multilingual-e5-large')
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
```
## Supported Languages
This model is initialized from [xlm-roberta-large](https://huggingface.co/xlm-roberta-large)
and continually trained on a mixture of multilingual datasets.
It supports 100 languages from xlm-roberta,
but low-resource languages may see performance degradation.
## Training Details
**Initialization**: [xlm-roberta-large](https://huggingface.co/xlm-roberta-large)
**First stage**: contrastive pre-training with weak supervision
| Dataset | Weak supervision | # of text pairs |
|--------------------------------------------------------------------------------------------------------|---------------------------------------|-----------------|
| Filtered [mC4](https://huggingface.co/datasets/mc4) | (title, page content) | 1B |
| [CC News](https://huggingface.co/datasets/intfloat/multilingual_cc_news) | (title, news content) | 400M |
| [NLLB](https://huggingface.co/datasets/allenai/nllb) | translation pairs | 2.4B |
| [Wikipedia](https://huggingface.co/datasets/intfloat/wikipedia) | (hierarchical section title, passage) | 150M |
| Filtered [Reddit](https://www.reddit.com/) | (comment, response) | 800M |
| [S2ORC](https://github.com/allenai/s2orc) | (title, abstract) and citation pairs | 100M |
| [Stackexchange](https://stackexchange.com/) | (question, answer) | 50M |
| [xP3](https://huggingface.co/datasets/bigscience/xP3) | (input prompt, response) | 80M |
| [Miscellaneous unsupervised SBERT data](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | - | 10M |
**Second stage**: supervised fine-tuning
| Dataset | Language | # of text pairs |
|----------------------------------------------------------------------------------------|--------------|-----------------|
| [MS MARCO](https://microsoft.github.io/msmarco/) | English | 500k |
| [NQ](https://github.com/facebookresearch/DPR) | English | 70k |
| [Trivia QA](https://github.com/facebookresearch/DPR) | English | 60k |
| [NLI from SimCSE](https://github.com/princeton-nlp/SimCSE) | English | <300k |
| [ELI5](https://huggingface.co/datasets/eli5) | English | 500k |
| [DuReader Retrieval](https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval) | Chinese | 86k |
| [KILT Fever](https://huggingface.co/datasets/kilt_tasks) | English | 70k |
| [KILT HotpotQA](https://huggingface.co/datasets/kilt_tasks) | English | 70k |
| [SQuAD](https://huggingface.co/datasets/squad) | English | 87k |
| [Quora](https://huggingface.co/datasets/quora) | English | 150k |
| [Mr. TyDi](https://huggingface.co/datasets/castorini/mr-tydi) | 11 languages | 50k |
| [MIRACL](https://huggingface.co/datasets/miracl/miracl) | 16 languages | 40k |
For all labeled datasets, we only use its training set for fine-tuning.
For other training details, please refer to our paper at [https://arxiv.org/pdf/2212.03533.pdf](https://arxiv.org/pdf/2212.03533.pdf).
## Benchmark Results on [Mr. TyDi](https://arxiv.org/abs/2108.08787)
| Model | Avg MRR@10 | | ar | bn | en | fi | id | ja | ko | ru | sw | te | th |
|-----------------------|------------|-------|------| --- | --- | --- | --- | --- | --- | --- |------| --- | --- |
| BM25 | 33.3 | | 36.7 | 41.3 | 15.1 | 28.8 | 38.2 | 21.7 | 28.1 | 32.9 | 39.6 | 42.4 | 41.7 |
| mDPR | 16.7 | | 26.0 | 25.8 | 16.2 | 11.3 | 14.6 | 18.1 | 21.9 | 18.5 | 7.3 | 10.6 | 13.5 |
| BM25 + mDPR | 41.7 | | 49.1 | 53.5 | 28.4 | 36.5 | 45.5 | 35.5 | 36.2 | 42.7 | 40.5 | 42.0 | 49.2 |
| | |
| multilingual-e5-small | 64.4 | | 71.5 | 66.3 | 54.5 | 57.7 | 63.2 | 55.4 | 54.3 | 60.8 | 65.4 | 89.1 | 70.1 |
| multilingual-e5-base | 65.9 | | 72.3 | 65.0 | 58.5 | 60.8 | 64.9 | 56.6 | 55.8 | 62.7 | 69.0 | 86.6 | 72.7 |
| multilingual-e5-large | **70.5** | | 77.5 | 73.2 | 60.8 | 66.8 | 68.5 | 62.5 | 61.6 | 65.8 | 72.7 | 90.2 | 76.2 |
## MTEB Benchmark Evaluation
Check out [unilm/e5](https://github.com/microsoft/unilm/tree/master/e5) to reproduce evaluation results
on the [BEIR](https://arxiv.org/abs/2104.08663) and [MTEB benchmark](https://arxiv.org/abs/2210.07316).
## Support for Sentence Transformers
Below is an example for usage with sentence_transformers.
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/multilingual-e5-large')
input_texts = [
'query: how much protein should a female eat',
'query: 南瓜的家常做法',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 i s 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or traini ng for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮 ,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右, 放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油 锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"
]
embeddings = model.encode(input_texts, normalize_embeddings=True)
```
Package requirements
`pip install sentence_transformers~=2.2.2`
Contributors: [michaelfeil](https://huggingface.co/michaelfeil)
## FAQ
**1. Do I need to add the prefix "query: " and "passage: " to input texts?**
Yes, this is how the model is trained, otherwise you will see a performance degradation.
Here are some rules of thumb:
- Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval.
- Use "query: " prefix for symmetric tasks such as semantic similarity, bitext mining, paraphrase retrieval.
- Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering.
**2. Why are my reproduced results slightly different from reported in the model card?**
Different versions of `transformers` and `pytorch` could cause negligible but non-zero performance differences.
**3. Why does the cosine similarity scores distribute around 0.7 to 1.0?**
This is a known and expected behavior as we use a low temperature 0.01 for InfoNCE contrastive loss.
For text embedding tasks like text retrieval or semantic similarity,
what matters is the relative order of the scores instead of the absolute values,
so this should not be an issue.
## Citation
If you find our paper or models helpful, please consider cite as follows:
```
@article{wang2022text,
title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
journal={arXiv preprint arXiv:2212.03533},
year={2022}
}
```
## Limitations
Long texts will be truncated to at most 512 tokens.
|
alantaquito6/practicaNLP
|
alantaquito6
| 2023-09-23T02:14:29Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-23T02:10:05Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: practicaNLP
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8235294117647058
- name: F1
type: f1
value: 0.8620689655172414
---
<!-- 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. -->
# practicaNLP
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5822
- Accuracy: 0.8235
- F1: 0.8621
## 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
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.5415 | 1.09 | 500 | 0.5463 | 0.8137 | 0.8681 |
| 0.3854 | 2.18 | 1000 | 0.5822 | 0.8235 | 0.8621 |
### Framework versions
- Transformers 4.28.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Juniplayground/Mist_LLaMA-2-7B-1024_V13_COT_Meta
|
Juniplayground
| 2023-09-23T02:13:01Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-23T02:13:00Z |
---
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 0.5.0
|
Juniplayground/Mist_LLaMA-2-7B-1024_V12-COT_Alapaca
|
Juniplayground
| 2023-09-23T02:08:35Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-23T02:08:33Z |
---
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 0.5.0
|
CyberHarem/cure_butterfly_hirogaruskyprecure
|
CyberHarem
| 2023-09-23T02:02:53Z | 0 | 1 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/cure_butterfly_hirogaruskyprecure",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-04T14:10:46Z |
---
license: mit
datasets:
- CyberHarem/cure_butterfly_hirogaruskyprecure
pipeline_tag: text-to-image
tags:
- art
---
# Lora of cure_butterfly_hirogaruskyprecure
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 5720, you need to download `5720/cure_butterfly_hirogaruskyprecure.pt` as the embedding and `5720/cure_butterfly_hirogaruskyprecure.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 5720**, with the score of 0.982. The trigger words are:
1. `cure_butterfly_hirogaruskyprecure`
2. `blonde_hair, long_hair, purple_eyes, jewelry, earrings, magical_girl, smile, open_mouth`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 6600 | 0.948 | [Download](6600/cure_butterfly_hirogaruskyprecure.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) |  |  |
| 6160 | 0.969 | [Download](6160/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6160/previews/nude.png) | [<NSFW, click to see>](6160/previews/nude2.png) |  |  |
| **5720** | **0.982** | [**Download**](5720/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5720/previews/nude.png) | [<NSFW, click to see>](5720/previews/nude2.png) |  |  |
| 5280 | 0.973 | [Download](5280/cure_butterfly_hirogaruskyprecure.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) |  |  |
| 4840 | 0.951 | [Download](4840/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4840/previews/nude.png) | [<NSFW, click to see>](4840/previews/nude2.png) |  |  |
| 4400 | 0.947 | [Download](4400/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4400/previews/nude.png) | [<NSFW, click to see>](4400/previews/nude2.png) |  |  |
| 3960 | 0.965 | [Download](3960/cure_butterfly_hirogaruskyprecure.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) |  |  |
| 3520 | 0.928 | [Download](3520/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3520/previews/nude.png) | [<NSFW, click to see>](3520/previews/nude2.png) |  |  |
| 3080 | 0.956 | [Download](3080/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3080/previews/nude.png) | [<NSFW, click to see>](3080/previews/nude2.png) |  |  |
| 2640 | 0.932 | [Download](2640/cure_butterfly_hirogaruskyprecure.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) |  |  |
| 2200 | 0.838 | [Download](2200/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2200/previews/nude.png) | [<NSFW, click to see>](2200/previews/nude2.png) |  |  |
| 1760 | 0.829 | [Download](1760/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1760/previews/nude.png) | [<NSFW, click to see>](1760/previews/nude2.png) |  |  |
| 1320 | 0.792 | [Download](1320/cure_butterfly_hirogaruskyprecure.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) |  |  |
| 880 | 0.769 | [Download](880/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](880/previews/nude.png) | [<NSFW, click to see>](880/previews/nude2.png) |  |  |
| 440 | 0.601 | [Download](440/cure_butterfly_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](440/previews/nude.png) | [<NSFW, click to see>](440/previews/nude2.png) |  |  |
|
CyberHarem/cure_prism_hirogaruskyprecure
|
CyberHarem
| 2023-09-23T01:56:55Z | 0 | 1 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/cure_prism_hirogaruskyprecure",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-04T13:19:56Z |
---
license: mit
datasets:
- CyberHarem/cure_prism_hirogaruskyprecure
pipeline_tag: text-to-image
tags:
- art
---
# Lora of cure_prism_hirogaruskyprecure
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 6440, you need to download `6440/cure_prism_hirogaruskyprecure.pt` as the embedding and `6440/cure_prism_hirogaruskyprecure.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 6440**, with the score of 0.838. The trigger words are:
1. `cure_prism_hirogaruskyprecure`
2. `long_hair, green_eyes, pink_hair, bow, open_mouth, bangs, smile, white_bow`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 6900 | 0.804 | [Download](6900/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6900/previews/nude.png) | [<NSFW, click to see>](6900/previews/nude2.png) |  |  |
| **6440** | **0.838** | [**Download**](6440/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6440/previews/nude.png) | [<NSFW, click to see>](6440/previews/nude2.png) |  |  |
| 5980 | 0.806 | [Download](5980/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5980/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5980/previews/nude.png) | [<NSFW, click to see>](5980/previews/nude2.png) |  |  |
| 5520 | 0.789 | [Download](5520/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5520/previews/nude.png) | [<NSFW, click to see>](5520/previews/nude2.png) |  |  |
| 5060 | 0.835 | [Download](5060/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5060/previews/nude.png) | [<NSFW, click to see>](5060/previews/nude2.png) |  |  |
| 4600 | 0.820 | [Download](4600/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4600/previews/nude.png) | [<NSFW, click to see>](4600/previews/nude2.png) |  |  |
| 4140 | 0.813 | [Download](4140/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4140/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4140/previews/nude.png) | [<NSFW, click to see>](4140/previews/nude2.png) |  |  |
| 3680 | 0.776 | [Download](3680/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3680/previews/nude.png) | [<NSFW, click to see>](3680/previews/nude2.png) |  |  |
| 3220 | 0.689 | [Download](3220/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3220/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3220/previews/nude.png) | [<NSFW, click to see>](3220/previews/nude2.png) |  |  |
| 2760 | 0.719 | [Download](2760/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2760/previews/nude.png) | [<NSFW, click to see>](2760/previews/nude2.png) |  |  |
| 2300 | 0.745 | [Download](2300/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2300/previews/nude.png) | [<NSFW, click to see>](2300/previews/nude2.png) |  |  |
| 1840 | 0.745 | [Download](1840/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1840/previews/nude.png) | [<NSFW, click to see>](1840/previews/nude2.png) |  |  |
| 1380 | 0.751 | [Download](1380/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1380/previews/nude.png) | [<NSFW, click to see>](1380/previews/nude2.png) |  |  |
| 920 | 0.679 | [Download](920/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](920/previews/nude.png) | [<NSFW, click to see>](920/previews/nude2.png) |  |  |
| 460 | 0.735 | [Download](460/cure_prism_hirogaruskyprecure.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](460/previews/bondage.png) |  |  |  | [<NSFW, click to see>](460/previews/nude.png) | [<NSFW, click to see>](460/previews/nude2.png) |  |  |
|
CyberHarem/shinohara_rei_idolmastercinderellagirls
|
CyberHarem
| 2023-09-23T01:43:05Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/shinohara_rei_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-23T01:32:58Z |
---
license: mit
datasets:
- CyberHarem/shinohara_rei_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of shinohara_rei_idolmastercinderellagirls
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 4080, you need to download `4080/shinohara_rei_idolmastercinderellagirls.pt` as the embedding and `4080/shinohara_rei_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4080**, with the score of 1.000. The trigger words are:
1. `shinohara_rei_idolmastercinderellagirls`
2. `brown_hair, green_eyes, short_hair, jewelry, earrings, breasts, cleavage, large_breasts, necklace, smile, 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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.999 | [Download](5100/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.999 | [Download](4760/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.999 | [Download](4420/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| **4080** | **1.000** | [**Download**](4080/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.991 | [Download](3740/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.971 | [Download](3400/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.983 | [Download](3060/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.980 | [Download](2720/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.952 | [Download](2380/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.880 | [Download](2040/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.951 | [Download](1700/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.912 | [Download](1360/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.955 | [Download](1020/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.916 | [Download](680/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.658 | [Download](340/shinohara_rei_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
CyberHarem/chihaya_anon_bangdreamitsmygo
|
CyberHarem
| 2023-09-23T01:40:16Z | 0 | 1 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/chihaya_anon_bangdreamitsmygo",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-02T19:39:44Z |
---
license: mit
datasets:
- CyberHarem/chihaya_anon_bangdreamitsmygo
pipeline_tag: text-to-image
tags:
- art
---
# Lora of chihaya_anon_bangdreamitsmygo
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 7200, you need to download `7200/chihaya_anon_bangdreamitsmygo.pt` as the embedding and `7200/chihaya_anon_bangdreamitsmygo.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7200**, with the score of 0.977. The trigger words are:
1. `chihaya_anon_bangdreamitsmygo`
2. `long_hair, pink_hair, bangs, blush, necktie, grey_eyes, blazer, open_mouth, upper_body, indoors`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **7200** | **0.977** | [**Download**](7200/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6720 | 0.973 | [Download](6720/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6240 | 0.976 | [Download](6240/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5760 | 0.974 | [Download](5760/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5280 | 0.928 | [Download](5280/chihaya_anon_bangdreamitsmygo.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) |  |  |
| 4800 | 0.975 | [Download](4800/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4320 | 0.927 | [Download](4320/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| 3840 | 0.973 | [Download](3840/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| 3360 | 0.975 | [Download](3360/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2880 | 0.879 | [Download](2880/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2400 | 0.972 | [Download](2400/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1920 | 0.968 | [Download](1920/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1440 | 0.966 | [Download](1440/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 960 | 0.963 | [Download](960/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](960/previews/nude.png) | [<NSFW, click to see>](960/previews/nude2.png) |  |  |
| 480 | 0.944 | [Download](480/chihaya_anon_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](480/previews/nude.png) | [<NSFW, click to see>](480/previews/nude2.png) |  |  |
|
OpenDILabCommunity/Walker2d-v3-SAC
|
OpenDILabCommunity
| 2023-09-23T01:32:43Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"Walker2d-v3",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-04-18T15:41:43Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- Walker2d-v3
benchmark_name: OpenAI/Gym/MuJoCo
task_name: Walker2d-v3
pipeline_tag: reinforcement-learning
model-index:
- name: SAC
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/MuJoCo-Walker2d-v3
type: OpenAI/Gym/MuJoCo-Walker2d-v3
metrics:
- type: mean_reward
value: 5296.43 +/- 19.68
name: mean_reward
---
# Play **Walker2d-v3** with **SAC** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **SAC** implementation to OpenAI/Gym/MuJoCo **Walker2d-v3** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
sudo apt update -y && sudo apt install -y build-essential libgl1-mesa-dev libgl1-mesa-glx libglew-dev libosmesa6-dev libglfw3 libglfw3-dev libsdl2-dev libsdl2-image-dev libglm-dev libfreetype6-dev patchelf
mkdir -p ~/.mujoco
wget https://mujoco.org/download/mujoco210-linux-x86_64.tar.gz -O mujoco.tar.gz
tar -xf mujoco.tar.gz -C ~/.mujoco
echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin" >> ~/.bashrc
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin
pip3 install "cython<3"
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import SACAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
# Instantiate the agent
agent = SACAgent(env_id="Walker2d-v3", exp_name="Walker2d-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import SACAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/Walker2d-v3-SAC")
# Instantiate the agent
agent = SACAgent(env_id="Walker2d-v3", exp_name="Walker2d-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import SACAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = SACAgent(env_id="Walker2d-v3", exp_name="Walker2d-v3-SAC")
# Train the agent
return_ = agent.train(step=int(5000000))
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/MuJoCo",
task_name="Walker2d-v3",
algo_name="SAC",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/sac.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/mujoco.html",
installation_guide='''
sudo apt update -y \
&& sudo apt install -y \
build-essential \
libgl1-mesa-dev \
libgl1-mesa-glx \
libglew-dev \
libosmesa6-dev \
libglfw3 \
libglfw3-dev \
libsdl2-dev \
libsdl2-image-dev \
libglm-dev \
libfreetype6-dev \
patchelf
mkdir -p ~/.mujoco
wget https://mujoco.org/download/mujoco210-linux-x86_64.tar.gz -O mujoco.tar.gz
tar -xf mujoco.tar.gz -C ~/.mujoco
echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin" >> ~/.bashrc
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin
pip3 install "cython<3"
pip3 install DI-engine[common_env]
''',
usage_file_by_git_clone="./sac/walker2d_sac_deploy.py",
usage_file_by_huggingface_ding="./sac/walker2d_sac_download.py",
train_file="./sac/walker2d_sac.py",
repo_id="OpenDILabCommunity/Walker2d-v3-SAC",
create_repo=False
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 6000,
'n_evaluator_episode': 8,
'env_id': 'Walker2d-v3',
'collector_env_num': 1,
'evaluator_env_num': 8,
'env_wrapper': 'mujoco_default'
},
'policy': {
'model': {
'twin_critic': True,
'action_space': 'reparameterization',
'obs_shape': 17,
'action_shape': 6,
'actor_head_hidden_size': 256,
'critic_head_hidden_size': 256
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 1,
'batch_size': 256,
'learning_rate_q': 0.001,
'learning_rate_policy': 0.001,
'learning_rate_alpha': 0.0003,
'target_theta': 0.005,
'discount_factor': 0.99,
'alpha': 0.2,
'auto_alpha': False,
'log_space': True,
'target_entropy': None,
'ignore_done': False,
'init_w': 0.003,
'reparameterization': True
},
'collect': {
'collector': {},
'n_sample': 1,
'unroll_len': 1,
'collector_logit': False
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'figure_path': None,
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 6000,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 1000000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'sac',
'priority': False,
'priority_IS_weight': False,
'random_collect_size': 10000,
'transition_with_policy_data': True,
'multi_agent': False,
'cfg_type': 'SACPolicyDict',
'command': {}
},
'exp_name': 'Walker2d-v3-SAC',
'seed': 0,
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
}
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/Walker2d-v3-SAC)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/sac.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-SAC/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-SAC/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 1702.11 KB
- **Last Update Date:** 2023-09-23
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/MuJoCo
- **Task:** Walker2d-v3
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.9
- **PyTorch version:** 2.0.1+cu117
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/mujoco.html)
|
CyberHarem/togawa_sakiko_bangdreamitsmygo
|
CyberHarem
| 2023-09-23T01:14:37Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/togawa_sakiko_bangdreamitsmygo",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-02T15:31:21Z |
---
license: mit
datasets:
- CyberHarem/togawa_sakiko_bangdreamitsmygo
pipeline_tag: text-to-image
tags:
- art
---
# Lora of togawa_sakiko_bangdreamitsmygo
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 4760, you need to download `4760/togawa_sakiko_bangdreamitsmygo.pt` as the embedding and `4760/togawa_sakiko_bangdreamitsmygo.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.990. The trigger words are:
1. `togawa_sakiko_bangdreamitsmygo`
2. `long_hair, ribbon, hair_ribbon, bangs, blush, black_ribbon, yellow_eyes, grey_hair, sidelocks, portrait, closed_mouth, smile, indoors, blurry, blue_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 |
|:---------|:----------|:--------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.989 | [Download](5100/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.990** | [**Download**](4760/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.984 | [Download](4420/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.989 | [Download](4080/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.986 | [Download](3740/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.933 | [Download](3400/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.979 | [Download](3060/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.978 | [Download](2720/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.964 | [Download](2380/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.981 | [Download](2040/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.982 | [Download](1700/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.975 | [Download](1360/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.958 | [Download](1020/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.961 | [Download](680/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.959 | [Download](340/togawa_sakiko_bangdreamitsmygo.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
UrbanJoe/llama2-qlora-finetunined-french
|
UrbanJoe
| 2023-09-23T00:39:37Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-23T00:39:32Z |
---
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
|
CyberHarem/shina_kuroko_ahogirl
|
CyberHarem
| 2023-09-23T00:18:04Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/shina_kuroko_ahogirl",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-31T09:35:22Z |
---
license: mit
datasets:
- CyberHarem/shina_kuroko_ahogirl
pipeline_tag: text-to-image
tags:
- art
---
# Lora of shina_kuroko_ahogirl
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 2600, you need to download `2600/shina_kuroko_ahogirl.pt` as the embedding and `2600/shina_kuroko_ahogirl.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 2600**, with the score of 0.991. The trigger words are:
1. `shina_kuroko_ahogirl`
2. `long_hair, black_hair, brown_eyes, sweatdrop`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 3000 | 0.983 | [Download](3000/shina_kuroko_ahogirl.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) |  |  |
| 2800 | 0.979 | [Download](2800/shina_kuroko_ahogirl.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) |  |  |
| **2600** | **0.991** | [**Download**](2600/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2400 | 0.981 | [Download](2400/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 2200 | 0.986 | [Download](2200/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](2200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2200/previews/nude.png) | [<NSFW, click to see>](2200/previews/nude2.png) |  |  |
| 2000 | 0.977 | [Download](2000/shina_kuroko_ahogirl.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) |  |  |
| 1800 | 0.984 | [Download](1800/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1600 | 0.975 | [Download](1600/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](1600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1600/previews/nude.png) | [<NSFW, click to see>](1600/previews/nude2.png) |  |  |
| 1400 | 0.979 | [Download](1400/shina_kuroko_ahogirl.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) |  |  |
| 1200 | 0.984 | [Download](1200/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](1200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1200/previews/nude.png) | [<NSFW, click to see>](1200/previews/nude2.png) |  |  |
| 1000 | 0.912 | [Download](1000/shina_kuroko_ahogirl.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) |  |  |
| 800 | 0.962 | [Download](800/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](800/previews/nude.png) | [<NSFW, click to see>](800/previews/nude2.png) |  |  |
| 600 | 0.957 | [Download](600/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](600/previews/nude.png) | [<NSFW, click to see>](600/previews/nude2.png) |  |  |
| 400 | 0.367 | [Download](400/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](400/previews/nude.png) | [<NSFW, click to see>](400/previews/nude2.png) |  |  |
| 200 | 0.161 | [Download](200/shina_kuroko_ahogirl.zip) |  |  |  |  |  | [<NSFW, click to see>](200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](200/previews/nude.png) | [<NSFW, click to see>](200/previews/nude2.png) |  |  |
|
CyberHarem/hiragi_kii_ahogirl
|
CyberHarem
| 2023-09-23T00:14:10Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/hiragi_kii_ahogirl",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-31T08:58:56Z |
---
license: mit
datasets:
- CyberHarem/hiragi_kii_ahogirl
pipeline_tag: text-to-image
tags:
- art
---
# Lora of hiragi_kii_ahogirl
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 2400, you need to download `2400/hiragi_kii_ahogirl.pt` as the embedding and `2400/hiragi_kii_ahogirl.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 2400**, with the score of 0.978. The trigger words are:
1. `hiragi_kii_ahogirl`
2. `blonde_hair, short_hair, green_eyes, multiple_girls, 2girls, open_mouth, sweatdrop`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 3000 | 0.972 | [Download](3000/hiragi_kii_ahogirl.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) |  |  |
| 2800 | 0.894 | [Download](2800/hiragi_kii_ahogirl.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) |  |  |
| 2600 | 0.885 | [Download](2600/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| **2400** | **0.978** | [**Download**](2400/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 2200 | 0.975 | [Download](2200/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](2200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2200/previews/nude.png) | [<NSFW, click to see>](2200/previews/nude2.png) |  |  |
| 2000 | 0.847 | [Download](2000/hiragi_kii_ahogirl.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) |  |  |
| 1800 | 0.951 | [Download](1800/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1600 | 0.908 | [Download](1600/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](1600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1600/previews/nude.png) | [<NSFW, click to see>](1600/previews/nude2.png) |  |  |
| 1400 | 0.918 | [Download](1400/hiragi_kii_ahogirl.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) |  |  |
| 1200 | 0.889 | [Download](1200/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](1200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1200/previews/nude.png) | [<NSFW, click to see>](1200/previews/nude2.png) |  |  |
| 1000 | 0.846 | [Download](1000/hiragi_kii_ahogirl.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) |  |  |
| 800 | 0.764 | [Download](800/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](800/previews/nude.png) | [<NSFW, click to see>](800/previews/nude2.png) |  |  |
| 600 | 0.772 | [Download](600/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](600/previews/nude.png) | [<NSFW, click to see>](600/previews/nude2.png) |  |  |
| 400 | 0.744 | [Download](400/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](400/previews/nude.png) | [<NSFW, click to see>](400/previews/nude2.png) |  |  |
| 200 | 0.189 | [Download](200/hiragi_kii_ahogirl.zip) |  |  |  | [<NSFW, click to see>](200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](200/previews/nude.png) | [<NSFW, click to see>](200/previews/nude2.png) |  |  |
|
umm-maybe/Skip-NoClip-StarCoder-1B
|
umm-maybe
| 2023-09-23T00:05:44Z | 127 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt_bigcode",
"text-generation",
"license:bigcode-openrail-m",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T14:08:53Z |
---
license: bigcode-openrail-m
---
|
simlamkr1/Llama2-simgpt2test
|
simlamkr1
| 2023-09-23T00:01:15Z | 49 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mixformer-sequential",
"text-generation",
"generated_from_trainer",
"custom_code",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-07T14:47:56Z |
---
tags:
- generated_from_trainer
model-index:
- name: Llama2-simgpt2test
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Llama2-simgpt2test
This model is a fine-tuned version of [simlamkr1/llama2_finetuned_chatbot](https://huggingface.co/simlamkr1/llama2_finetuned_chatbot) 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Undi95/MXLewdMini-L2-13B-GGUF
|
Undi95
| 2023-09-22T23:56:31Z | 100 | 4 | null |
[
"gguf",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | 2023-09-22T23:30:21Z |
---
license: cc-by-nc-4.0
---
Merge:
```shell
[Xwin (0.66) + ReMM (0.33)] x [Xwin (0.33) + MLewd (0.66)]
```
The goal was to recreate https://huggingface.co/Undi95/MXLewd-L2-20B-GGUF in 13B without using merge interlacing (will probably be a little less good).
<!-- 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 -->
One part is ReMM (0.33) and Xwin (0.66)
One part is Xwin (0.33) and MLewd (0.66)
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that completes the request.
### Instruction:
{prompt}
### Response:
```
|
trieudemo11/llama_7b_attrb_cate_4m_10
|
trieudemo11
| 2023-09-22T23:49:23Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T23:49:06Z |
---
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
|
CyberHarem/otosuna_mihari_mangakasantoassistantsanto
|
CyberHarem
| 2023-09-22T23:31:10Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/otosuna_mihari_mangakasantoassistantsanto",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-30T21:25:22Z |
---
license: mit
datasets:
- CyberHarem/otosuna_mihari_mangakasantoassistantsanto
pipeline_tag: text-to-image
tags:
- art
---
# Lora of otosuna_mihari_mangakasantoassistantsanto
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 5060, you need to download `5060/otosuna_mihari_mangakasantoassistantsanto.pt` as the embedding and `5060/otosuna_mihari_mangakasantoassistantsanto.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 5060**, with the score of 0.803. The trigger words are:
1. `otosuna_mihari_mangakasantoassistantsanto`
2. `blonde_hair, short_hair, open_mouth, brown_eyes, red_eyes`
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 |
|:---------|:----------|:-------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 6900 | 0.748 | [Download](6900/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6900/previews/pattern_13.png) | [<NSFW, click to see>](6900/previews/bikini.png) | [<NSFW, click to see>](6900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6900/previews/nude.png) | [<NSFW, click to see>](6900/previews/nude2.png) |  |  |
| 6440 | 0.714 | [Download](6440/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6440/previews/pattern_13.png) | [<NSFW, click to see>](6440/previews/bikini.png) | [<NSFW, click to see>](6440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6440/previews/nude.png) | [<NSFW, click to see>](6440/previews/nude2.png) |  |  |
| 5980 | 0.718 | [Download](5980/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5980/previews/pattern_13.png) | [<NSFW, click to see>](5980/previews/bikini.png) | [<NSFW, click to see>](5980/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5980/previews/nude.png) | [<NSFW, click to see>](5980/previews/nude2.png) |  |  |
| 5520 | 0.749 | [Download](5520/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5520/previews/pattern_13.png) | [<NSFW, click to see>](5520/previews/bikini.png) | [<NSFW, click to see>](5520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5520/previews/nude.png) | [<NSFW, click to see>](5520/previews/nude2.png) |  |  |
| **5060** | **0.803** | [**Download**](5060/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5060/previews/pattern_13.png) | [<NSFW, click to see>](5060/previews/bikini.png) | [<NSFW, click to see>](5060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5060/previews/nude.png) | [<NSFW, click to see>](5060/previews/nude2.png) |  |  |
| 4600 | 0.790 | [Download](4600/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4600/previews/pattern_13.png) | [<NSFW, click to see>](4600/previews/bikini.png) | [<NSFW, click to see>](4600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4600/previews/nude.png) | [<NSFW, click to see>](4600/previews/nude2.png) |  |  |
| 4140 | 0.724 | [Download](4140/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4140/previews/pattern_13.png) | [<NSFW, click to see>](4140/previews/bikini.png) | [<NSFW, click to see>](4140/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4140/previews/nude.png) | [<NSFW, click to see>](4140/previews/nude2.png) |  |  |
| 3680 | 0.735 | [Download](3680/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3680/previews/pattern_13.png) | [<NSFW, click to see>](3680/previews/bikini.png) | [<NSFW, click to see>](3680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3680/previews/nude.png) | [<NSFW, click to see>](3680/previews/nude2.png) |  |  |
| 3220 | 0.697 | [Download](3220/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3220/previews/pattern_13.png) | [<NSFW, click to see>](3220/previews/bikini.png) | [<NSFW, click to see>](3220/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3220/previews/nude.png) | [<NSFW, click to see>](3220/previews/nude2.png) |  |  |
| 2760 | 0.673 | [Download](2760/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2760/previews/pattern_13.png) | [<NSFW, click to see>](2760/previews/bikini.png) | [<NSFW, click to see>](2760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2760/previews/nude.png) | [<NSFW, click to see>](2760/previews/nude2.png) |  |  |
| 2300 | 0.556 | [Download](2300/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2300/previews/pattern_13.png) | [<NSFW, click to see>](2300/previews/bikini.png) | [<NSFW, click to see>](2300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2300/previews/nude.png) | [<NSFW, click to see>](2300/previews/nude2.png) |  |  |
| 1840 | 0.493 | [Download](1840/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1840/previews/pattern_13.png) | [<NSFW, click to see>](1840/previews/bikini.png) | [<NSFW, click to see>](1840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1840/previews/nude.png) | [<NSFW, click to see>](1840/previews/nude2.png) |  |  |
| 1380 | 0.475 | [Download](1380/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1380/previews/pattern_13.png) | [<NSFW, click to see>](1380/previews/bikini.png) | [<NSFW, click to see>](1380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1380/previews/nude.png) | [<NSFW, click to see>](1380/previews/nude2.png) |  |  |
| 920 | 0.498 | [Download](920/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](920/previews/pattern_13.png) | [<NSFW, click to see>](920/previews/bikini.png) | [<NSFW, click to see>](920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](920/previews/nude.png) | [<NSFW, click to see>](920/previews/nude2.png) |  |  |
| 460 | 0.241 | [Download](460/otosuna_mihari_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](460/previews/pattern_13.png) | [<NSFW, click to see>](460/previews/bikini.png) | [<NSFW, click to see>](460/previews/bondage.png) |  |  |  | [<NSFW, click to see>](460/previews/nude.png) | [<NSFW, click to see>](460/previews/nude2.png) |  |  |
|
MarcosMunoz95/LunarLander-v2
|
MarcosMunoz95
| 2023-09-22T23:27:51Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T23:25:29Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -201.31 +/- 134.63
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
|
CyberHarem/ashisu_sahoto_mangakasantoassistantsanto
|
CyberHarem
| 2023-09-22T23:24:41Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/ashisu_sahoto_mangakasantoassistantsanto",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-30T20:35:17Z |
---
license: mit
datasets:
- CyberHarem/ashisu_sahoto_mangakasantoassistantsanto
pipeline_tag: text-to-image
tags:
- art
---
# Lora of ashisu_sahoto_mangakasantoassistantsanto
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 5880, you need to download `5880/ashisu_sahoto_mangakasantoassistantsanto.pt` as the embedding and `5880/ashisu_sahoto_mangakasantoassistantsanto.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 5880**, with the score of 0.853. The trigger words are:
1. `ashisu_sahoto_mangakasantoassistantsanto`
2. `long_hair, black_hair, brown_eyes`
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 |
|:---------|:----------|:------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 6300 | 0.847 | [Download](6300/ashisu_sahoto_mangakasantoassistantsanto.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) |  |  |
| **5880** | **0.853** | [**Download**](5880/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5880/previews/nude.png) | [<NSFW, click to see>](5880/previews/nude2.png) |  |  |
| 5460 | 0.809 | [Download](5460/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5460/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5460/previews/nude.png) | [<NSFW, click to see>](5460/previews/nude2.png) |  |  |
| 5040 | 0.825 | [Download](5040/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5040/previews/nude.png) | [<NSFW, click to see>](5040/previews/nude2.png) |  |  |
| 4620 | 0.847 | [Download](4620/ashisu_sahoto_mangakasantoassistantsanto.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) |  |  |
| 4200 | 0.776 | [Download](4200/ashisu_sahoto_mangakasantoassistantsanto.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) |  |  |
| 3780 | 0.834 | [Download](3780/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3780/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3780/previews/nude.png) | [<NSFW, click to see>](3780/previews/nude2.png) |  |  |
| 3360 | 0.801 | [Download](3360/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2940 | 0.819 | [Download](2940/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2940/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2940/previews/nude.png) | [<NSFW, click to see>](2940/previews/nude2.png) |  |  |
| 2520 | 0.821 | [Download](2520/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2520/previews/nude.png) | [<NSFW, click to see>](2520/previews/nude2.png) |  |  |
| 2100 | 0.791 | [Download](2100/ashisu_sahoto_mangakasantoassistantsanto.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) |  |  |
| 1680 | 0.756 | [Download](1680/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1680/previews/nude.png) | [<NSFW, click to see>](1680/previews/nude2.png) |  |  |
| 1260 | 0.758 | [Download](1260/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1260/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1260/previews/nude.png) | [<NSFW, click to see>](1260/previews/nude2.png) |  |  |
| 840 | 0.703 | [Download](840/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](840/previews/nude.png) | [<NSFW, click to see>](840/previews/nude2.png) |  |  |
| 420 | 0.647 | [Download](420/ashisu_sahoto_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](420/previews/nude.png) | [<NSFW, click to see>](420/previews/nude2.png) |  |  |
|
MarcosMunoz95/ppo-CartPole-v1
|
MarcosMunoz95
| 2023-09-22T23:16:24Z | 0 | 0 | null |
[
"tensorboard",
"CartPole-v1",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T22:59:55Z |
---
tags:
- CartPole-v1
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 18.80 +/- 6.23
name: mean_reward
verified: false
---
# PPO Agent Playing CartPole-v1
This is a trained model of a PPO agent playing CartPole-v1.
# Hyperparameters
|
CyberHarem/fuwa_rinna_mangakasantoassistantsanto
|
CyberHarem
| 2023-09-22T23:16:22Z | 0 | 1 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/fuwa_rinna_mangakasantoassistantsanto",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-30T15:52:08Z |
---
license: mit
datasets:
- CyberHarem/fuwa_rinna_mangakasantoassistantsanto
pipeline_tag: text-to-image
tags:
- art
---
# Lora of fuwa_rinna_mangakasantoassistantsanto
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 1560, you need to download `1560/fuwa_rinna_mangakasantoassistantsanto.pt` as the embedding and `1560/fuwa_rinna_mangakasantoassistantsanto.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 1560**, with the score of 0.867. The trigger words are:
1. `fuwa_rinna_mangakasantoassistantsanto`
2. `brown_hair, long_hair, open_mouth, blush, purple_eyes, smile, closed_eyes`
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 |
|:---------|:----------|:---------------------------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 3900 | 0.859 | [Download](3900/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](3900/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](3900/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](3900/previews/bikini.png) | [<NSFW, click to see>](3900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3900/previews/nude.png) | [<NSFW, click to see>](3900/previews/nude2.png) |  |  |
| 3640 | 0.859 | [Download](3640/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](3640/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](3640/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](3640/previews/bikini.png) | [<NSFW, click to see>](3640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3640/previews/nude.png) | [<NSFW, click to see>](3640/previews/nude2.png) |  |  |
| 3380 | 0.861 | [Download](3380/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](3380/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](3380/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](3380/previews/bikini.png) | [<NSFW, click to see>](3380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3380/previews/nude.png) | [<NSFW, click to see>](3380/previews/nude2.png) |  |  |
| 3120 | 0.846 | [Download](3120/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](3120/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](3120/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](3120/previews/bikini.png) | [<NSFW, click to see>](3120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3120/previews/nude.png) | [<NSFW, click to see>](3120/previews/nude2.png) |  |  |
| 2860 | 0.810 | [Download](2860/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](2860/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](2860/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](2860/previews/bikini.png) | [<NSFW, click to see>](2860/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2860/previews/nude.png) | [<NSFW, click to see>](2860/previews/nude2.png) |  |  |
| 2600 | 0.847 | [Download](2600/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](2600/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](2600/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](2600/previews/bikini.png) | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| 2340 | 0.795 | [Download](2340/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](2340/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](2340/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](2340/previews/bikini.png) | [<NSFW, click to see>](2340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2340/previews/nude.png) | [<NSFW, click to see>](2340/previews/nude2.png) |  |  |
| 2080 | 0.775 | [Download](2080/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](2080/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](2080/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](2080/previews/bikini.png) | [<NSFW, click to see>](2080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2080/previews/nude.png) | [<NSFW, click to see>](2080/previews/nude2.png) |  |  |
| 1820 | 0.835 | [Download](1820/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](1820/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](1820/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](1820/previews/bikini.png) | [<NSFW, click to see>](1820/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1820/previews/nude.png) | [<NSFW, click to see>](1820/previews/nude2.png) |  |  |
| **1560** | **0.867** | [**Download**](1560/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](1560/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](1560/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](1560/previews/bikini.png) | [<NSFW, click to see>](1560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1560/previews/nude.png) | [<NSFW, click to see>](1560/previews/nude2.png) |  |  |
| 1300 | 0.858 | [Download](1300/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](1300/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](1300/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](1300/previews/bikini.png) | [<NSFW, click to see>](1300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1300/previews/nude.png) | [<NSFW, click to see>](1300/previews/nude2.png) |  |  |
| 1040 | 0.792 | [Download](1040/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](1040/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](1040/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](1040/previews/bikini.png) | [<NSFW, click to see>](1040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1040/previews/nude.png) | [<NSFW, click to see>](1040/previews/nude2.png) |  |  |
| 780 | 0.634 | [Download](780/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](780/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](780/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](780/previews/bikini.png) | [<NSFW, click to see>](780/previews/bondage.png) |  |  |  | [<NSFW, click to see>](780/previews/nude.png) | [<NSFW, click to see>](780/previews/nude2.png) |  |  |
| 520 | 0.572 | [Download](520/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](520/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](520/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](520/previews/bikini.png) | [<NSFW, click to see>](520/previews/bondage.png) |  |  |  | [<NSFW, click to see>](520/previews/nude.png) | [<NSFW, click to see>](520/previews/nude2.png) |  |  |
| 260 | 0.147 | [Download](260/fuwa_rinna_mangakasantoassistantsanto.zip) | [<NSFW, click to see>](260/previews/pattern_1.png) |  |  |  |  | [<NSFW, click to see>](260/previews/pattern_6.png) |  |  |  | [<NSFW, click to see>](260/previews/bikini.png) | [<NSFW, click to see>](260/previews/bondage.png) |  |  |  | [<NSFW, click to see>](260/previews/nude.png) | [<NSFW, click to see>](260/previews/nude2.png) |  |  |
|
CyberHarem/ashisu_sahono_mangakasantoassistantsanto
|
CyberHarem
| 2023-09-22T23:07:44Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/ashisu_sahono_mangakasantoassistantsanto",
"license:mit",
"region:us"
] |
text-to-image
| 2023-08-30T14:54:12Z |
---
license: mit
datasets:
- CyberHarem/ashisu_sahono_mangakasantoassistantsanto
pipeline_tag: text-to-image
tags:
- art
---
# Lora of ashisu_sahono_mangakasantoassistantsanto
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 2400, you need to download `2400/ashisu_sahono_mangakasantoassistantsanto.pt` as the embedding and `2400/ashisu_sahono_mangakasantoassistantsanto.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 2400**, with the score of 0.736. The trigger words are:
1. `ashisu_sahono_mangakasantoassistantsanto`
2. `black_hair, short_hair, brown_eyes, open_mouth, hair_bobbles, hair_ornament, side_ponytail, smile`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 3000 | 0.693 | [Download](3000/ashisu_sahono_mangakasantoassistantsanto.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) |  |  |
| 2800 | 0.702 | [Download](2800/ashisu_sahono_mangakasantoassistantsanto.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) |  |  |
| 2600 | 0.694 | [Download](2600/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](2600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2600/previews/nude.png) | [<NSFW, click to see>](2600/previews/nude2.png) |  |  |
| **2400** | **0.736** | [**Download**](2400/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 2200 | 0.635 | [Download](2200/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](2200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2200/previews/nude.png) | [<NSFW, click to see>](2200/previews/nude2.png) |  |  |
| 2000 | 0.623 | [Download](2000/ashisu_sahono_mangakasantoassistantsanto.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) |  |  |
| 1800 | 0.546 | [Download](1800/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1600 | 0.640 | [Download](1600/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](1600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1600/previews/nude.png) | [<NSFW, click to see>](1600/previews/nude2.png) |  |  |
| 1400 | 0.663 | [Download](1400/ashisu_sahono_mangakasantoassistantsanto.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) |  |  |
| 1200 | 0.577 | [Download](1200/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](1200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1200/previews/nude.png) | [<NSFW, click to see>](1200/previews/nude2.png) |  |  |
| 1000 | 0.631 | [Download](1000/ashisu_sahono_mangakasantoassistantsanto.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) |  |  |
| 800 | 0.464 | [Download](800/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](800/previews/nude.png) | [<NSFW, click to see>](800/previews/nude2.png) |  |  |
| 600 | 0.453 | [Download](600/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](600/previews/nude.png) | [<NSFW, click to see>](600/previews/nude2.png) |  |  |
| 400 | 0.385 | [Download](400/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](400/previews/nude.png) | [<NSFW, click to see>](400/previews/nude2.png) |  |  |
| 200 | 0.192 | [Download](200/ashisu_sahono_mangakasantoassistantsanto.zip) |  |  |  |  |  |  |  | [<NSFW, click to see>](200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](200/previews/nude.png) | [<NSFW, click to see>](200/previews/nude2.png) |  |  |
|
OpenDILabCommunity/BipedalWalker-v3-TD3
|
OpenDILabCommunity
| 2023-09-22T22:40:13Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"BipedalWalker-v3",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-05-16T12:11:25Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- BipedalWalker-v3
benchmark_name: OpenAI/Gym/Box2d
task_name: BipedalWalker-v3
pipeline_tag: reinforcement-learning
model-index:
- name: TD3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Box2d-BipedalWalker-v3
type: OpenAI/Gym/Box2d-BipedalWalker-v3
metrics:
- type: mean_reward
value: 320.88 +/- 0.56
name: mean_reward
---
# Play **BipedalWalker-v3** with **TD3** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **TD3** implementation to OpenAI/Gym/Box2d **BipedalWalker-v3** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import TD3Agent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
# Instantiate the agent
agent = TD3Agent(
env_id="BipedalWalker-v3", exp_name="BipedalWalker-v3-TD3", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import TD3Agent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/BipedalWalker-v3-TD3")
# Instantiate the agent
agent = TD3Agent(
env_id="BipedalWalker-v3",
exp_name="BipedalWalker-v3-TD3",
cfg=cfg.exp_config,
policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import TD3Agent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = TD3Agent(env_id="BipedalWalker-v3", exp_name="BipedalWalker-v3-TD3")
# Train the agent
return_ = agent.train(step=int(200000))
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Box2d",
task_name="BipedalWalker-v3",
algo_name="TD3",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/td3.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/bipedalwalker.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./td3/bipedalwalker_td3_deploy.py",
usage_file_by_huggingface_ding="./td3/bipedalwalker_td3_download.py",
train_file="./td3/bipedalwalker_td3.py",
repo_id="OpenDILabCommunity/BipedalWalker-v3-TD3",
create_repo=False
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 10000000000,
'n_evaluator_episode': 5,
'env_id': 'BipedalWalker-v3',
'collector_env_num': 8,
'evaluator_env_num': 5,
'act_scale': True,
'rew_clip': True
},
'policy': {
'model': {
'twin_critic': True,
'obs_shape': 24,
'action_shape': 4,
'action_space': 'regression',
'actor_head_hidden_size': 400,
'critic_head_hidden_size': 400
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 1000,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 64,
'batch_size': 256,
'learning_rate_actor': 0.0003,
'learning_rate_critic': 0.0003,
'ignore_done': False,
'target_theta': 0.005,
'discount_factor': 0.99,
'actor_update_freq': 2,
'noise': True,
'noise_sigma': 0.2,
'noise_range': {
'min': -0.5,
'max': 0.5
}
},
'collect': {
'collector': {},
'unroll_len': 1,
'noise_sigma': 0.1,
'n_sample': 64
},
'eval': {
'evaluator': {
'eval_freq': 5000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'figure_path': None,
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 10000000000,
'n_episode': 5
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 300000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'td3',
'priority': False,
'priority_IS_weight': False,
'random_collect_size': 10000,
'transition_with_policy_data': False,
'action_space': 'continuous',
'reward_batch_norm': False,
'multi_agent': False,
'cfg_type': 'TD3PolicyDict'
},
'exp_name': 'BipedalWalker-v3-TD3',
'seed': 0,
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
}
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/BipedalWalker-v3-TD3)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/td3.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-TD3/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-TD3/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 4037.55 KB
- **Last Update Date:** 2023-09-22
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Box2d
- **Task:** BipedalWalker-v3
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.9
- **PyTorch version:** 2.0.1+cu117
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/bipedalwalker.html)
|
Chega/distill-scibert_scivocab_uncased
|
Chega
| 2023-09-22T22:23:50Z | 125 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"pretraining",
"biology",
"fill-mask",
"en",
"dataset:arxiv_dataset",
"dataset:pubmed",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-09-22T22:18:09Z |
---
license: apache-2.0
datasets:
- arxiv_dataset
- pubmed
language:
- en
pipeline_tag: fill-mask
tags:
- biology
---
|
OpenDILabCommunity/LunarLander-v2-TD3
|
OpenDILabCommunity
| 2023-09-22T22:10:58Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"LunarLander-v2",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-04-17T08:35:24Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- LunarLander-v2
benchmark_name: OpenAI/Gym/Box2d
task_name: LunarLander-v2
pipeline_tag: reinforcement-learning
model-index:
- name: TD3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Box2d-LunarLander-v2
type: OpenAI/Gym/Box2d-LunarLander-v2
metrics:
- type: mean_reward
value: 235.02 +/- 78.67
name: mean_reward
---
# Play **LunarLander-v2** with **TD3** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **TD3** implementation to OpenAI/Gym/Box2d **LunarLander-v2** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import TD3Agent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
# Instantiate the agent
agent = TD3Agent(
env_id="LunarLanderContinuous-v2",
exp_name="LunarLander-v2-TD3",
cfg=cfg.exp_config,
policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import TD3Agent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/LunarLander-v2-TD3")
# Instantiate the agent
agent = TD3Agent(
env_id="LunarLanderContinuous-v2",
exp_name="LunarLander-v2-TD3",
cfg=cfg.exp_config,
policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import TD3Agent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = TD3Agent(env_id="LunarLanderContinuous-v2", exp_name="LunarLander-v2-TD3")
# Train the agent
return_ = agent.train(step=int(4000000), collector_env_num=4, evaluator_env_num=4)
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Box2d",
task_name="LunarLander-v2",
algo_name="TD3",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/td3.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./td3/lunarlander_td3_deploy.py",
usage_file_by_huggingface_ding="./td3/lunarlander_td3_download.py",
train_file="./td3/lunarlander_td3.py",
repo_id="OpenDILabCommunity/LunarLander-v2-TD3",
create_repo=False
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 240,
'n_evaluator_episode': 8,
'env_id': 'LunarLanderContinuous-v2',
'collector_env_num': 4,
'evaluator_env_num': 8,
'act_scale': True
},
'policy': {
'model': {
'twin_critic': True,
'obs_shape': 8,
'action_shape': 2,
'action_space': 'regression'
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 256,
'batch_size': 256,
'learning_rate_actor': 0.0003,
'learning_rate_critic': 0.001,
'ignore_done': False,
'target_theta': 0.005,
'discount_factor': 0.99,
'actor_update_freq': 2,
'noise': True,
'noise_sigma': 0.1,
'noise_range': {
'min': -0.5,
'max': 0.5
}
},
'collect': {
'collector': {},
'unroll_len': 1,
'noise_sigma': 0.1,
'n_sample': 256
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'figure_path': None,
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 240,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 100000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'td3',
'priority': False,
'priority_IS_weight': False,
'random_collect_size': 10000,
'transition_with_policy_data': False,
'action_space': 'continuous',
'reward_batch_norm': False,
'multi_agent': False,
'cfg_type': 'TD3PolicyDict'
},
'exp_name': 'LunarLander-v2-TD3',
'seed': 0,
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
}
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/LunarLander-v2-TD3)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/td3.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-TD3/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-TD3/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 115.03 KB
- **Last Update Date:** 2023-09-22
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Box2d
- **Task:** LunarLander-v2
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.9
- **PyTorch version:** 2.0.1+cu117
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html)
|
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_ent_75_gates
|
jordyvl
| 2023-09-22T22:03:49Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"text-classification",
"generated_from_trainer",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T14:07:07Z |
---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_ent_75_gates
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. -->
# EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_ent_75_gates
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9971
- Accuracy: 0.7275
- Exit 0 Accuracy: 0.0625
- Exit 1 Accuracy: 0.055
- Exit 2 Accuracy: 0.0525
- Exit 3 Accuracy: 0.0625
- Exit 4 Accuracy: 0.0625
## 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: 20
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:|
| No log | 0.9 | 3 | 2.7374 | 0.1225 | 0.065 | 0.065 | 0.0825 | 0.0625 | 0.0625 |
| No log | 1.9 | 6 | 2.6769 | 0.1525 | 0.0625 | 0.06 | 0.09 | 0.0625 | 0.0625 |
| No log | 2.9 | 9 | 2.6398 | 0.1925 | 0.0625 | 0.0575 | 0.0875 | 0.0625 | 0.0625 |
| No log | 3.9 | 12 | 2.6077 | 0.21 | 0.065 | 0.0525 | 0.085 | 0.0625 | 0.0625 |
| No log | 4.9 | 15 | 2.5432 | 0.235 | 0.065 | 0.05 | 0.085 | 0.0625 | 0.0625 |
| No log | 5.9 | 18 | 2.4882 | 0.2525 | 0.065 | 0.05 | 0.085 | 0.0625 | 0.0625 |
| No log | 6.9 | 21 | 2.4322 | 0.27 | 0.065 | 0.04 | 0.085 | 0.0625 | 0.0625 |
| No log | 7.9 | 24 | 2.3583 | 0.2925 | 0.065 | 0.0425 | 0.09 | 0.0625 | 0.0625 |
| No log | 8.9 | 27 | 2.3032 | 0.3175 | 0.065 | 0.04 | 0.0925 | 0.0625 | 0.0625 |
| No log | 9.9 | 30 | 2.2374 | 0.34 | 0.0675 | 0.04 | 0.0825 | 0.0625 | 0.0625 |
| No log | 10.9 | 33 | 2.1630 | 0.3775 | 0.0675 | 0.0425 | 0.0775 | 0.0625 | 0.0625 |
| No log | 11.9 | 36 | 2.0998 | 0.395 | 0.0675 | 0.045 | 0.07 | 0.0625 | 0.0625 |
| No log | 12.9 | 39 | 2.0223 | 0.43 | 0.0675 | 0.045 | 0.0725 | 0.0625 | 0.0625 |
| No log | 13.9 | 42 | 1.9143 | 0.4825 | 0.065 | 0.05 | 0.07 | 0.0625 | 0.0625 |
| No log | 14.9 | 45 | 1.8329 | 0.5275 | 0.065 | 0.05 | 0.0725 | 0.0625 | 0.0625 |
| No log | 15.9 | 48 | 1.7532 | 0.545 | 0.0625 | 0.05 | 0.065 | 0.0625 | 0.0625 |
| No log | 16.9 | 51 | 1.6447 | 0.58 | 0.0625 | 0.05 | 0.065 | 0.0625 | 0.0625 |
| No log | 17.9 | 54 | 1.5863 | 0.59 | 0.065 | 0.0475 | 0.065 | 0.0625 | 0.0625 |
| No log | 18.9 | 57 | 1.5150 | 0.62 | 0.065 | 0.0475 | 0.0725 | 0.0625 | 0.0625 |
| No log | 19.9 | 60 | 1.4389 | 0.6325 | 0.065 | 0.0475 | 0.0725 | 0.0625 | 0.0625 |
| No log | 20.9 | 63 | 1.3834 | 0.6575 | 0.0625 | 0.0475 | 0.0725 | 0.0625 | 0.0625 |
| No log | 21.9 | 66 | 1.3297 | 0.675 | 0.0625 | 0.0475 | 0.075 | 0.0625 | 0.0625 |
| No log | 22.9 | 69 | 1.2805 | 0.6775 | 0.0625 | 0.0475 | 0.075 | 0.0625 | 0.0625 |
| No log | 23.9 | 72 | 1.2448 | 0.6825 | 0.0625 | 0.05 | 0.07 | 0.0625 | 0.0625 |
| No log | 24.9 | 75 | 1.1965 | 0.695 | 0.0625 | 0.05 | 0.0675 | 0.0625 | 0.0625 |
| No log | 25.9 | 78 | 1.1793 | 0.6925 | 0.0625 | 0.0525 | 0.0675 | 0.0625 | 0.0625 |
| No log | 26.9 | 81 | 1.1513 | 0.7 | 0.0625 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 27.9 | 84 | 1.1275 | 0.6975 | 0.0625 | 0.055 | 0.07 | 0.0625 | 0.0625 |
| No log | 28.9 | 87 | 1.0880 | 0.7225 | 0.0625 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 29.9 | 90 | 1.0749 | 0.7175 | 0.065 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 30.9 | 93 | 1.0716 | 0.7175 | 0.0625 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 31.9 | 96 | 1.0496 | 0.72 | 0.0625 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 32.9 | 99 | 1.0253 | 0.7275 | 0.065 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 33.9 | 102 | 1.0305 | 0.7175 | 0.065 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 34.9 | 105 | 1.0273 | 0.73 | 0.065 | 0.055 | 0.0675 | 0.0625 | 0.0625 |
| No log | 35.9 | 108 | 1.0072 | 0.73 | 0.065 | 0.055 | 0.07 | 0.0625 | 0.0625 |
| No log | 36.9 | 111 | 1.0183 | 0.7225 | 0.0625 | 0.055 | 0.07 | 0.0625 | 0.0625 |
| No log | 37.9 | 114 | 1.0079 | 0.725 | 0.0625 | 0.055 | 0.065 | 0.0625 | 0.0625 |
| No log | 38.9 | 117 | 1.0086 | 0.7375 | 0.0625 | 0.055 | 0.065 | 0.0625 | 0.0625 |
| No log | 39.9 | 120 | 0.9931 | 0.72 | 0.0625 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 40.9 | 123 | 0.9968 | 0.7325 | 0.0625 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 41.9 | 126 | 0.9848 | 0.73 | 0.0625 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 42.9 | 129 | 0.9983 | 0.7325 | 0.06 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 43.9 | 132 | 0.9988 | 0.725 | 0.06 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 44.9 | 135 | 0.9941 | 0.7275 | 0.0625 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 45.9 | 138 | 1.0053 | 0.72 | 0.0625 | 0.055 | 0.065 | 0.0625 | 0.0625 |
| No log | 46.9 | 141 | 0.9904 | 0.725 | 0.0625 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 47.9 | 144 | 0.9907 | 0.7225 | 0.0625 | 0.055 | 0.0625 | 0.0625 | 0.0625 |
| No log | 48.9 | 147 | 0.9883 | 0.7325 | 0.06 | 0.055 | 0.06 | 0.0625 | 0.0625 |
| No log | 49.9 | 150 | 0.9927 | 0.7325 | 0.0625 | 0.055 | 0.0575 | 0.0625 | 0.0625 |
| No log | 50.9 | 153 | 0.9981 | 0.73 | 0.0625 | 0.055 | 0.055 | 0.0625 | 0.0625 |
| No log | 51.9 | 156 | 0.9997 | 0.73 | 0.0625 | 0.055 | 0.055 | 0.0625 | 0.0625 |
| No log | 52.9 | 159 | 0.9899 | 0.73 | 0.0575 | 0.055 | 0.055 | 0.0625 | 0.0625 |
| No log | 53.9 | 162 | 0.9910 | 0.7275 | 0.0575 | 0.055 | 0.055 | 0.0625 | 0.0625 |
| No log | 54.9 | 165 | 1.0002 | 0.725 | 0.0575 | 0.055 | 0.055 | 0.0625 | 0.0625 |
| No log | 55.9 | 168 | 1.0044 | 0.7325 | 0.0575 | 0.055 | 0.0525 | 0.0625 | 0.0625 |
| No log | 56.9 | 171 | 0.9977 | 0.73 | 0.0575 | 0.055 | 0.05 | 0.0625 | 0.0625 |
| No log | 57.9 | 174 | 0.9960 | 0.73 | 0.0575 | 0.055 | 0.0525 | 0.0625 | 0.0625 |
| No log | 58.9 | 177 | 0.9964 | 0.7275 | 0.06 | 0.055 | 0.0525 | 0.0625 | 0.0625 |
| No log | 59.9 | 180 | 0.9971 | 0.7275 | 0.0625 | 0.055 | 0.0525 | 0.0625 | 0.0625 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
|
totally-not-an-llm/EverythingLM-13b-V3-peft
|
totally-not-an-llm
| 2023-09-22T21:35:17Z | 8 | 1 |
peft
|
[
"peft",
"llama",
"base_model:NousResearch/Llama-2-13b-hf",
"base_model:adapter:NousResearch/Llama-2-13b-hf",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2023-09-21T03:28:45Z |
---
library_name: peft
base_model: NousResearch/Llama-2-13b-hf
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
tlano/Tora-NijiFurry-LoRA-XL
|
tlano
| 2023-09-22T21:34:44Z | 0 | 7 | null |
[
"stable-diffusion",
"text-to-image",
"license:openrail++",
"region:us"
] |
text-to-image
| 2023-07-28T09:15:28Z |
---
license: openrail++
pipeline_tag: text-to-image
tags:
- stable-diffusion
---
# 説明 / Description
**Training Model:**<br>
 SDXL1.0<br>
**Trigger Words:**<br>
 furry<br>
<br>
# ライセンス / License
[CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md)
<br>
# おまけ
kohya_ss GUI用の学習設定ファイル<br>
ToraFurry_XL_p1-v1.json<br>
<br>
**作者**<br>
 twitter: [@TlanoAI](https://twitter.com/TlanoAI)<br>
<br>
|
Panchovix/Marcoroni-70B-v1-4.65bpw-h6-exl2
|
Panchovix
| 2023-09-22T21:32:05Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T20:54:23Z |
---
license: other
---
4.65 bit/bpw quantization of Marcoroni-70B-v1 (https://huggingface.co/AIDC-ai-business/Marcoroni-70B-v1) using exllamav2.
|
Medissa/my_awesome_eli5_mlm_model
|
Medissa
| 2023-09-22T21:29:48Z | 162 | 0 |
transformers
|
[
"transformers",
"pytorch",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilroberta-base",
"base_model:finetune:distilbert/distilroberta-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-08-18T15:46:46Z |
---
license: apache-2.0
tags:
- generated_from_trainer
base_model: distilroberta-base
model-index:
- name: my_awesome_eli5_mlm_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_eli5_mlm_model
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9892
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2633 | 1.0 | 1134 | 2.0191 |
| 2.1646 | 2.0 | 2268 | 1.9993 |
| 2.1182 | 3.0 | 3402 | 1.9892 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.11.0
|
Medissa/xlm-roberta-base-finetuned-panx-de
|
Medissa
| 2023-09-22T21:29:07Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-03-19T14:40:31Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
base_model: xlm-roberta-base
model-index:
- name: xlm-roberta-base-finetuned-panx-de
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.de
split: validation
args: PAN-X.de
metrics:
- type: f1
value: 0.8638300289723342
name: F1
---
<!-- 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-de
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: 0.1358
- F1: 0.8638
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2591 | 1.0 | 525 | 0.1621 | 0.8206 |
| 0.1276 | 2.0 | 1050 | 0.1379 | 0.8486 |
| 0.082 | 3.0 | 1575 | 0.1358 | 0.8638 |
### Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
|
Ori/lama-2-13b-peft-strategyqa-with-retrieval-at-1-v2-seed-3
|
Ori
| 2023-09-22T21:09:25Z | 0 | 0 |
peft
|
[
"peft",
"safetensors",
"region:us"
] | null | 2023-09-22T08:03:53Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0.dev0
|
sujitrect/llama2-qlora-finetuned-french
|
sujitrect
| 2023-09-22T20:53:07Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T20:52:59Z |
---
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
|
CyberHarem/aikawa_chinatsu_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T20:47:15Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/aikawa_chinatsu_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T20:38:09Z |
---
license: mit
datasets:
- CyberHarem/aikawa_chinatsu_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of aikawa_chinatsu_idolmastercinderellagirls
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 4080, you need to download `4080/aikawa_chinatsu_idolmastercinderellagirls.pt` as the embedding and `4080/aikawa_chinatsu_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4080**, with the score of 0.921. The trigger words are:
1. `aikawa_chinatsu_idolmastercinderellagirls`
2. `short_hair, glasses, brown_hair, brown_eyes, red-framed_eyewear, jewelry`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.921 | [Download](5100/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.912 | [Download](4760/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.838 | [Download](4420/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| **4080** | **0.921** | [**Download**](4080/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.880 | [Download](3740/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.884 | [Download](3400/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.886 | [Download](3060/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.816 | [Download](2720/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.896 | [Download](2380/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.879 | [Download](2040/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.884 | [Download](1700/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.802 | [Download](1360/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.843 | [Download](1020/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.832 | [Download](680/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.750 | [Download](340/aikawa_chinatsu_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
keikofujii/distilbert-base-uncased-finetuned-stsb
|
keikofujii
| 2023-09-22T20:41:45Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"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
| 2023-09-22T20:11:27Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert-base-uncased-finetuned-stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: stsb
split: validation
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.8679004942016133
---
<!-- 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-stsb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5563
- Pearson: 0.8708
- Spearmanr: 0.8679
## 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
| No log | 1.0 | 360 | 0.6167 | 0.8601 | 0.8577 |
| 1.0026 | 2.0 | 720 | 0.6175 | 0.8670 | 0.8653 |
| 0.3862 | 3.0 | 1080 | 0.6439 | 0.8703 | 0.8675 |
| 0.3862 | 4.0 | 1440 | 0.5563 | 0.8708 | 0.8679 |
| 0.2514 | 5.0 | 1800 | 0.5616 | 0.8694 | 0.8659 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
YassineBenlaria/testing_pretrained_niger_mali
|
YassineBenlaria
| 2023-09-22T20:41:39Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-22T17:26:37Z |
---
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: testing_pretrained_niger_mali
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. -->
# testing_pretrained_niger_mali
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9245
- Wer: 0.8889
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 350
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 6.427 | 35.29 | 300 | 2.9588 | 1.0 |
| 2.8653 | 70.59 | 600 | 2.7466 | 1.0 |
| 2.7675 | 105.88 | 900 | 2.7207 | 1.0 |
| 2.6674 | 141.18 | 1200 | 2.2285 | 1.0 |
| 1.7813 | 176.47 | 1500 | 1.5717 | 0.8852 |
| 1.0447 | 211.76 | 1800 | 1.7009 | 0.8778 |
| 0.8167 | 247.06 | 2100 | 1.8010 | 0.8815 |
| 0.7059 | 282.35 | 2400 | 1.8748 | 0.8815 |
| 0.6572 | 317.65 | 2700 | 1.9245 | 0.8889 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
kmaksatk/controlnet_80k_data_blip
|
kmaksatk
| 2023-09-22T20:18:20Z | 2 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"controlnet",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-09-21T06:40:04Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- controlnet
inference: true
---
# controlnet-kmaksatk/controlnet_80k_data_blip
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
You can find some example images below.
prompt: High qualityphoto of male gymnast in a blue sport outfit in the olympic game
prompt: High qualityphoto of male gymnast in a blue sport outfit in the olympic game
prompt: High qualityphoto of male gymnast in a blue sport outfit in the olympic game
|
CyberHarem/momoi_azuki_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T19:56:22Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/momoi_azuki_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T19:43:43Z |
---
license: mit
datasets:
- CyberHarem/momoi_azuki_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of momoi_azuki_idolmastercinderellagirls
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 3060, you need to download `3060/momoi_azuki_idolmastercinderellagirls.pt` as the embedding and `3060/momoi_azuki_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3060**, with the score of 0.937. The trigger words are:
1. `momoi_azuki_idolmastercinderellagirls`
2. `brown_eyes, black_hair, smile, breasts, blush, hair_ornament, open_mouth, flower, hair_flower, single_hair_bun, hair_bun, brown_hair, long_hair, 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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.863 | [Download](5100/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](5100/previews/pattern_1.png) |  |  | [<NSFW, click to see>](5100/previews/pattern_4.png) |  | [<NSFW, click to see>](5100/previews/pattern_6.png) | [<NSFW, click to see>](5100/previews/pattern_7.png) |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.852 | [Download](4760/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](4760/previews/pattern_1.png) |  |  | [<NSFW, click to see>](4760/previews/pattern_4.png) |  | [<NSFW, click to see>](4760/previews/pattern_6.png) | [<NSFW, click to see>](4760/previews/pattern_7.png) |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.800 | [Download](4420/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](4420/previews/pattern_1.png) |  |  | [<NSFW, click to see>](4420/previews/pattern_4.png) |  | [<NSFW, click to see>](4420/previews/pattern_6.png) | [<NSFW, click to see>](4420/previews/pattern_7.png) |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.897 | [Download](4080/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](4080/previews/pattern_1.png) |  |  | [<NSFW, click to see>](4080/previews/pattern_4.png) |  | [<NSFW, click to see>](4080/previews/pattern_6.png) | [<NSFW, click to see>](4080/previews/pattern_7.png) |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.866 | [Download](3740/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](3740/previews/pattern_1.png) |  |  | [<NSFW, click to see>](3740/previews/pattern_4.png) |  | [<NSFW, click to see>](3740/previews/pattern_6.png) | [<NSFW, click to see>](3740/previews/pattern_7.png) |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.874 | [Download](3400/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](3400/previews/pattern_1.png) |  |  | [<NSFW, click to see>](3400/previews/pattern_4.png) |  | [<NSFW, click to see>](3400/previews/pattern_6.png) | [<NSFW, click to see>](3400/previews/pattern_7.png) |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| **3060** | **0.937** | [**Download**](3060/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](3060/previews/pattern_1.png) |  |  | [<NSFW, click to see>](3060/previews/pattern_4.png) |  | [<NSFW, click to see>](3060/previews/pattern_6.png) | [<NSFW, click to see>](3060/previews/pattern_7.png) |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.873 | [Download](2720/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](2720/previews/pattern_1.png) |  |  | [<NSFW, click to see>](2720/previews/pattern_4.png) |  | [<NSFW, click to see>](2720/previews/pattern_6.png) | [<NSFW, click to see>](2720/previews/pattern_7.png) |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.858 | [Download](2380/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](2380/previews/pattern_1.png) |  |  | [<NSFW, click to see>](2380/previews/pattern_4.png) |  | [<NSFW, click to see>](2380/previews/pattern_6.png) | [<NSFW, click to see>](2380/previews/pattern_7.png) |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.877 | [Download](2040/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](2040/previews/pattern_1.png) |  |  | [<NSFW, click to see>](2040/previews/pattern_4.png) |  | [<NSFW, click to see>](2040/previews/pattern_6.png) | [<NSFW, click to see>](2040/previews/pattern_7.png) |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.872 | [Download](1700/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](1700/previews/pattern_1.png) |  |  | [<NSFW, click to see>](1700/previews/pattern_4.png) |  | [<NSFW, click to see>](1700/previews/pattern_6.png) | [<NSFW, click to see>](1700/previews/pattern_7.png) |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.901 | [Download](1360/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](1360/previews/pattern_1.png) |  |  | [<NSFW, click to see>](1360/previews/pattern_4.png) |  | [<NSFW, click to see>](1360/previews/pattern_6.png) | [<NSFW, click to see>](1360/previews/pattern_7.png) |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.896 | [Download](1020/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](1020/previews/pattern_1.png) |  |  | [<NSFW, click to see>](1020/previews/pattern_4.png) |  | [<NSFW, click to see>](1020/previews/pattern_6.png) | [<NSFW, click to see>](1020/previews/pattern_7.png) |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.877 | [Download](680/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](680/previews/pattern_1.png) |  |  | [<NSFW, click to see>](680/previews/pattern_4.png) |  | [<NSFW, click to see>](680/previews/pattern_6.png) | [<NSFW, click to see>](680/previews/pattern_7.png) |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.786 | [Download](340/momoi_azuki_idolmastercinderellagirls.zip) | [<NSFW, click to see>](340/previews/pattern_1.png) |  |  | [<NSFW, click to see>](340/previews/pattern_4.png) |  | [<NSFW, click to see>](340/previews/pattern_6.png) | [<NSFW, click to see>](340/previews/pattern_7.png) |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
UnstableLlama/Xwin-LM-13B-V0.1-4.65bpw-exl2
|
UnstableLlama
| 2023-09-22T19:54:24Z | 94 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-22T19:27:28Z |
---
base_model: https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1
inference: false
license: llama2
model_creator: Xwin-LM
model_name: Xwin-LM 13B V0.1
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: UnstableLlama
---
---
4.65bpw ExLlamaV2 quantization by UnstableLlama
license: llama2
---
<h3 align="center">
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
</h3>
<p align="center">
<a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
</p>
**Step up your LLM alignment with Xwin-LM!**
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
## News
- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
## Model Card
| Model | Checkpoint | Report | License |
|------------|------------|-------------|------------------|
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
## Benchmarks
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|----------------------------------|------------|----------|-------------|
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
| GPT-4 | 95.28 | 84.66 | 50.00 |
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
| ChatGPT | 89.37 | 50.00 | 16.60 |
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
| Prompts | GTP4 response | Xwin-LM response |
|----------------|------------|--------|
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
### Xwin-LM performance on NLP foundation tasks.
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|------------------|-------------|-------------|-------------------|-------------------|------------|
| Text-davinci-003 | 56.9 | **85.2** | 59.3 | 82.2 | 70.9 |
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|Guanaco 30B | 57.6 | 63.7 | 50.7 | 85.1 | 64.3 |
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
| WizardLM-30B 1.0 | 58.8 | 62.5 | 52.4 | 83.3 | 64.2|
| Llama-2-7B-Chat | 48.3 | 52.9 | 45.6 | 78.6 | 56.4 |
| Llama-2-13B-Chat | 54.6 | 59.0 | 44.1 | 81.9 | 59.9 |
| Llama-2-70B-Chat | 63.9 | 64.6 | 52.8 | 85.9 | 66.8 |
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
| **Xwin-LM-13B-V0.1** | 56.6 | 62.4 | 45.5 | 83.0 | 61.9 |
| **Xwin-LM-70B-V0.1** | **69.6** | 70.5 | **60.1** | **87.1** | **71.8** |
## Inference
### Conversation templates
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
```
### HuggingFace Example
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
inputs = tokenizer(prompt, return_tensors="pt")
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(output)
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
```
### vllm Example
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions.
```python
from vllm import LLM, SamplingParams
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
outputs = llm.generate([prompt,], sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(generated_text)
```
## TODO
- [ ] Release the source code
- [ ] Release more capabilities, such as math, reasoning, and etc.
## Citation
Please consider citing our work if you use the data or code in this repo.
```
@software{xwin-lm,
title = {Xwin-LM},
author = {Xwin-LM Team},
url = {https://github.com/Xwin-LM/Xwin-LM},
version = {pre-release},
year = {2023},
month = {9},
}
```
## Acknowledgements
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
|
eugene6/q-FrozenLake-v1-4x4-noSlippery
|
eugene6
| 2023-09-22T19:54:05Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T19:54:03Z |
---
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="eugene6/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"])
```
|
DriveMyScream/News_Sentiment_Analysis_model
|
DriveMyScream
| 2023-09-22T19:44:17Z | 0 | 0 |
keras
|
[
"keras",
"tf-keras",
"region:us"
] | null | 2023-09-22T19:43:45Z |
---
library_name: keras
---
## 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:
| Hyperparameters | Value |
| :-- | :-- |
| name | Adam |
| weight_decay | None |
| clipnorm | None |
| global_clipnorm | None |
| clipvalue | None |
| use_ema | False |
| ema_momentum | 0.99 |
| ema_overwrite_frequency | None |
| jit_compile | True |
| is_legacy_optimizer | False |
| learning_rate | 0.0010000000474974513 |
| beta_1 | 0.9 |
| beta_2 | 0.999 |
| epsilon | 1e-07 |
| amsgrad | False |
| training_precision | float32 |
## Model Plot
<details>
<summary>View Model Plot</summary>
</details>
|
Amey-HH/ddpm-butterflies-128
|
Amey-HH
| 2023-09-22T19:15:14Z | 34 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] |
unconditional-image-generation
| 2023-09-22T18:33:33Z |
---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of Polyps.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('Amey-HH/ddpm-butterflies-128')
image = pipeline().images[0]
image
```
|
CyberHarem/aino_nagisa_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T19:06:17Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/aino_nagisa_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T18:57:44Z |
---
license: mit
datasets:
- CyberHarem/aino_nagisa_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of aino_nagisa_idolmastercinderellagirls
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 4760, you need to download `4760/aino_nagisa_idolmastercinderellagirls.pt` as the embedding and `4760/aino_nagisa_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.957. The trigger words are:
1. `aino_nagisa_idolmastercinderellagirls`
2. `brown_hair, long_hair, ponytail, smile, brown_eyes, 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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:---------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.954 | [Download](5100/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.957** | [**Download**](4760/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.908 | [Download](4420/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.952 | [Download](4080/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.938 | [Download](3740/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.902 | [Download](3400/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.870 | [Download](3060/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.867 | [Download](2720/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.858 | [Download](2380/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.871 | [Download](2040/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.827 | [Download](1700/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.573 | [Download](1360/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.677 | [Download](1020/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.400 | [Download](680/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.458 | [Download](340/aino_nagisa_idolmastercinderellagirls.zip) |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
przl/q-Taxi-v3
|
przl
| 2023-09-22T18:57:57Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T18:57:55Z |
---
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: 7.54 +/- 2.73
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="przl/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"])
```
|
santis2/gpt2-alpaca-instruction-fine-tuning-lora
|
santis2
| 2023-09-22T18:52:42Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"region:us"
] | null | 2023-09-22T15:35:13Z |
---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-alpaca-instruction-fine-tuning-lora
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. -->
# gpt2-alpaca-instruction-fine-tuning-lora
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6981
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.118 | 0.11 | 1000 | 1.7807 |
| 1.8878 | 0.22 | 2000 | 1.7477 |
| 1.8609 | 0.33 | 3000 | 1.7318 |
| 1.8489 | 0.44 | 4000 | 1.7207 |
| 1.8416 | 0.55 | 5000 | 1.7134 |
| 1.8181 | 0.66 | 6000 | 1.7082 |
| 1.8144 | 0.77 | 7000 | 1.7021 |
| 1.816 | 0.88 | 8000 | 1.6987 |
| 1.7825 | 0.99 | 9000 | 1.6981 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
UnstableLlama/Xwin-LM-13B-V0.1-5bpw-exl2
|
UnstableLlama
| 2023-09-22T18:51:12Z | 94 | 3 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-22T18:22:40Z |
---
base_model: https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1
inference: false
license: llama2
model_creator: Xwin-LM
model_name: Xwin-LM 13B V0.1
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: UnstableLlama
---
---
5bpw ExLlamaV2 quantization by UnstableLlama
license: llama2
---
<h3 align="center">
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
</h3>
<p align="center">
<a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
</p>
**Step up your LLM alignment with Xwin-LM!**
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
## News
- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
## Model Card
| Model | Checkpoint | Report | License |
|------------|------------|-------------|------------------|
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
## Benchmarks
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|----------------------------------|------------|----------|-------------|
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
| GPT-4 | 95.28 | 84.66 | 50.00 |
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
| ChatGPT | 89.37 | 50.00 | 16.60 |
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
| Prompts | GTP4 response | Xwin-LM response |
|----------------|------------|--------|
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
### Xwin-LM performance on NLP foundation tasks.
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|------------------|-------------|-------------|-------------------|-------------------|------------|
| Text-davinci-003 | 56.9 | **85.2** | 59.3 | 82.2 | 70.9 |
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|Guanaco 30B | 57.6 | 63.7 | 50.7 | 85.1 | 64.3 |
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
| WizardLM-30B 1.0 | 58.8 | 62.5 | 52.4 | 83.3 | 64.2|
| Llama-2-7B-Chat | 48.3 | 52.9 | 45.6 | 78.6 | 56.4 |
| Llama-2-13B-Chat | 54.6 | 59.0 | 44.1 | 81.9 | 59.9 |
| Llama-2-70B-Chat | 63.9 | 64.6 | 52.8 | 85.9 | 66.8 |
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
| **Xwin-LM-13B-V0.1** | 56.6 | 62.4 | 45.5 | 83.0 | 61.9 |
| **Xwin-LM-70B-V0.1** | **69.6** | 70.5 | **60.1** | **87.1** | **71.8** |
## Inference
### Conversation templates
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
```
### HuggingFace Example
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
inputs = tokenizer(prompt, return_tensors="pt")
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(output)
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
```
### vllm Example
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions.
```python
from vllm import LLM, SamplingParams
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
outputs = llm.generate([prompt,], sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(generated_text)
```
## TODO
- [ ] Release the source code
- [ ] Release more capabilities, such as math, reasoning, and etc.
## Citation
Please consider citing our work if you use the data or code in this repo.
```
@software{xwin-lm,
title = {Xwin-LM},
author = {Xwin-LM Team},
url = {https://github.com/Xwin-LM/Xwin-LM},
version = {pre-release},
year = {2023},
month = {9},
}
```
## Acknowledgements
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
|
jmoney54378256438905/jondurbin_airoboros-c34b-2.2.1-4.65bpw
|
jmoney54378256438905
| 2023-09-22T18:48:51Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T18:38:37Z |
---
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.
|
TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11
|
TamerAbdelaziz
| 2023-09-22T18:45:47Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"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
| 2023-09-22T17:59:17Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0094
- Validation Loss: 0.3097
- Train Accuracy: 0.9364
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.2466 | 0.1804 | 0.9314 | 0 |
| 0.1417 | 0.1824 | 0.9324 | 1 |
| 0.0892 | 0.2208 | 0.9268 | 2 |
| 0.0532 | 0.2212 | 0.9348 | 3 |
| 0.0328 | 0.2518 | 0.936 | 4 |
| 0.0218 | 0.2750 | 0.9358 | 5 |
| 0.0185 | 0.2856 | 0.9338 | 6 |
| 0.0147 | 0.3055 | 0.935 | 7 |
| 0.0113 | 0.3060 | 0.9352 | 8 |
| 0.0094 | 0.3097 | 0.9364 | 9 |
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.8.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
treei/llama-2-7b-keyword-ft
|
treei
| 2023-09-22T18:44:02Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T18:41:07Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
- PEFT 0.5.0
- PEFT 0.5.0
- PEFT 0.5.0
|
thainq107/flan-t5-small-twitter-sentiment-analysis-lora
|
thainq107
| 2023-09-22T18:36:38Z | 0 | 0 | null |
[
"pytorch",
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2023-09-22T17:02:51Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: flan-t5-small-twitter-sentiment-analysis-lora
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flan-t5-small-twitter-sentiment-analysis-lora
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2093
- Accuracy: 0.8115
## 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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2573 | 1.0 | 938 | 0.2270 | 0.7941 |
| 0.2369 | 2.0 | 1876 | 0.2176 | 0.8057 |
| 0.2286 | 3.0 | 2814 | 0.2132 | 0.8091 |
| 0.2227 | 4.0 | 3752 | 0.2089 | 0.8122 |
| 0.2204 | 5.0 | 4690 | 0.2083 | 0.8141 |
| 0.2191 | 6.0 | 5628 | 0.2077 | 0.8143 |
| 0.2183 | 7.0 | 6566 | 0.2048 | 0.8169 |
| 0.2155 | 8.0 | 7504 | 0.2066 | 0.8156 |
| 0.2164 | 9.0 | 8442 | 0.2047 | 0.8174 |
| 0.2167 | 10.0 | 9380 | 0.2041 | 0.8177 |
### Framework versions
- Transformers 4.27.1
- Pytorch 2.0.1
- Datasets 2.9.0
- Tokenizers 0.13.3
|
Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2
|
Thireus
| 2023-09-22T18:33:52Z | 9 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-17T19:08:07Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2
|
Thireus
| 2023-09-22T18:33:35Z | 12 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-21T03:52:37Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2
|
Thireus
| 2023-09-22T18:33:24Z | 5 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-19T08:09:31Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
alpindale/Llama-2-13b-ONNX
|
alpindale
| 2023-09-22T18:33:20Z | 0 | 5 | null |
[
"onnx",
"text generation",
"text-generation",
"en",
"license:llama2",
"region:us"
] |
text-generation
| 2023-09-21T20:28:10Z |
---
language:
- en
thumbnail: null
tags:
- text generation
pipeline_tag: text-generation
inference: false
license: llama2
---
# Llama-2 ONNX
This repository contains optimized version of Llama-2 13B.
## Downloading the model
You can use `huggingface_hub` to download this repository. This can be done through both python scripting and the commandline. Refer to the [HuggingFace Hub Documentation](https://huggingface.co/docs/huggingface_hub/guides/download) for the Python examples.
With CLI:
1. Make sure you have an updated `huggingface_hub` installed.
```sh
pip install -U huggingface_hub
```
2. Download the repository.
```sh
huggingface-cli download alpindale/Llama-2-13b-ONNX --repo-type model --cache-dir /path/to/custom/cache/directory --local-dir /path/to/download/dir --local-dir-use-symlinks False
```
The `--cache-dir` kwarg is only necessary if your default cache directory (`~/.cache`) does not have enough disk space to accomodate the entire repository.
## Using the model
The repository provides example code for running the models.
```sh
python llama2_onnx_inference.py --onnx_file FP16/LlamaV2_13B_float16.onnx --embedding_file embeddings.pth --tokenizer_path tokenizer.model --prompt "What is the lightest element?"
```
Output:
```
The lightest element is hydrogen. Hydrogen is the lightest element on the periodic table, with an atomic mass of 1.00794 u (unified atomic mass units).
```
### Chat Interface
Alternatively, you can use the Gradio chat interface to run the models.
First, install the required packages:
```sh
pip install -r requirements.txt
```
Set the Python path to the root directory of the repository (necessary for importing the required modules):
```sh
export PYTHONPATH=$PYTHONPATH:$(pwd)
```
Then you can simply run:
```sh
python ChatApp/app.py
```
You can then navigate to [http://localhost:7860](https://127.0.0.1:7860) on your browser to access the interface.
## FAQ
### Why is the first inference session slow?
ONNX runtime execution provider might need to generate JIT binaries for the underlying hardware, typically the binary is cache and will be loaded directly in the subsequent runs to reduce the overhead.
### Why is FP16 slower than FP32 on my device?
Your device may not support native FP16 math, therefore weights will be cast to FP32 at runtime. Using the FP32 version of the model will avoid the cast overhead.
### How do I optimize inference?
It's recommended that inputs/outputs are put on target device to avoid expensive data copies, please refer to the following documentations for details:
[I/O Binding | onnxruntime](https://onnxruntime.ai/docs/performance/tune-performance/iobinding.html)
### What generation parameters should I use the model with?
You can perform temperature and top-p sampling with the provided example code. Please refer to Meta's example [here](https://github.com/facebookresearch/llama/).
|
Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2
|
Thireus
| 2023-09-22T18:33:08Z | 10 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-21T03:52:35Z |
---
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: Thireus
---
# WizardLM 70B V1.0 – EXL2
- Model creator: [WizardLM](https://huggingface.co/WizardLM)
- FP32 Original model used for quantization: [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) – float32
- FP16 Model used for quantization: [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) – float16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
- BF16 Model used for quantization: [WizardLM 70B V1.0-BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) – bfloat16 of [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
## Models available:
| Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
| ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
| [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
\* wikitext-2-raw-v1
\*\* Evaluated with text-generation-webui ExLlama v0.0.2 on wikitext-2-raw-v1 (stride 512 and max_length 0). For reference, [TheBloke_WizardLM-70B-V1.0-GPTQ_gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) has a score of 4.1015625 in perplexity.
## Description:
_This repository contains EXL2 model files for [WizardLM's WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)._
EXL2 is a new format used by ExLlamaV2 – https://github.com/turboderp/exllamav2. EXL2 is based on the same optimization method as GPTQ. The format allows for mixing quantization
levels within a model to achieve any average bitrate between 2 and 8 bits per weight.
## Prompt template (official):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
## Prompt template (suggested):
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER:
{prompt}
ASSISTANT:
```
## Quantization process:
| Original Model | → | (optional) float16 or bfloat16 Model* | → | Safetensors Model** | → | EXL2 Model |
| -------------- | --- | ------------- | --- | ---------------- | --- | ---------- |
| [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | → | [WizardLM 70B V1.0-HF](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF)* | → | Safetensors** | → | EXL2 |
Example to convert WizardLM-70B-V1.0-HF to EXL2 4.0 bpw with 6-bit head:
```
mkdir -p ~/EXL2/WizardLM-70B-V1.0-HF_4bit # Create the output directory
python convert.py -i ~/float16_safetensored/WizardLM-70B-V1.0-HF -o ~/EXL2/WizardLM-70B-V1.0-HF_4bit -c ~/EXL2/0000.parquet -b 4.0 -hb 6
```
\* Use the following script to convert your local pytorch_model bin files to float16 (you can also choose bfloat16) + safetensors all in one go:
- https://github.com/oobabooga/text-generation-webui/blob/main/convert-to-safetensors.py
(best for sharding and float16/FP16 or bfloat16/BF16 conversion)
Example to convert [WizardLM 70B V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) directly to float16 safetensors in 10GB shards:
```
python convert-to-safetensors.py ~/original/WizardLM-70B-V1.0 --output ~/float16_safetensored/WizardLM-70B-V1.0 --max-shard-size 10GB
```
Use `--bf16` if you'd like to try bfloat16 instead, but note that there are concerns about quantization quality – https://github.com/turboderp/exllamav2/issues/30#issuecomment-1719009289
\*\* Use any one of the following scripts to convert your local pytorch_model bin files to safetensors:
- https://github.com/turboderp/exllamav2/blob/master/util/convert_safetensors.py (official ExLlamaV2)
- https://huggingface.co/Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors/blob/main/bin2safetensors/convert.py (recommended)
- https://gist.github.com/epicfilemcnulty/1f55fd96b08f8d4d6693293e37b4c55e#file-2safetensors-py
## Further reading:
- https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html
|
sachithgunasekara/open-llama-v2-lamini-orca-evol-guanaco-qlora-checkpoint
|
sachithgunasekara
| 2023-09-22T18:25:14Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T18:25:09Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
LucaAsga/ppo-LunarLander-v2-NEW
|
LucaAsga
| 2023-09-22T18:22:03Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T18:21:42Z |
---
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: 274.11 +/- 17.24
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
...
```
|
0ppxnhximxr/distilbert-base-uncased-finetuned-emotion
|
0ppxnhximxr
| 2023-09-22T18:14:16Z | 107 | 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
| 2023-09-22T18:11:23Z |
---
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: 0.926
- name: F1
type: f1
value: 0.9259596663626415
---
<!-- 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: 0.2200
- Accuracy: 0.926
- F1: 0.9260
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.836 | 1.0 | 250 | 0.3195 | 0.906 | 0.9053 |
| 0.2573 | 2.0 | 500 | 0.2200 | 0.926 | 0.9260 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
AIYIYA/my_html3
|
AIYIYA
| 2023-09-22T18:03:14Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-chinese",
"base_model:finetune:google-bert/bert-base-chinese",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T17:50:11Z |
---
base_model: bert-base-chinese
tags:
- generated_from_keras_callback
model-index:
- name: AIYIYA/my_html3
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# AIYIYA/my_html3
This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1064
- Train Accuracy: 1.0
- Validation Loss: 0.1251
- Validation Accuracy: 0.9804
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 30, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.8291 | 0.7386 | 0.2926 | 0.9804 | 0 |
| 0.2239 | 0.9804 | 0.1478 | 0.9804 | 1 |
| 0.1064 | 1.0 | 0.1251 | 0.9804 | 2 |
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
|
UnstableLlama/Xwin-LM-7B-V0.1-4bpw-exl2
|
UnstableLlama
| 2023-09-22T18:00:50Z | 79 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-09-22T17:43:37Z |
---
base_model: https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1
inference: false
license: llama2
model_creator: Xwin-LM
model_name: Xwin-LM 7B V0.1
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: UnstableLlama
---
---
4bpw ExLlamaV2 quantization by UnstableLlama
license: llama2
---
<h3 align="center">
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
</h3>
<p align="center">
<a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
</p>
**Step up your LLM alignment with Xwin-LM!**
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
## News
- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
## Model Card
| Model | Checkpoint | Report | License |
|------------|------------|-------------|------------------|
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
## Benchmarks
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|----------------------------------|------------|----------|-------------|
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
| GPT-4 | 95.28 | 84.66 | 50.00 |
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
| ChatGPT | 89.37 | 50.00 | 16.60 |
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
| Prompts | GTP4 response | Xwin-LM response |
|----------------|------------|--------|
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
### Xwin-LM performance on NLP foundation tasks.
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|------------------|-------------|-------------|-------------------|-------------------|------------|
| Text-davinci-003 | 56.9 | **85.2** | 59.3 | 82.2 | 70.9 |
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|Guanaco 30B | 57.6 | 63.7 | 50.7 | 85.1 | 64.3 |
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
| WizardLM-30B 1.0 | 58.8 | 62.5 | 52.4 | 83.3 | 64.2|
| Llama-2-7B-Chat | 48.3 | 52.9 | 45.6 | 78.6 | 56.4 |
| Llama-2-13B-Chat | 54.6 | 59.0 | 44.1 | 81.9 | 59.9 |
| Llama-2-70B-Chat | 63.9 | 64.6 | 52.8 | 85.9 | 66.8 |
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
| **Xwin-LM-13B-V0.1** | 56.6 | 62.4 | 45.5 | 83.0 | 61.9 |
| **Xwin-LM-70B-V0.1** | **69.6** | 70.5 | **60.1** | **87.1** | **71.8** |
## Inference
### Conversation templates
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
```
### HuggingFace Example
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
inputs = tokenizer(prompt, return_tensors="pt")
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(output)
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
```
### vllm Example
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions.
```python
from vllm import LLM, SamplingParams
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
outputs = llm.generate([prompt,], sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(generated_text)
```
## TODO
- [ ] Release the source code
- [ ] Release more capabilities, such as math, reasoning, and etc.
## Citation
Please consider citing our work if you use the data or code in this repo.
```
@software{xwin-lm,
title = {Xwin-LM},
author = {Xwin-LM Team},
url = {https://github.com/Xwin-LM/Xwin-LM},
version = {pre-release},
year = {2023},
month = {9},
}
```
## Acknowledgements
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
|
TieIncred/cloth2
|
TieIncred
| 2023-09-22T17:58:39Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-08T13:22:15Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of checkodsasdass man
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - TieIncred/cloth2
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a photo of checkodsasdass man using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: True.
|
kupru/ppo-Pyramids
|
kupru
| 2023-09-22T17:43:02Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-09-22T17:42:56Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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: kupru/ppo-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_10
|
TamerAbdelaziz
| 2023-09-22T17:41:24Z | 63 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"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
| 2023-09-22T11:03:52Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_10
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_10
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0067
- Validation Loss: 0.3379
- Train Accuracy: 0.9354
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.2338 | 0.1838 | 0.9304 | 0 |
| 0.1379 | 0.1821 | 0.931 | 1 |
| 0.0748 | 0.1896 | 0.9334 | 2 |
| 0.0427 | 0.2671 | 0.9318 | 3 |
| 0.0260 | 0.2814 | 0.933 | 4 |
| 0.0198 | 0.3015 | 0.9338 | 5 |
| 0.0134 | 0.3239 | 0.9342 | 6 |
| 0.0104 | 0.3797 | 0.9268 | 7 |
| 0.0088 | 0.3347 | 0.9338 | 8 |
| 0.0067 | 0.3379 | 0.9354 | 9 |
### Framework versions
- Transformers 4.33.2
- TensorFlow 2.8.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
EdBianchi/vit-fire-detection
|
EdBianchi
| 2023-09-22T17:17:15Z | 1,621 | 6 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2022-12-29T15:41:07Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: vit-fire-detection
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. -->
# vit-fire-detection
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 None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0126
- Precision: 0.9960
- Recall: 0.9960
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
| 0.1018 | 1.0 | 190 | 0.0375 | 0.9934 | 0.9934 |
| 0.0484 | 2.0 | 380 | 0.0167 | 0.9961 | 0.9960 |
| 0.0357 | 3.0 | 570 | 0.0253 | 0.9948 | 0.9947 |
| 0.0133 | 4.0 | 760 | 0.0198 | 0.9961 | 0.9960 |
| 0.012 | 5.0 | 950 | 0.0203 | 0.9947 | 0.9947 |
| 0.0139 | 6.0 | 1140 | 0.0204 | 0.9947 | 0.9947 |
| 0.0076 | 7.0 | 1330 | 0.0175 | 0.9961 | 0.9960 |
| 0.0098 | 8.0 | 1520 | 0.0115 | 0.9974 | 0.9974 |
| 0.0062 | 9.0 | 1710 | 0.0133 | 0.9960 | 0.9960 |
| 0.0012 | 10.0 | 1900 | 0.0126 | 0.9960 | 0.9960 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.14.0.dev20221111
- Datasets 2.8.0
- Tokenizers 0.12.1
|
MattStammers/appo-atari-asteroids
|
MattStammers
| 2023-09-22T17:11:19Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T17:11:13Z |
---
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: atari_asteroid
type: atari_asteroid
metrics:
- type: mean_reward
value: 1388.00 +/- 437.35
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **atari_asteroid** 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 MattStammers/appo-atari-asteroids
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_asteroid --train_dir=./train_dir --experiment=appo-atari-asteroids
```
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 sf_examples.atari.train_atari --algo=APPO --env=atari_asteroid --train_dir=./train_dir --experiment=appo-atari-asteroids --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.
|
Venkatesh4342/distilbert-helpdesk-sentence-sentiment
|
Venkatesh4342
| 2023-09-22T17:05:07Z | 129 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T17:04:36Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-helpdesk-sentence-sentiment
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-helpdesk-sentence-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: 0.1746
- Accuracy: 0.9697
- F1: 0.9697
## 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: 2
- 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 | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.05 | 100 | 0.3796 | 0.8636 | 0.8604 |
| No log | 2.11 | 200 | 0.1258 | 0.9697 | 0.9697 |
| No log | 3.16 | 300 | 0.1814 | 0.9697 | 0.9697 |
| 0.1951 | 4.21 | 400 | 0.1746 | 0.9697 | 0.9697 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/asari_nanami_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T16:43:35Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/asari_nanami_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T16:29:14Z |
---
license: mit
datasets:
- CyberHarem/asari_nanami_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of asari_nanami_idolmastercinderellagirls
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 2880, you need to download `2880/asari_nanami_idolmastercinderellagirls.pt` as the embedding and `2880/asari_nanami_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 2880**, with the score of 0.955. The trigger words are:
1. `asari_nanami_idolmastercinderellagirls`
2. `long_hair, blue_hair, hair_ornament, blue_eyes, bangs, fish_hair_ornament, blush, open_mouth, smile, hair_rings, teeth, :d, breasts, upper_teeth_only`
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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 7200 | 0.938 | [Download](7200/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/pattern_10.png) |  |  | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6720 | 0.934 | [Download](6720/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/pattern_10.png) |  |  | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6240 | 0.939 | [Download](6240/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6240/previews/pattern_10.png) |  |  | [<NSFW, click to see>](6240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6240/previews/nude.png) | [<NSFW, click to see>](6240/previews/nude2.png) |  |  |
| 5760 | 0.918 | [Download](5760/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/pattern_10.png) |  |  | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5280 | 0.911 | [Download](5280/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/pattern_10.png) |  |  | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4800 | 0.928 | [Download](4800/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/pattern_10.png) |  |  | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4320 | 0.931 | [Download](4320/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4320/previews/pattern_10.png) |  |  | [<NSFW, click to see>](4320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4320/previews/nude.png) | [<NSFW, click to see>](4320/previews/nude2.png) |  |  |
| 3840 | 0.918 | [Download](3840/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/pattern_10.png) |  |  | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| 3360 | 0.911 | [Download](3360/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/pattern_10.png) |  |  | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| **2880** | **0.955** | [**Download**](2880/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2880/previews/pattern_10.png) |  |  | [<NSFW, click to see>](2880/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2880/previews/nude.png) | [<NSFW, click to see>](2880/previews/nude2.png) |  |  |
| 2400 | 0.919 | [Download](2400/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/pattern_10.png) |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1920 | 0.897 | [Download](1920/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/pattern_10.png) |  |  | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1440 | 0.905 | [Download](1440/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1440/previews/pattern_10.png) |  |  | [<NSFW, click to see>](1440/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1440/previews/nude.png) | [<NSFW, click to see>](1440/previews/nude2.png) |  |  |
| 960 | 0.763 | [Download](960/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](960/previews/pattern_10.png) |  |  | [<NSFW, click to see>](960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](960/previews/nude.png) | [<NSFW, click to see>](960/previews/nude2.png) |  |  |
| 480 | 0.691 | [Download](480/asari_nanami_idolmastercinderellagirls.zip) |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](480/previews/pattern_10.png) |  |  | [<NSFW, click to see>](480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](480/previews/nude.png) | [<NSFW, click to see>](480/previews/nude2.png) |  |  |
|
alexdbz/bert-base-peft-Lora-abstracts-6epochs
|
alexdbz
| 2023-09-22T16:40:42Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-08-31T17:41:31Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
redstonehero/amireal_v4_fixed_vae
|
redstonehero
| 2023-09-22T16:37:35Z | 109 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-22T16:27:49Z |
---
license: creativeml-openrail-m
library_name: diffusers
---
|
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_subgraphs_gates
|
jordyvl
| 2023-09-22T16:30:26Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"text-classification",
"generated_from_trainer",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-22T14:06:12Z |
---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_subgraphs_gates
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. -->
# EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-22_subgraphs_gates
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0995
- Accuracy: 0.705
- Exit 0 Accuracy: 0.065
- Exit 1 Accuracy: 0.0575
- Exit 2 Accuracy: 0.065
- Exit 3 Accuracy: 0.07
- Exit 4 Accuracy: 0.1575
## 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: 20
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:|
| No log | 0.9 | 3 | 2.7455 | 0.0975 | 0.0625 | 0.0625 | 0.0875 | 0.0625 | 0.0625 |
| No log | 1.9 | 6 | 2.6867 | 0.1475 | 0.06 | 0.0625 | 0.0875 | 0.0625 | 0.0625 |
| No log | 2.9 | 9 | 2.6527 | 0.18 | 0.0475 | 0.0575 | 0.09 | 0.0625 | 0.0625 |
| No log | 3.9 | 12 | 2.6188 | 0.1975 | 0.035 | 0.0525 | 0.095 | 0.0625 | 0.0625 |
| No log | 4.9 | 15 | 2.5827 | 0.22 | 0.035 | 0.05 | 0.0875 | 0.0625 | 0.0625 |
| No log | 5.9 | 18 | 2.6265 | 0.1725 | 0.0475 | 0.0375 | 0.0775 | 0.0625 | 0.0825 |
| No log | 6.9 | 21 | 2.5771 | 0.23 | 0.0525 | 0.0375 | 0.0775 | 0.0625 | 0.0975 |
| No log | 7.9 | 24 | 2.4865 | 0.2675 | 0.055 | 0.0375 | 0.0675 | 0.0625 | 0.08 |
| No log | 8.9 | 27 | 2.4184 | 0.25 | 0.0475 | 0.04 | 0.0625 | 0.0625 | 0.0775 |
| No log | 9.9 | 30 | 2.3451 | 0.28 | 0.06 | 0.045 | 0.0625 | 0.0625 | 0.085 |
| No log | 10.9 | 33 | 2.3027 | 0.3175 | 0.0675 | 0.045 | 0.0625 | 0.0625 | 0.0775 |
| No log | 11.9 | 36 | 2.2168 | 0.3225 | 0.07 | 0.045 | 0.0625 | 0.0625 | 0.0775 |
| No log | 12.9 | 39 | 2.1698 | 0.365 | 0.07 | 0.045 | 0.0625 | 0.0625 | 0.085 |
| No log | 13.9 | 42 | 2.0647 | 0.4125 | 0.065 | 0.045 | 0.0625 | 0.0625 | 0.0875 |
| No log | 14.9 | 45 | 2.0370 | 0.4125 | 0.0675 | 0.0475 | 0.0625 | 0.06 | 0.09 |
| No log | 15.9 | 48 | 1.9523 | 0.4675 | 0.065 | 0.0475 | 0.0625 | 0.0575 | 0.0975 |
| No log | 16.9 | 51 | 1.8758 | 0.4925 | 0.0675 | 0.05 | 0.0625 | 0.055 | 0.1075 |
| No log | 17.9 | 54 | 1.7940 | 0.52 | 0.0675 | 0.05 | 0.0625 | 0.0525 | 0.0975 |
| No log | 18.9 | 57 | 1.7417 | 0.5125 | 0.0675 | 0.05 | 0.0625 | 0.0525 | 0.125 |
| No log | 19.9 | 60 | 1.6789 | 0.565 | 0.0675 | 0.05 | 0.0625 | 0.055 | 0.1325 |
| No log | 20.9 | 63 | 1.6016 | 0.5825 | 0.0675 | 0.05 | 0.0625 | 0.0575 | 0.1525 |
| No log | 21.9 | 66 | 1.5649 | 0.5775 | 0.065 | 0.05 | 0.0625 | 0.07 | 0.155 |
| No log | 22.9 | 69 | 1.5164 | 0.6075 | 0.065 | 0.05 | 0.0625 | 0.0775 | 0.155 |
| No log | 23.9 | 72 | 1.4614 | 0.6225 | 0.065 | 0.05 | 0.0625 | 0.085 | 0.1475 |
| No log | 24.9 | 75 | 1.4301 | 0.62 | 0.065 | 0.05 | 0.0625 | 0.085 | 0.16 |
| No log | 25.9 | 78 | 1.3935 | 0.645 | 0.065 | 0.0525 | 0.065 | 0.0775 | 0.1425 |
| No log | 26.9 | 81 | 1.3777 | 0.64 | 0.065 | 0.0525 | 0.065 | 0.08 | 0.1625 |
| No log | 27.9 | 84 | 1.3301 | 0.6525 | 0.065 | 0.0525 | 0.065 | 0.0825 | 0.16 |
| No log | 28.9 | 87 | 1.3064 | 0.6775 | 0.065 | 0.0525 | 0.065 | 0.0825 | 0.1625 |
| No log | 29.9 | 90 | 1.2689 | 0.675 | 0.065 | 0.0525 | 0.065 | 0.085 | 0.1625 |
| No log | 30.9 | 93 | 1.2549 | 0.6575 | 0.065 | 0.0525 | 0.065 | 0.075 | 0.175 |
| No log | 31.9 | 96 | 1.2440 | 0.66 | 0.065 | 0.055 | 0.065 | 0.08 | 0.1525 |
| No log | 32.9 | 99 | 1.2250 | 0.685 | 0.065 | 0.055 | 0.065 | 0.09 | 0.1675 |
| No log | 33.9 | 102 | 1.2243 | 0.665 | 0.065 | 0.055 | 0.065 | 0.0775 | 0.155 |
| No log | 34.9 | 105 | 1.1960 | 0.6625 | 0.065 | 0.055 | 0.065 | 0.0825 | 0.1675 |
| No log | 35.9 | 108 | 1.1879 | 0.685 | 0.065 | 0.055 | 0.065 | 0.08 | 0.155 |
| No log | 36.9 | 111 | 1.1710 | 0.6825 | 0.065 | 0.055 | 0.065 | 0.0825 | 0.155 |
| No log | 37.9 | 114 | 1.1739 | 0.6925 | 0.065 | 0.055 | 0.065 | 0.0675 | 0.1525 |
| No log | 38.9 | 117 | 1.1414 | 0.7 | 0.065 | 0.055 | 0.065 | 0.0725 | 0.1475 |
| No log | 39.9 | 120 | 1.1476 | 0.695 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.1525 |
| No log | 40.9 | 123 | 1.1435 | 0.6875 | 0.065 | 0.0575 | 0.065 | 0.0825 | 0.15 |
| No log | 41.9 | 126 | 1.1196 | 0.695 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.165 |
| No log | 42.9 | 129 | 1.1454 | 0.7 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 43.9 | 132 | 1.1133 | 0.7 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.1575 |
| No log | 44.9 | 135 | 1.1205 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.1625 |
| No log | 45.9 | 138 | 1.1188 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.1525 |
| No log | 46.9 | 141 | 1.1076 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 47.9 | 144 | 1.1304 | 0.7075 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 48.9 | 147 | 1.1029 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 49.9 | 150 | 1.0979 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.08 | 0.16 |
| No log | 50.9 | 153 | 1.1081 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.0775 | 0.155 |
| No log | 51.9 | 156 | 1.1023 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.16 |
| No log | 52.9 | 159 | 1.1029 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.16 |
| No log | 53.9 | 162 | 1.1015 | 0.71 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.155 |
| No log | 54.9 | 165 | 1.0968 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.155 |
| No log | 55.9 | 168 | 1.0968 | 0.7125 | 0.065 | 0.0575 | 0.065 | 0.0725 | 0.16 |
| No log | 56.9 | 171 | 1.1006 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.075 | 0.155 |
| No log | 57.9 | 174 | 1.1024 | 0.7025 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
| No log | 58.9 | 177 | 1.1006 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
| No log | 59.9 | 180 | 1.0995 | 0.705 | 0.065 | 0.0575 | 0.065 | 0.07 | 0.1575 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
|
mohammadh128/whisper_small-fa_v02
|
mohammadh128
| 2023-09-22T16:18:48Z | 11 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"fa",
"dataset:mozilla-foundation/common_voice_11_0",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-09T21:33:59Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: whisper_small-fa_v02
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0 fa
type: mozilla-foundation/common_voice_11_0
config: fa
split: test
metrics:
- name: Wer
type: wer
value: 30.9315
language:
- fa
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper_small-fa_v02
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_11_0 fa dataset. We also did data augmentation using audiomentations library.
It achieves the following results on the evaluation set:
- Loss: 0.2291
- Wer: 30.3423
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
You can Find the notebooks [here](https://github.com/mohammadh128/Persian_ASR).
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-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
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Step | Training Loss | Validation Loss | Wer |
|:----:|:-------------:|:---------------:|:-------:|
| 500 | 1.770700 | 0.476709 | 52.29181|
| 1000 | 0.762300 | 0.368512 | 41.83410|
| 1500 | 0.645000 | 0.323680 | 37.57881|
| 2000 | 0.601900 | 0.297370 | 36.43209|
| 2500 | 0.529700 | 0.276422 | 33.52608|
| 3000 | 0.523200 | 0.260825 | 31.94485|
| 3500 | 0.488400 | 0.249957 | 33.11771|
| 4000 | 0.464800 | 0.241462 | 30.34238|
| 4500 | 0.440500 | 0.233215 | 31.04969|
| 5000 | 0.440500 | 0.229116 | 30.73605|
### Framework versions
- Transformers 4.26.0
- Pytorch 2.0.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.3
|
cegy369/sk-squad-falcon-7b
|
cegy369
| 2023-09-22T16:14:34Z | 0 | 3 | null |
[
"falcon-7b-instruct",
"falcon",
"text-generation",
"sk",
"dataset:TUKE-DeutscheTelekom/skquad",
"region:us"
] |
text-generation
| 2023-09-20T17:04:35Z |
---
pipeline_tag: text-generation
datasets:
- TUKE-DeutscheTelekom/skquad
language:
- sk
tags:
- falcon-7b-instruct
- falcon
- text-generation
---
|
luanvuvt/results
|
luanvuvt
| 2023-09-22T16:12:52Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:TinyPixel/Llama-2-7B-bf16-sharded",
"base_model:finetune:TinyPixel/Llama-2-7B-bf16-sharded",
"region:us"
] | null | 2023-09-22T16:12:27Z |
---
base_model: TinyPixel/Llama-2-7B-bf16-sharded
tags:
- generated_from_trainer
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [TinyPixel/Llama-2-7B-bf16-sharded](https://huggingface.co/TinyPixel/Llama-2-7B-bf16-sharded) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 35
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
aramka/arka
|
aramka
| 2023-09-22T16:11:27Z | 0 | 0 |
allennlp
|
[
"allennlp",
"biology",
"question-answering",
"ar",
"dataset:allenai/dolma",
"license:afl-3.0",
"region:us"
] |
question-answering
| 2022-05-24T22:59:55Z |
---
license: afl-3.0
datasets:
- allenai/dolma
language:
- ar
metrics:
- bertscore
library_name: allennlp
pipeline_tag: question-answering
tags:
- biology
---
|
iainmcqueen/output
|
iainmcqueen
| 2023-09-22T16:04:24Z | 30 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-22T15:52:59Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of ctstech dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - iainmcqueen/output
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of ctstech dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
csdc-atl/internlm-chat-20b-GPTQ-Int4
|
csdc-atl
| 2023-09-22T15:57:06Z | 19 | 2 |
transformers
|
[
"transformers",
"safetensors",
"internlm",
"feature-extraction",
"text-generation",
"custom_code",
"license:apache-2.0",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-09-21T17:06:23Z |
---
license: apache-2.0
pipeline_tag: text-generation
---
**InternLM**
<div align="center">
<img src="https://github.com/InternLM/InternLM/assets/22529082/b9788105-8892-4398-8b47-b513a292378e" width="200"/>
<div> </div>
<div align="center">
<b><font size="5">InternLM</font></b>
<sup>
<a href="https://internlm.intern-ai.org.cn/">
<i><font size="4">HOT</font></i>
</a>
</sup>
<div> </div>
</div>
[](https://github.com/internLM/OpenCompass/)
[💻Github Repo](https://github.com/InternLM/InternLM) • [🤔Reporting Issues](https://github.com/InternLM/InternLM/issues/new)
</div>
## Introduction
The Shanghai Artificial Intelligence Laboratory, in collaboration with SenseTime Technology, the Chinese University of Hong Kong, and Fudan University, has officially released the 20 billion parameter pretrained model, InternLM-20B. InternLM-20B was pre-trained on over **2.3T** Tokens containing high-quality English, Chinese, and code data. Additionally, the Chat version has undergone SFT and RLHF training, enabling it to better and more securely meet users' needs.
In terms of model structure, InternLM-20B opted for a deeper architecture, with a depth set at 60 layers. This surpasses the conventional 7B and 13B models that utilize 32 or 40 layers. When parameters are limited, increasing the number of layers can enhance the model's overall capability. Furthermore, compared to InternLM-7B, the pre-training data used for InternLM-20B underwent higher quality cleansing and was supplemented with data rich in knowledge and designed for reinforcing understanding and reasoning capabilities. As a result, it exhibits significant improvements in understanding, reasoning, mathematical, and programming abilities—all of which test the technical proficiency of language models. Overall, InternLM-20B features the following characteristics:
- Outstanding overall performance
- Strong utility invocation capability
- Supports a 16k context length (Through infererence extrapolation)
- Better value alignment.
## Performance Evaluation
On the 5 capability dimensions proposed by OpenCompass, InternLM-20B has achieved excellent results (the bolded scores represent the best performances within the 13B-33B parameter range).
| Capability | Llama-13B | Llama2-13B | Baichuan2-13B | InternLM-20B | Llama-33B | Llama-65B | Llama2-70B |
|----------|-----------|------------|---------------|--------------|-----------|-----------|------------|
| Language | 42.5 | 47 | 47.5 | **55** | 44.6 | 47.1 | 51.6 |
| Knowledge | 58.2 | 58.3 | 48.9 | 60.1 | **64** | 66 | 67.7 |
| Understanding | 45.5 | 50.9 | 58.1 | **67.3** | 50.6 | 54.2 | 60.8 |
| Reasoning | 42.7 | 43.6 | 44.2 | **54.9** | 46.4 | 49.8 | 55 |
| Examination | 37.3 | 45.2 | 51.8 | **62.5** | 47.4 | 49.7 | 57.3 |
| Overall | 43.8 | 47.3 | 49.4 | **59.2** | 48.9 | 51.9 | 57.4 |
The table below compares the performance of mainstream open-source models on some influential and typical datasets.
| | Benchmarks | Llama-13B | Llama2-13B | Baichuan2-13B | InternLM-20B | Llama-33B | Llama-65B | Llama2-70B |
|------|------------------|-----------|------------|---------------|--------------|-----------|-----------|------------|
| Examination | MMLU | 47.73 | 54.99 | 59.55 | **62.05** | 58.73 | 63.71 | 69.75 |
| | C-Eval (val) | 31.83 | 41.4 | **59.01** | 58.8 | 37.47 | 40.36 | 50.13 |
| | AGI-Eval | 22.03 | 30.93 | 37.37 | **44.58** | 33.53 | 33.92 | 40.02 |
| Knowledge | BoolQ | 78.75 | 82.42 | 67 | **87.46** | 84.43 | 86.61 | 87.74 |
| | TriviaQA | 52.47 | 59.36 | 46.61 | 57.26 | **66.24** | 69.79 | 70.71 |
| | NaturalQuestions | 20.17 | 24.85 | 16.32 | 25.15 | **30.89** | 33.41 | 34.16 |
| Understanding | CMRC | 9.26 | 31.59 | 29.85 | **68.78** | 14.17 | 34.73 | 43.74 |
| | CSL | 55 | 58.75 | 63.12 | **65.62** | 57.5 | 59.38 | 60 |
| | RACE (middle) | 53.41 | 63.02 | 68.94 | **86.35** | 64.55 | 72.35 | 81.55 |
| | RACE (high) | 47.63 | 58.86 | 67.18 | **83.28** | 62.61 | 68.01 | 79.93 |
| | XSum | 20.37 | 23.37 | 25.23 | **35.54** | 20.55 | 19.91 | 25.38 |
| Reasoning | WinoGrande | 64.64 | 64.01 | 67.32 | **69.38** | 66.85 | 69.38 | 69.77 |
| | BBH | 37.93 | 45.62 | 48.98 | **52.51** | 49.98 | 58.38 | 64.91 |
| | GSM8K | 20.32 | 29.57 | **52.62** | **52.62** | 42.3 | 54.44 | 63.31 |
| | PIQA | 79.71 | 79.76 | 78.07 | 80.25 | **81.34** | 82.15 | 82.54 |
| Programming | HumanEval | 14.02 | 18.9 | 17.07 | **25.61** | 17.68 | 18.9 | 26.22 |
| | MBPP | 20.6 | 26.8 | 30.8 | **35.6** | 28.4 | 33.6 | 39.6 |
Overall, InternLM-20B comprehensively outperforms open-source models in the 13B parameter range in terms of overall capabilities, and on inference evaluation sets, it approaches or even surpasses the performance of Llama-65B.
## Import from Transformers
To load the InternLM 20B model using Transformers, use the following code:
```python
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-20b", trust_remote_code=True)
>>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-20b", trust_remote_code=True).cuda()
>>> model = model.eval()
>>> output, history = model.chat(tokenizer, "Hello! Today is sunny, it is time to go out")
>>> print(output)
Hello! Today is sunny, and it sounds like a great day to go out an enjoy the weather. What would you like to do?
```
**Limitations:** Although we have made efforts to ensure the safety of the model during the training process and to encourage the model to generate text that complies with ethical and legal requirements, the model may still produce unexpected outputs due to its size and probabilistic generation paradigm. For example, the generated responses may contain biases, discrimination, or other harmful content. Please do not propagate such content. We are not responsible for any consequences resulting from the dissemination of harmful information.
## Open Source License
The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow **free** commercial usage. To apply for a commercial license, please fill in the [application form (English)](https://wj.qq.com/s2/12727483/5dba/)/[申请表（中文）](https://wj.qq.com/s2/12725412/f7c1/). For other questions or collaborations, please contact <[email protected]>.
## 简介
上海人工智能实验室与商汤科技联合香港中文大学和复旦大学正式推出书生·浦语200亿参数模型版本 InternLM-20B ，InternLM-20B 在超过 **2.3T** Tokens 包含高质量英文、中文和代码的数据上进行预训练，其中 Chat 版本还经过了 SFT 和 RLHF 训练，使其能够更好、更安全地满足用户的需求。
InternLM 20B 在模型结构上选择了深结构，层数设定为60层，超过常规7B和13B模型所使用的32层或者40层。在参数受限的情况下，提高层数有利于提高模型的综合能力。此外，相较于InternLM-7B，InternLM-20B使用的预训练数据经过了更高质量的清洗，并补充了高知识密度和用于强化理解与推理能力的训练数据。因此，它在理解能力、推理能力、数学能力、编程能力等考验语言模型技术水平的方面都得到了显著提升。总体而言，InternLM-20B具有以下的特点：
- 优异的综合性能
- 很强的工具调用功能
- 支持16k语境长度（通过推理时外推）
- 更好的价值对齐
## 性能评测
在OpenCompass提出的5个能力维度上，InternLM-20B都取得很好的效果（粗体为13B-33B这个量级范围内，各项最佳成绩）
| 能力维度 | Llama-13B | Llama2-13B | Baichuan2-13B | InternLM-20B | Llama-33B | Llama-65B | Llama2-70B |
|----------|-----------|------------|---------------|--------------|-----------|-----------|------------|
| 语言 | 42.5 | 47 | 47.5 | **55** | 44.6 | 47.1 | 51.6 |
| 知识 | 58.2 | 58.3 | 48.9 | 60.1 | **64** | 66 | 67.7 |
| 理解 | 45.5 | 50.9 | 58.1 | **67.3** | 50.6 | 54.2 | 60.8 |
| 推理 | 42.7 | 43.6 | 44.2 | **54.9** | 46.4 | 49.8 | 55 |
| 学科 | 37.3 | 45.2 | 51.8 | **62.5** | 47.4 | 49.7 | 57.3 |
| 总平均 | 43.8 | 47.3 | 49.4 | **59.2** | 48.9 | 51.9 | 57.4 |
下表展示了在多个经典数据集上 InternLM 20B 与各个主流开源模型的表现
| | 评测集 | Llama-13B | Llama2-13B | Baichuan2-13B | InternLM-20B | Llama-33B | Llama-65B | Llama2-70B |
|------|------------------|-----------|------------|---------------|--------------|-----------|-----------|------------|
| 学科 | MMLU | 47.73 | 54.99 | 59.55 | **62.05** | 58.73 | 63.71 | 69.75 |
| | C-Eval (val) | 31.83 | 41.4 | **59.01** | 58.8 | 37.47 | 40.36 | 50.13 |
| | AGI-Eval | 22.03 | 30.93 | 37.37 | **44.58** | 33.53 | 33.92 | 40.02 |
| 知识 | BoolQ | 78.75 | 82.42 | 67 | **87.46** | 84.43 | 86.61 | 87.74 |
| | TriviaQA | 52.47 | 59.36 | 46.61 | 57.26 | **66.24** | 69.79 | 70.71 |
| | NaturalQuestions | 20.17 | 24.85 | 16.32 | 25.15 | **30.89** | 33.41 | 34.16 |
| 理解 | CMRC | 9.26 | 31.59 | 29.85 | **68.78** | 14.17 | 34.73 | 43.74 |
| | CSL | 55 | 58.75 | 63.12 | **65.62** | 57.5 | 59.38 | 60 |
| | RACE (middle) | 53.41 | 63.02 | 68.94 | **86.35** | 64.55 | 72.35 | 81.55 |
| | RACE (high) | 47.63 | 58.86 | 67.18 | **83.28** | 62.61 | 68.01 | 79.93 |
| | XSum | 20.37 | 23.37 | 25.23 | **35.54** | 20.55 | 19.91 | 25.38 |
| 推理 | WinoGrande | 64.64 | 64.01 | 67.32 | **69.38** | 66.85 | 69.38 | 69.77 |
| | BBH | 37.93 | 45.62 | 48.98 | **52.51** | 49.98 | 58.38 | 64.91 |
| | GSM8K | 20.32 | 29.57 | **52.62** | **52.62** | 42.3 | 54.44 | 63.31 |
| | PIQA | 79.71 | 79.76 | 78.07 | 80.25 | **81.34** | 82.15 | 82.54 |
| 编程 | HumanEval | 14.02 | 18.9 | 17.07 | **25.61** | 17.68 | 18.9 | 26.22 |
| | MBPP | 20.6 | 26.8 | 30.8 | **35.6** | 28.4 | 33.6 | 39.6 |
总体而言，InternLM-20B 在综合能力上全面领先于13B量级的开源模型，同时在推理评测集上能够接近甚至超越Llama-65B的性能。
## 通过 Transformers 加载
通过以下的代码加载 InternLM 20B 模型
```python
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-20b", trust_remote_code=True)
>>> model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-20b", trust_remote_code=True).cuda()
>>> model = model.eval()
>>> output, history = model.chat(tokenizer, "你好呀！今天天气真好")
>>> print(output)
你好！是的，今天的天气非常晴朗，非常适合户外活动。
```
**局限性：** 尽管在训练过程中我们非常注重模型的安全性，尽力促使模型输出符合伦理和法律要求的文本，但受限于模型大小以及概率生成范式，模型可能会产生各种不符合预期的输出，例如回复内容包含偏见、歧视等有害内容，请勿传播这些内容。由于传播不良信息导致的任何后果，本项目不承担责任。
## 开源许可证
本仓库的代码依照 Apache-2.0 协议开源。模型权重对学术研究完全开放，也可申请免费的商业使用授权（[申请表](https://wj.qq.com/s2/12725412/f7c1/)）。其他问题与合作请联系 <[email protected]>。
|
yumujiu/llama2-qlora-finetunined-french
|
yumujiu
| 2023-09-22T15:55:46Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-22T15:55:39Z |
---
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
|
CyberHarem/mizuno_midori_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T15:41:46Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/mizuno_midori_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T15:29:46Z |
---
license: mit
datasets:
- CyberHarem/mizuno_midori_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of mizuno_midori_idolmastercinderellagirls
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 4760, you need to download `4760/mizuno_midori_idolmastercinderellagirls.pt` as the embedding and `4760/mizuno_midori_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.915. The trigger words are:
1. `mizuno_midori_idolmastercinderellagirls`
2. `black_hair, long_hair, ponytail, brown_eyes, blush, 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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.873 | [Download](5100/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](5100/previews/pattern_6.png) |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.915** | [**Download**](4760/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4760/previews/pattern_6.png) |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.908 | [Download](4420/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4420/previews/pattern_6.png) |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.913 | [Download](4080/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](4080/previews/pattern_6.png) |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.854 | [Download](3740/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3740/previews/pattern_6.png) |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.867 | [Download](3400/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3400/previews/pattern_6.png) |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.871 | [Download](3060/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](3060/previews/pattern_6.png) |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.845 | [Download](2720/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2720/previews/pattern_6.png) |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.856 | [Download](2380/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2380/previews/pattern_6.png) |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.863 | [Download](2040/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](2040/previews/pattern_6.png) |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.829 | [Download](1700/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1700/previews/pattern_6.png) |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.831 | [Download](1360/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1360/previews/pattern_6.png) |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.815 | [Download](1020/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](1020/previews/pattern_6.png) |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.768 | [Download](680/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](680/previews/pattern_6.png) |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.561 | [Download](340/mizuno_midori_idolmastercinderellagirls.zip) |  |  |  |  |  | [<NSFW, click to see>](340/previews/pattern_6.png) |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
LarryAIDraw/saigyouji_yuyuko_touhou
|
LarryAIDraw
| 2023-09-22T15:25:09Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-13T16:05:36Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/131028/saigyoujiyuyuko-touhou
|
tombm/bert-base-uncased-finetuned-cola
|
tombm
| 2023-09-22T15:21:45Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"generated_from_trainer",
"dataset:glue",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2023-09-22T12:36:41Z |
---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-finetuned-cola
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-cola
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5931
- Matthews Correlation: 0.5598
## 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: 128
- 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 | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5206 | 1.0 | 535 | 0.4503 | 0.4984 |
| 0.347 | 2.0 | 1070 | 0.4558 | 0.5816 |
| 0.2461 | 3.0 | 1605 | 0.5931 | 0.5598 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
fgiannini69/ppo-Huggy
|
fgiannini69
| 2023-09-22T15:09:47Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-22T15:09:42Z |
---
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: fgiannini69/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
VuongQuoc/checkpoints_2_microsoft_deberta_21_9
|
VuongQuoc
| 2023-09-22T15:07:19Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"multiple-choice",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-09-21T04:50:45Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: checkpoints_2_microsoft_deberta_21_9
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. -->
# checkpoints_2_microsoft_deberta_21_9
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8635
- Map@3: 0.8558
- Accuracy: 0.76
## 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: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
| 0.6215 | 0.15 | 300 | 0.6511 | 0.8592 | 0.76 |
| 0.5953 | 0.3 | 600 | 0.6929 | 0.8533 | 0.765 |
| 0.5332 | 0.45 | 900 | 0.6665 | 0.8525 | 0.76 |
| 0.587 | 0.6 | 1200 | 0.6638 | 0.855 | 0.775 |
| 0.5626 | 0.75 | 1500 | 0.6476 | 0.8692 | 0.78 |
| 0.6712 | 0.9 | 1800 | 0.6499 | 0.8700 | 0.785 |
| 0.2181 | 1.05 | 2100 | 0.8619 | 0.8417 | 0.75 |
| 0.2024 | 1.2 | 2400 | 0.8607 | 0.8467 | 0.75 |
| 0.2571 | 1.35 | 2700 | 0.8282 | 0.8483 | 0.75 |
| 0.2407 | 1.5 | 3000 | 0.8297 | 0.8558 | 0.765 |
| 0.2282 | 1.65 | 3300 | 0.8635 | 0.8558 | 0.76 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
ShivamMangale/XLM-Roberta-base-finetuned-squad-only-es-12-epoch
|
ShivamMangale
| 2023-09-22T15:06:43Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-22T14:26:41Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: XLM-Roberta-base-finetuned-squad-only-es-12-epoch
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. -->
# XLM-Roberta-base-finetuned-squad-only-es-12-epoch
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the squad 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: 12
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
zyongqing/q-FrozenLake-v1-4x4-noSlippery
|
zyongqing
| 2023-09-22T15:04:32Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-22T15:04:31Z |
---
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="zyongqing/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"])
```
|
necoarc/spatchgan-model
|
necoarc
| 2023-09-22T15:02:45Z | 0 | 1 | null |
[
"arxiv:2103.16219",
"license:bsd-3-clause",
"region:us"
] | null | 2023-09-22T14:05:05Z |
---
license: bsd-3-clause
---
Pretrained models for SPatchGAN (ICCV 2021)
[<img src='https://img.shields.io/badge/arXiv-2103.16219-blue'>](https://arxiv.org/abs/2103.16219)
[<img src='https://img.shields.io/badge/code-github-red'>](https://github.com/NetEase-GameAI/SPatchGAN)
|
CyberHarem/furusawa_yoriko_idolmastercinderellagirls
|
CyberHarem
| 2023-09-22T14:51:35Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/furusawa_yoriko_idolmastercinderellagirls",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-22T14:42:20Z |
---
license: mit
datasets:
- CyberHarem/furusawa_yoriko_idolmastercinderellagirls
pipeline_tag: text-to-image
tags:
- art
---
# Lora of furusawa_yoriko_idolmastercinderellagirls
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 3400, you need to download `3400/furusawa_yoriko_idolmastercinderellagirls.pt` as the embedding and `3400/furusawa_yoriko_idolmastercinderellagirls.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 3400**, with the score of 0.965. The trigger words are:
1. `furusawa_yoriko_idolmastercinderellagirls`
2. `blue_eyes, brown_hair, long_hair, glasses, mole, mole_under_eye, smile, hairband, 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 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:----------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.954 | [Download](5100/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](5100/previews/pattern_3.png) |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.925 | [Download](4760/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4760/previews/pattern_3.png) |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.943 | [Download](4420/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4420/previews/pattern_3.png) |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.945 | [Download](4080/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](4080/previews/pattern_3.png) |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.940 | [Download](3740/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3740/previews/pattern_3.png) |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| **3400** | **0.965** | [**Download**](3400/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3400/previews/pattern_3.png) |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.927 | [Download](3060/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](3060/previews/pattern_3.png) |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.922 | [Download](2720/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2720/previews/pattern_3.png) |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.895 | [Download](2380/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2380/previews/pattern_3.png) |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.907 | [Download](2040/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](2040/previews/pattern_3.png) |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.914 | [Download](1700/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1700/previews/pattern_3.png) |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.920 | [Download](1360/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1360/previews/pattern_3.png) |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.859 | [Download](1020/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](1020/previews/pattern_3.png) |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.810 | [Download](680/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](680/previews/pattern_3.png) |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.653 | [Download](340/furusawa_yoriko_idolmastercinderellagirls.zip) |  |  | [<NSFW, click to see>](340/previews/pattern_3.png) |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.