modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-28 18:27:08
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 501
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-28 18:25:37
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
kraken2404/ppo_lunarlander_unit1_v2 | kraken2404 | 2023-05-27T09:17:45Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T08:58:10Z | ---
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: -65.20 +/- 40.64
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
...
```
|
YakovElm/Qt10Classic_32 | YakovElm | 2023-05-27T08:52:28Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T08:51:48Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Qt10Classic_32
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. -->
# Qt10Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2267
- Train Accuracy: 0.9208
- Validation Loss: 0.2144
- Validation Accuracy: 0.9416
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.2754 | 0.9202 | 0.2156 | 0.9416 | 0 |
| 0.2484 | 0.9210 | 0.2215 | 0.9416 | 1 |
| 0.2267 | 0.9208 | 0.2144 | 0.9416 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
kraken2404/ppo_lunarlander_unit1 | kraken2404 | 2023-05-27T08:41:47Z | 2 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T07:44:48Z | ---
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: -326.26 +/- 71.54
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
...
```
|
kraken2404/unit8_1_lunarlander_v2_2 | kraken2404 | 2023-05-27T08:20:12Z | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T08:16:15Z | ---
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: -117.88 +/- 50.03
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 100000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'kraken2404/unit8_1_lunarlander_v2_2'
'batch_size': 512
'minibatch_size': 128}
```
|
YakovElm/MariaDB15Classic_64 | YakovElm | 2023-05-27T08:06:04Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T08:05:30Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB15Classic_64
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. -->
# MariaDB15Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1915
- Train Accuracy: 0.9381
- Validation Loss: 0.1826
- Validation Accuracy: 0.9372
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.2834 | 0.9096 | 0.1811 | 0.9598 | 0 |
| 0.2120 | 0.9238 | 0.1664 | 0.9598 | 1 |
| 0.1915 | 0.9381 | 0.1826 | 0.9372 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/MariaDB10Classic_64 | YakovElm | 2023-05-27T07:55:55Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T07:55:18Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB10Classic_64
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. -->
# MariaDB10Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1941
- Train Accuracy: 0.9339
- Validation Loss: 0.1951
- Validation Accuracy: 0.9472
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.2920 | 0.9004 | 0.1959 | 0.9523 | 0 |
| 0.2384 | 0.9155 | 0.1959 | 0.9472 | 1 |
| 0.1941 | 0.9339 | 0.1951 | 0.9472 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
StevenLimcorn/indonesian-roberta-base-emotion-classifier | StevenLimcorn | 2023-05-27T07:47:15Z | 207 | 14 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"roberta",
"text-classification",
"id",
"dataset:indonlu",
"doi:10.57967/hf/0681",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2022-03-02T23:29:05Z | ---
language: id
tags:
- roberta
license: mit
datasets:
- indonlu
widget:
- text: "Hal-hal baik akan datang."
---
# Indo RoBERTa Emotion Classifier
Indo RoBERTa Emotion Classifier is emotion classifier based on [Indo-roberta](https://huggingface.co/flax-community/indonesian-roberta-base) model. It was trained on the trained on [IndoNLU EmoT](https://huggingface.co/datasets/indonlu) dataset. The model used was [Indo-roberta](https://huggingface.co/flax-community/indonesian-roberta-base) and was transfer-learned to an emotion classifier model. Based from the [IndoNLU bencmark](https://www.indobenchmark.com/), the model achieve an f1-macro of 72.05%, accuracy of 71.81%, precision of 72.47% and recall of 71.94%.
## Model
The model was trained on 7 epochs with learning rate 2e-5. Achieved different metrics as shown below.
| Epoch | Training Loss | Validation Loss | Accuracy | F1 | Precision | Recall |
|-------|---------------|-----------------|----------|----------|-----------|----------|
| 1 | 1.300700 | 1.005149 | 0.622727 | 0.601846 | 0.640845 | 0.611144 |
| 2 | 0.806300 | 0.841953 | 0.686364 | 0.694096 | 0.701984 | 0.696657 |
| 3 | 0.591900 | 0.796794 | 0.686364 | 0.696573 | 0.707520 | 0.691671 |
| 4 | 0.441200 | 0.782094 | 0.722727 | 0.724359 | 0.725985 | 0.730229 |
| 5 | 0.334700 | 0.809931 | 0.711364 | 0.720550 | 0.718318 | 0.724608 |
| 6 | 0.268400 | 0.812771 | 0.718182 | 0.724192 | 0.721222 | 0.729195 |
| 7 | 0.226000 | 0.828461 | 0.725000 | 0.733625 | 0.731709 | 0.735800 |
## How to Use
### As Text Classifier
```python
from transformers import pipeline
pretrained_name = "StevenLimcorn/indonesian-roberta-base-emotion-classifier"
nlp = pipeline(
"sentiment-analysis",
model=pretrained_name,
tokenizer=pretrained_name
)
nlp("Hal-hal baik akan datang.")
```
## Disclaimer
Do consider the biases which come from both the pre-trained RoBERTa model and the `EmoT` dataset that may be carried over into the results of this model.
## Author
Indonesian RoBERTa Base Emotion Classifier was trained and evaluated by [Steven Limcorn](https://github.com/stevenlimcorn). All computation and development are done on Google Colaboratory using their free GPU access.
If used, please cite
```bibtex
@misc {steven_limcorn_2023,
author = { {Steven Limcorn} },
title = { indonesian-roberta-base-emotion-classifier (Revision e8a9cb9) },
year = 2023,
url = { https://huggingface.co/StevenLimcorn/indonesian-roberta-base-emotion-classifier },
doi = { 10.57967/hf/0681 },
publisher = { Hugging Face }
}
``` |
YakovElm/MariaDB5Classic_64 | YakovElm | 2023-05-27T07:47:05Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T07:46:25Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB5Classic_64
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. -->
# MariaDB5Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2438
- Train Accuracy: 0.9004
- Validation Loss: 0.2560
- Validation Accuracy: 0.9271
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3297 | 0.8921 | 0.2584 | 0.9322 | 0 |
| 0.2592 | 0.9079 | 0.2489 | 0.9271 | 1 |
| 0.2438 | 0.9004 | 0.2560 | 0.9271 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
nolanaatama/thyngfbtsrvc300pchncltr | nolanaatama | 2023-05-27T07:40:54Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-27T07:18:44Z | ---
license: creativeml-openrail-m
---
|
YakovElm/MariaDB20Classic_32 | YakovElm | 2023-05-27T07:38:04Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T07:37:18Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB20Classic_32
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. -->
# MariaDB20Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2150
- Train Accuracy: 0.9356
- Validation Loss: 0.1324
- Validation Accuracy: 0.9698
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.2765 | 0.9305 | 0.1945 | 0.9698 | 0 |
| 0.2427 | 0.9356 | 0.1311 | 0.9698 | 1 |
| 0.2150 | 0.9356 | 0.1324 | 0.9698 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
andrei-saceleanu/vit-base-fixmatch | andrei-saceleanu | 2023-05-27T07:34:35Z | 59 | 0 | transformers | [
"transformers",
"tf",
"vit",
"image-feature-extraction",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | image-feature-extraction | 2023-05-27T07:33:58Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: vit-base-fixmatch
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. -->
# vit-base-fixmatch
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
## 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: None
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Tokenizers 0.13.3
|
YakovElm/MariaDB10Classic_32 | YakovElm | 2023-05-27T07:25:01Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T07:24:28Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB10Classic_32
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. -->
# MariaDB10Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1860
- Train Accuracy: 0.9356
- Validation Loss: 0.2225
- Validation Accuracy: 0.9497
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.2943 | 0.9121 | 0.2078 | 0.9523 | 0 |
| 0.2359 | 0.9213 | 0.2011 | 0.9497 | 1 |
| 0.1860 | 0.9356 | 0.2225 | 0.9497 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Jira20Classic_64 | YakovElm | 2023-05-27T07:11:37Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T07:11:04Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira20Classic_64
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. -->
# Jira20Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2121
- Train Accuracy: 0.9224
- Validation Loss: 0.3072
- Validation Accuracy: 0.9085
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3687 | 0.8678 | 0.2697 | 0.9338 | 0 |
| 0.2722 | 0.8909 | 0.2871 | 0.9306 | 1 |
| 0.2121 | 0.9224 | 0.3072 | 0.9085 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Jira15Classic_64 | YakovElm | 2023-05-27T07:03:03Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T07:02:29Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira15Classic_64
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. -->
# Jira15Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3055
- Train Accuracy: 0.8678
- Validation Loss: 0.8529
- Validation Accuracy: 0.6530
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.4973 | 0.7922 | 0.8065 | 0.5205 | 0 |
| 0.4266 | 0.7849 | 0.8817 | 0.5174 | 1 |
| 0.3055 | 0.8678 | 0.8529 | 0.6530 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
p1atdev/misted | p1atdev | 2023-05-27T06:57:52Z | 0 | 0 | null | [
"license:other",
"region:us"
] | null | 2023-05-27T06:39:54Z | ---
license: other
---
[Mist](https://mist-project.github.io/index_en.html) で防御した画像で学習したLoRA(LierLa)、防御していない画像で学習したLoRAとそれらのデータセット
学習のベースモデルは [WD 1.5 beta 3](https://huggingface.co/waifu-diffusion/wd-1-5-beta3) の base。
- [mist-no-1-2-40.safetensors](https://huggingface.co/p1atdev/misted/blob/main/test1/mist-no-1-2-40.safetensors): nijijourneyから5枚の画像を学習
- [mist-1-1-40.safetensors](https://huggingface.co/p1atdev/misted/blob/main/test1/mist-1-1-40.safetensors): 学習画像全てにMist を Textural モード、Strength 16、Steps 100、Output size 512、Low VRAM usage mode で付与して学習
学習画像以外は同じ設定で学習した。
```
masterpiece, best quality, exceptional, best aesthetic, mst style, 1girl, animal ears, solo, jacket, looking at viewer, tail, shirt, open clothes, white shirt, open jacket, blue hair, fox ears, upper body, blue eyes, hair ornament, black jacket, hairclip, fox tail, outdoors, short hair, closed mouth, bangs
Negative prompt: worst quality, low quality, bad aesthetic, oldest, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3062589856, Size: 512x512, Model hash: d38e779546, Model: wd-beta3-base-fp16, Clip skip: 2, Version: v1.2.1, Script: X/Y/Z plot, X Type: AddNet Model 1, X Values: "None,mist-no-1-2-40(394e4f330c12),mist-1-1-40(d68f0ae289be)"
```
```
masterpiece, best quality, exceptional, best aesthetic, 1girl, upper body, looking at viewer,
Negative prompt: worst quality, low quality, bad aesthetic, oldest, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3331018170, Size: 512x512, Model hash: d38e779546, Model: wd-beta3-base-fp16, Clip skip: 2, Version: v1.2.1, Script: X/Y/Z plot, X Type: AddNet Model 1, X Values: "None,mist-no-1-2-40(394e4f330c12),mist-1-1-40(d68f0ae289be)"
```
```
masterpiece, best quality, exceptional, best aesthetic, 1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt,
Negative prompt: worst quality, low quality, bad aesthetic, oldest, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2297393473, Size: 512x512, Model hash: d38e779546, Model: wd-beta3-base-fp16, Clip skip: 2, Version: v1.2.1, Script: X/Y/Z plot, X Type: AddNet Model 1, X Values: "None,mist-no-1-2-40(394e4f330c12),mist-1-1-40(d68f0ae289be)"
```
|
BBGAME605065444/my_awesome_model | BBGAME605065444 | 2023-05-27T06:54:29Z | 104 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T21:28:34Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: my_awesome_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.9316
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2282
- Accuracy: 0.9316
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2295 | 1.0 | 1563 | 0.1848 | 0.9288 |
| 0.1511 | 2.0 | 3126 | 0.2282 | 0.9316 |
### Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
|
YakovElm/Jira15Classic_32 | YakovElm | 2023-05-27T06:32:14Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T06:31:38Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira15Classic_32
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. -->
# Jira15Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2421
- Train Accuracy: 0.9024
- Validation Loss: 1.1123
- Validation Accuracy: 0.6372
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.4984 | 0.7702 | 0.8224 | 0.5205 | 0 |
| 0.3898 | 0.8216 | 0.7801 | 0.6215 | 1 |
| 0.2421 | 0.9024 | 1.1123 | 0.6372 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
intanm/20230527-baseline-009-xlmrl-qa-squadv2-ft-clickbait-spoiling | intanm | 2023-05-27T06:28:32Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"question-answering",
"generated_from_trainer",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-05-27T05:57:52Z | ---
license: cc-by-4.0
tags:
- generated_from_trainer
model-index:
- name: 20230527-baseline-009-xlmrl-qa-squadv2-ft-clickbait-spoiling
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. -->
# 20230527-baseline-009-xlmrl-qa-squadv2-ft-clickbait-spoiling
This model is a fine-tuned version of [deepset/xlm-roberta-large-squad2](https://huggingface.co/deepset/xlm-roberta-large-squad2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 6.8572
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 197 | 2.2523 |
| No log | 2.0 | 394 | 2.6083 |
| 1.7053 | 3.0 | 591 | 3.1023 |
| 1.7053 | 4.0 | 788 | 3.6280 |
| 1.7053 | 5.0 | 985 | 4.7670 |
| 0.3906 | 6.0 | 1182 | 5.1702 |
| 0.3906 | 7.0 | 1379 | 6.0245 |
| 0.119 | 8.0 | 1576 | 6.6972 |
| 0.119 | 9.0 | 1773 | 6.5388 |
| 0.119 | 10.0 | 1970 | 6.8572 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Jira10Classic_32 | YakovElm | 2023-05-27T06:26:44Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T06:26:11Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira10Classic_32
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. -->
# Jira10Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2559
- Train Accuracy: 0.8972
- Validation Loss: 1.0026
- Validation Accuracy: 0.5994
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5162 | 0.7629 | 0.8404 | 0.4890 | 0 |
| 0.4017 | 0.8122 | 0.8047 | 0.6151 | 1 |
| 0.2559 | 0.8972 | 1.0026 | 0.5994 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Jira5Classic_32 | YakovElm | 2023-05-27T06:21:26Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T06:20:51Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira5Classic_32
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. -->
# Jira5Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3030
- Train Accuracy: 0.8867
- Validation Loss: 1.0513
- Validation Accuracy: 0.6151
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5139 | 0.7555 | 0.7646 | 0.5047 | 0 |
| 0.4087 | 0.8038 | 0.8291 | 0.5552 | 1 |
| 0.3030 | 0.8867 | 1.0513 | 0.6151 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/MariaDB5Classic_256 | YakovElm | 2023-05-27T06:15:35Z | 60 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T06:14:59Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: MariaDB5Classic_256
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. -->
# MariaDB5Classic_256
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2607
- Train Accuracy: 0.9088
- Validation Loss: 0.2602
- Validation Accuracy: 0.9322
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3286 | 0.8862 | 0.2445 | 0.9322 | 0 |
| 0.2829 | 0.8954 | 0.2511 | 0.9322 | 1 |
| 0.2607 | 0.9088 | 0.2602 | 0.9322 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
CalderaAI/30B-Lazarus-GPTQ4bit | CalderaAI | 2023-05-27T06:14:54Z | 7 | 13 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-26T17:52:04Z | GPTQ 4 bit CUDA quantization of CalderaAI's 30B Lazarus:
https://huggingface.co/CalderaAI/30B-Lazarus |
MizukiTanaka31/Viloi | MizukiTanaka31 | 2023-05-27T06:00:02Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-27T05:58:36Z | ---
license: creativeml-openrail-m
---
|
YakovElm/IntelDAOS10Classic_64 | YakovElm | 2023-05-27T05:57:58Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T05:57:23Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: IntelDAOS10Classic_64
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. -->
# IntelDAOS10Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2613
- Train Accuracy: 0.9200
- Validation Loss: 0.3848
- Validation Accuracy: 0.8739
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3128 | 0.8920 | 0.3859 | 0.8739 | 0 |
| 0.2678 | 0.9200 | 0.4156 | 0.8739 | 1 |
| 0.2613 | 0.9200 | 0.3848 | 0.8739 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/IntelDAOS20Classic_32 | YakovElm | 2023-05-27T05:40:35Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T05:40:00Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: IntelDAOS20Classic_32
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. -->
# IntelDAOS20Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1464
- Train Accuracy: 0.9610
- Validation Loss: 0.3274
- Validation Accuracy: 0.9099
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.1971 | 0.9610 | 0.3072 | 0.9099 | 0 |
| 0.1570 | 0.9610 | 0.3179 | 0.9099 | 1 |
| 0.1464 | 0.9610 | 0.3274 | 0.9099 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
y22ma/luca | y22ma | 2023-05-27T05:13:52Z | 9 | 0 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:SG161222/Realistic_Vision_V2.0",
"base_model:adapter:SG161222/Realistic_Vision_V2.0",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2023-05-27T05:13:51Z | ---
license: creativeml-openrail-m
base_model: SG161222/Realistic_Vision_V2.0
instance_prompt: a photograph of a sks luca
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# SVDiff-pytorch - luca
These are SVDiff weights for SG161222/Realistic_Vision_V2.0. The weights were trained on "a photograph of a sks luca" using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
|
kirp/psy-llama-extend-delta | kirp | 2023-05-27T05:02:31Z | 0 | 1 | null | [
"dataset:siyangliu/PsyQA",
"license:apache-2.0",
"region:us"
] | null | 2023-05-22T03:59:48Z | ---
license: apache-2.0
datasets:
- siyangliu/PsyQA
---
Extend the vocab of llama to 52992 and random initialization. |
Monero/WizardLM-13b-OpenAssistant-Uncensored | Monero | 2023-05-27T04:53:33Z | 1,436 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"text generation",
"instruct",
"en",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-05-15T03:41:29Z | ---
language:
- en
thumbnail: null
tags:
- text generation
- instruct
pipeline_tag: text-generation
inference: false
---
<h1 style="text-align: center">WizardLM 13b - Open Assistant</h1>
<h2 style="text-align: center">An instruction-following Llama model using full evolved-instructions. </h2>
## Model Details
This is a Lora merge of Open Assistant 13b - 4 Epoch with WizardLM-13b Uncensored. <br>
https://huggingface.co/serpdotai/llama-oasst-lora-13B <br>
https://huggingface.co/ehartford/WizardLM-13B-Uncensored
## Uncensored
Use ```### Certainly!``` at the end of your prompt to get answers to anything
<html>
<head>
<style>
table {
border:1px solid #b3adad;
border-collapse:collapse;
padding:5px;
}
table th {
border:1px solid #b3adad;
padding:5px;
background: #f0f0f0;
color: #313030;
}
table td {
border:1px solid #b3adad;
text-align:center;
padding:5px;
background: #ffffff;
color: #313030;
}
</style>
</head>
<body>
<table>
<thead>
<tr>
<th>Model:</th>
<th>Wikitext2</th>
<th>Ptb-New</th>
<th>C4-New</th>
</tr>
</thead>
<tbody>
<tr>
<td>WizardLM 13b OASST 16bit</td>
<td>8.9622220993042</td>
<td>15.324528694152832</td>
<td>12.847634315490723</td>
</tr>
<tr>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
</tbody>
</table>
</body>
</html>
<br><b>Other benchmark scores at the bottom of readme.</b>
<hr>
<hr>
<p><strong><font size="5">Click to Expand Benchmarks of different quantized variations</font></strong></p>
<strong><font size="4">The lower the number, the better the score.</font></strong>
<html>
<body>
<details>
<summary>Benchmarks Sorted by C4-New score</summary>
<table>
<thead>
<tr>
<th>GPTQ Variation:</th>
<th>Wikitext2</th>
<th>Ptb-New</th>
<th>C4-New</th>
</tr>
</thead>
<tbody>
<tr>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
<tr>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
<tr> |
YakovElm/Hyperledger15Classic_64 | YakovElm | 2023-05-27T04:53:01Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T04:52:27Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Hyperledger15Classic_64
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. -->
# Hyperledger15Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2628
- Train Accuracy: 0.9045
- Validation Loss: 0.3526
- Validation Accuracy: 0.8683
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3275 | 0.8942 | 0.3392 | 0.8807 | 0 |
| 0.2991 | 0.9035 | 0.3343 | 0.8807 | 1 |
| 0.2628 | 0.9045 | 0.3526 | 0.8683 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
kirp/psy-llama-base-delta | kirp | 2023-05-27T04:45:10Z | 0 | 0 | null | [
"dataset:siyangliu/PsyQA",
"region:us"
] | null | 2023-05-24T06:46:10Z | ---
datasets:
- siyangliu/PsyQA
---
lora + chinese llama + special tokens = psy-llama-base
https://wandb.ai/darkbird/psy-llama-4-4090 |
HillZhang/pseudo_native_bart_CGEC_media | HillZhang | 2023-05-27T04:43:35Z | 120 | 0 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"Chinese",
"seq2seq",
"grammar",
"zh",
"arxiv:2305.16023",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-05-24T15:29:08Z | ---
tags:
- text2text-generation
- Chinese
- seq2seq
- grammar
language: zh
license: apache-2.0
---
# Pseudo-Native-BART-CGEC
This model is a cutting-edge CGEC model based on [Chinese BART-large](https://huggingface.co/fnlp/bart-large-chinese).
It is trained with about 100M pseudo native speaker CGEC training data generated by heuristic rules and human-annotated training data for the media domain.
More details can be found in our [Github](https://github.com/HillZhang1999/NaSGEC) and the [paper](https://arxiv.org/pdf/2305.16023.pdf).
## Usage
pip install transformers
```
from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
tokenizer = BertTokenizer.from_pretrained("HillZhang/pseudo_native_bart_CGEC_media")
model = BartForConditionalGeneration.from_pretrained("HillZhang/pseudo_native_bart_CGEC_media")
encoded_input = tokenizer(["北京是中国的都。", "他说：”我最爱的运动是打蓝球“", "我每天大约喝5次水左右。", "今天，我非常开开心。"], return_tensors="pt", padding=True, truncation=True)
if "token_type_ids" in encoded_input:
del encoded_input["token_type_ids"]
output = model.generate(**encoded_input)
print(tokenizer.batch_decode(output, skip_special_tokens=True))
```
## Citation
```
@inproceedings{zhang-etal-2023-nasgec,
title = "{Na}{SGEC}: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts",
author = "Zhang, Yue and
Zhang, Bo and
Jiang, Haochen and
Li, Zhenghua and
Li, Chen and
Huang, Fei and
Zhang, Min"
booktitle = "Findings of ACL",
year = "2023"
}
``` |
HillZhang/real_learner_bart_CGEC_exam | HillZhang | 2023-05-27T04:43:02Z | 120 | 3 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"Chinese",
"seq2seq",
"grammar",
"zh",
"arxiv:2305.16023",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-05-24T15:28:28Z | ---
tags:
- text2text-generation
- Chinese
- seq2seq
- grammar
language: zh
license: apache-2.0
---
# Pseudo-Native-BART-CGEC
This model is a cutting-edge CGEC model based on [Chinese BART-large](https://huggingface.co/fnlp/bart-large-chinese).
It is trained with HSK and Lang8 learner CGEC data (about 1.3M) and human-annotated training data for the exam domain.
More details can be found in our [Github](https://github.com/HillZhang1999/NaSGEC) and the [paper](https://arxiv.org/pdf/2305.16023.pdf).
## Usage
pip install transformers
```
from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
tokenizer = BertTokenizer.from_pretrained("HillZhang/real_learner_bart_CGEC_exam")
model = BartForConditionalGeneration.from_pretrained("HillZhang/real_learner_bart_CGEC_exam")
encoded_input = tokenizer(["北京是中国的都。", "他说：”我最爱的运动是打蓝球“", "我每天大约喝5次水左右。", "今天，我非常开开心。"], return_tensors="pt", padding=True, truncation=True)
if "token_type_ids" in encoded_input:
del encoded_input["token_type_ids"]
output = model.generate(**encoded_input)
print(tokenizer.batch_decode(output, skip_special_tokens=True))
```
## Citation
```
@inproceedings{zhang-etal-2023-nasgec,
title = "{Na}{SGEC}: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts",
author = "Zhang, Yue and
Zhang, Bo and
Jiang, Haochen and
Li, Zhenghua and
Li, Chen and
Huang, Fei and
Zhang, Min"
booktitle = "Findings of ACL",
year = "2023"
}
``` |
HillZhang/pseudo_native_bart_CGEC | HillZhang | 2023-05-27T04:39:23Z | 304 | 1 | transformers | [
"transformers",
"pytorch",
"bart",
"text2text-generation",
"Chinese",
"seq2seq",
"grammar",
"zh",
"arxiv:2305.16023",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-05-24T15:19:59Z | ---
tags:
- text2text-generation
- Chinese
- seq2seq
- grammar
language: zh
license: apache-2.0
---
# Pseudo-Native-BART-CGEC
This model is a cutting-edge CGEC model based on [Chinese BART-large](https://huggingface.co/fnlp/bart-large-chinese).
It is trained with about 100M pseudo native speaker CGEC training data generated by heuristic rules.
More details can be found in our [Github](https://github.com/HillZhang1999/NaSGEC) and the [paper](https://arxiv.org/pdf/2305.16023.pdf).
## Usage
pip install transformers
```
from transformers import BertTokenizer, BartForConditionalGeneration, Text2TextGenerationPipeline
tokenizer = BertTokenizer.from_pretrained("HillZhang/pseudo_native_bart_CGEC")
model = BartForConditionalGeneration.from_pretrained("HillZhang/pseudo_native_bart_CGEC")
encoded_input = tokenizer(["北京是中国的都。", "他说：”我最爱的运动是打蓝球“", "我每天大约喝5次水左右。", "今天，我非常开开心。"], return_tensors="pt", padding=True, truncation=True)
if "token_type_ids" in encoded_input:
del encoded_input["token_type_ids"]
output = model.generate(**encoded_input)
print(tokenizer.batch_decode(output, skip_special_tokens=True))
```
## Citation
```
@inproceedings{zhang-etal-2023-nasgec,
title = "{Na}{SGEC}: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts",
author = "Zhang, Yue and
Zhang, Bo and
Jiang, Haochen and
Li, Zhenghua and
Li, Chen and
Huang, Fei and
Zhang, Min"
booktitle = "Findings of ACL",
year = "2023"
}
``` |
rsadaphule/vit-base-patch16-224-finetuned-flower-ravindrasadaphule | rsadaphule | 2023-05-27T04:32:58Z | 163 | 0 | transformers | [
"transformers",
"pytorch",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-05-24T17:13:25Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: vit-base-patch16-224-finetuned-flower-ravindrasadaphule
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-base-patch16-224-finetuned-flower-ravindrasadaphule
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.24.0
- Pytorch 2.0.1+cu118
- Datasets 2.7.1
- Tokenizers 0.13.3
|
nakajimayoshi/ddpm-iris-256 | nakajimayoshi | 2023-05-27T04:32:06Z | 37 | 2 | diffusers | [
"diffusers",
"tensorboard",
"biology",
"unconditional-image-generation",
"arxiv:2006.11239",
"license:apache-2.0",
"diffusers:DDPMPipeline",
"region:us"
] | unconditional-image-generation | 2023-05-09T07:31:36Z | ---
license: apache-2.0
pipeline_tag: unconditional-image-generation
tags:
- biology
library_name: diffusers
---
Diffusion model trained on a public dataset of images from [image data resource](https://idr.openmicroscopy.org/cell/) to create highly detailed accurate depictions of flourescent and super-resolution cell images.
# Ground-truth image data obtained from idr:
```py
from diffusers import DDIMPipeline, DDPMPipeline, PNDMPipeline
model_id = "nakajimayoshi/ddpm-iris-256"
# load model and scheduler
ddim = DDIMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference
# run pipeline in inference (sample random noise and denoise)
image = ddim().images[0]
# save image
image.save("sample.png")
```
The role of generative AI in the science is a new discussion and the merits of it have yet to be evaluated. Whilst current image-to-image and text-to-image models make it easier than ever to create stunning images, they lack the specific training sets to replicate accurate and detailed images found in flourescent cell microscopy.
We propose ddpm-IRIS, a difusion network leveraging Google's [Diffusion Model](https://arxiv.org/abs/2006.11239) to generate visual depitctions of cell features with more detail than traditional models.
Hyperparameters:
- image_size = 256
- train_batch_size = 16
- eval_batch_size = 16
- num_epochs = 50
- gradient_accumulation_steps = 1
- learning_rate = 1e-4
- lr_warmup_steps = 500
- save_image_epochs = 10
- save_model_epochs = 30
- mixed_precision = 'fp16'
trained on 1 Nvidia A100 40GB GPU over 50 epochs for 2.5 hours.
|
Varaprabha/Qtable_taxi | Varaprabha | 2023-05-27T04:13:34Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T04:13:32Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Qtable_taxi
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="Varaprbha/Qtable_taxi", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
YakovElm/Hyperledger5Classic_64 | YakovElm | 2023-05-27T04:03:05Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T04:02:31Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Hyperledger5Classic_64
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. -->
# Hyperledger5Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3683
- Train Accuracy: 0.8561
- Validation Loss: 0.4172
- Validation Accuracy: 0.8351
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.4207 | 0.8481 | 0.4357 | 0.8361 | 0 |
| 0.3940 | 0.8547 | 0.4199 | 0.8361 | 1 |
| 0.3683 | 0.8561 | 0.4172 | 0.8351 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
ThePioneer/CBDMix | ThePioneer | 2023-05-27T03:39:30Z | 0 | 0 | null | [
"art",
"safetensors",
"en",
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-25T11:24:01Z | ---
license: creativeml-openrail-m
language:
- en
tags:
- art
- safetensors
---
CBDMix is a mixed model of [BRAv5](https://huggingface.co/BanKaiPls/AsianModel) and [chilled remix V2](https://huggingface.co/sazyou-roukaku/chilled_remix), ranging from 10% to 90%.
Since both of them are released under the openrail license family, the same [CreativeML Open RAIL-M](https://huggingface.co/spaces/CompVis/stable-diffusion-license) license will be applied to the model as well.
## Samples
 |
YakovElm/Hyperledger10Classic_32 | YakovElm | 2023-05-27T03:02:45Z | 62 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T03:02:01Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Hyperledger10Classic_32
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. -->
# Hyperledger10Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2991
- Train Accuracy: 0.8845
- Validation Loss: 0.3973
- Validation Accuracy: 0.8548
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3675 | 0.8779 | 0.3861 | 0.8600 | 0 |
| 0.3449 | 0.8838 | 0.3911 | 0.8600 | 1 |
| 0.2991 | 0.8845 | 0.3973 | 0.8548 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
ShadowPower/ggml-alpaca-chatgpt-new | ShadowPower | 2023-05-27T02:34:47Z | 0 | 7 | null | [
"text generation",
"ggml",
"text-generation",
"zh",
"en",
"license:other",
"region:us"
] | text-generation | 2023-05-12T03:37:41Z | ---
license: other
language:
- zh
- en
pipeline_tag: text-generation
tags:
- text generation
- ggml
---
# 说明
这是兼容 llama.cpp commit [b9fd7ee](https://github.com/ggerganov/llama.cpp/pull/1405) 的版本。
支持的语言：汉语、英语。
以 LLaMa 为基础模型，使用 Alpaca 的方式，在大量 ChatGPT 聊天记录和百度搜索结果的基础上，使用 8 块 A100 训练一星期而成。输出的 Token 中加入了常用汉字，相比 Vicuna 有更好的汉语表达能力，能生成更长的中文内容。
可以生成和 ChatGPT 风格相似的对话。如果精心构造 Prompt，也可以用在一部分 NLP 任务中。
建议使用 koboldcpp 加载，然后载入 koboldcpp_config.json 配置文件。
也可以用来续写小说，质量比几乎所有同等参数量的开源模型还要好。
仅供个人娱乐，学习研究使用。不得用于商业用途。
小说续写，橙色线条以下为模型生成内容：
# 局限性
训练内容未经人工修正，模型可能产生存在偏见、错误或有害的内容；
有时模型会生成与 Alpaca 训练数据相似的无意义内容；
由于训练数据存在问题，在回答知识类问题时，模型会在末尾生成虚假的参考来源。 |
YakovElm/Apache20Classic_64 | YakovElm | 2023-05-27T02:30:58Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T02:30:21Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Apache20Classic_64
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. -->
# Apache20Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1374
- Train Accuracy: 0.9624
- Validation Loss: 0.3081
- Validation Accuracy: 0.9055
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.1664 | 0.9620 | 0.3171 | 0.9055 | 0 |
| 0.1522 | 0.9624 | 0.2966 | 0.9055 | 1 |
| 0.1374 | 0.9624 | 0.3081 | 0.9055 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Apache15Classic_64 | YakovElm | 2023-05-27T01:46:32Z | 62 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T01:45:58Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Apache15Classic_64
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. -->
# Apache15Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1664
- Train Accuracy: 0.9542
- Validation Loss: 0.3210
- Validation Accuracy: 0.8924
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.1964 | 0.9533 | 0.3529 | 0.8924 | 0 |
| 0.1834 | 0.9542 | 0.3501 | 0.8924 | 1 |
| 0.1664 | 0.9542 | 0.3210 | 0.8924 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Ryosuke/an2-stable-diffusion | Ryosuke | 2023-05-27T01:21:44Z | 31 | 3 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2022-11-27T04:46:50Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### an2-stable-diffusion Dreambooth model trained by Ryosuke 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)
Or you can run your new concept via `diffusers` [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb)
Sample pictures of this concept:
00074-3537062306-portrait
|
YakovElm/Jira10Classic_256 | YakovElm | 2023-05-27T01:19:24Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T01:18:48Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira10Classic_256
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. -->
# Jira10Classic_256
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3342
- Train Accuracy: 0.8405
- Validation Loss: 0.7061
- Validation Accuracy: 0.6088
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5118 | 0.7817 | 0.8080 | 0.4921 | 0 |
| 0.4265 | 0.7849 | 0.8772 | 0.4921 | 1 |
| 0.3342 | 0.8405 | 0.7061 | 0.6088 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
DelusionalDreams/taxi-v3 | DelusionalDreams | 2023-05-27T01:12:48Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T01:12:45Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.48 +/- 2.77
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="DelusionalDreams/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"])
```
|
DelusionalDreams/q-FrozenLake-v1-4x4-noSlippery | DelusionalDreams | 2023-05-27T01:11:24Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T01:11:22Z | ---
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="DelusionalDreams/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"])
```
|
stevbach/a2c-PandaReachDense-v2 | stevbach | 2023-05-27T01:10:22Z | 3 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T23:49:28Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -1.06 +/- 0.17
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-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
...
```
|
lmattingly/controlnet-uncanny-simpsons-v2-0 | lmattingly | 2023-05-27T00:57:35Z | 24 | 1 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"controlnet",
"jax-diffusers-event",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2023-05-03T03:45:44Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- controlnet
- jax-diffusers-event
inference: true
---
# controlnet- lmattingly/controlnet-uncanny-simpsons-v2-0
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images in the following.
prompt: Simpsons, cartoon character, riding a horse
prompt: Simpsons, character, a boxer
|
sadra-barikbin/rl_course_vizdoom_health_gathering_supreme | sadra-barikbin | 2023-05-27T00:37:58Z | 0 | 0 | sample-factory | [
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-27T00:37:50Z | ---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 10.58 +/- 4.61
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r sadra-barikbin/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
YakovElm/Apache5Classic_64 | YakovElm | 2023-05-27T00:28:21Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-27T00:27:46Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Apache5Classic_64
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. -->
# Apache5Classic_64
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2482
- Train Accuracy: 0.9136
- Validation Loss: 0.5374
- Validation Accuracy: 0.7947
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.3112 | 0.9051 | 0.5143 | 0.8233 | 0 |
| 0.2845 | 0.9116 | 0.4954 | 0.8220 | 1 |
| 0.2482 | 0.9136 | 0.5374 | 0.7947 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
aalonso-developer/vit-base-clothing-leafs-example | aalonso-developer | 2023-05-27T00:26:33Z | 19 | 1 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-05-21T21:39:12Z | ---
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-clothing-leafs-example
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-base-clothing-leafs-example
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 beans dataset.
It achieves the following results on the evaluation set:
- Loss: 6.1420
- Accuracy: 0.0448
## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 8.6059 | 0.14 | 1000 | 8.5844 | 0.0002 |
| 8.5506 | 0.28 | 2000 | 8.5189 | 0.0010 |
| 8.4931 | 0.41 | 3000 | 8.4641 | 0.0012 |
| 8.4223 | 0.55 | 4000 | 8.3495 | 0.0016 |
| 8.3144 | 0.69 | 5000 | 8.2552 | 0.0021 |
| 8.1936 | 0.83 | 6000 | 8.1385 | 0.0024 |
| 8.0638 | 0.97 | 7000 | 7.9924 | 0.0028 |
| 7.8485 | 1.11 | 8000 | 7.8366 | 0.0036 |
| 7.6933 | 1.24 | 9000 | 7.6595 | 0.0045 |
| 7.5808 | 1.38 | 10000 | 7.5232 | 0.0062 |
| 7.4352 | 1.52 | 11000 | 7.3816 | 0.0070 |
| 7.3279 | 1.66 | 12000 | 7.2853 | 0.0084 |
| 7.2141 | 1.8 | 13000 | 7.1553 | 0.0105 |
| 7.151 | 1.94 | 14000 | 7.0853 | 0.0119 |
| 6.9695 | 2.07 | 15000 | 7.0088 | 0.0134 |
| 6.8563 | 2.21 | 16000 | 6.9409 | 0.0139 |
| 6.8019 | 2.35 | 17000 | 6.8634 | 0.0158 |
| 6.7372 | 2.49 | 18000 | 6.8001 | 0.0175 |
| 6.6903 | 2.63 | 19000 | 6.7323 | 0.0191 |
| 6.6482 | 2.77 | 20000 | 6.6638 | 0.0207 |
| 6.5669 | 2.9 | 21000 | 6.6090 | 0.0239 |
| 6.4484 | 3.04 | 22000 | 6.5441 | 0.0240 |
| 6.2568 | 3.18 | 23000 | 6.5015 | 0.0273 |
| 6.2452 | 3.32 | 24000 | 6.4589 | 0.0304 |
| 6.2002 | 3.46 | 25000 | 6.4312 | 0.0310 |
| 6.1699 | 3.6 | 26000 | 6.3723 | 0.0319 |
| 6.1284 | 3.73 | 27000 | 6.3324 | 0.0343 |
| 6.1186 | 3.87 | 28000 | 6.3029 | 0.0350 |
| 6.0611 | 4.01 | 29000 | 6.2723 | 0.0381 |
| 5.7883 | 4.15 | 30000 | 6.2527 | 0.0383 |
| 5.7684 | 4.29 | 31000 | 6.2186 | 0.0392 |
| 5.7701 | 4.43 | 32000 | 6.2031 | 0.0403 |
| 5.7473 | 4.56 | 33000 | 6.1777 | 0.0430 |
| 5.735 | 4.7 | 34000 | 6.1634 | 0.0442 |
| 5.7324 | 4.84 | 35000 | 6.1494 | 0.0443 |
| 5.6949 | 4.98 | 36000 | 6.1420 | 0.0448 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
|
nolanaatama/rlstcvgnsgdpssy1 | nolanaatama | 2023-05-27T00:26:10Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-27T00:22:55Z | ---
license: creativeml-openrail-m
---
|
KostiuchenkoArtem/bart_large_multi | KostiuchenkoArtem | 2023-05-26T23:53:50Z | 63 | 0 | transformers | [
"transformers",
"tf",
"bart",
"text2text-generation",
"generated_from_keras_callback",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2023-05-26T22:04:59Z | ---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: KostiuchenkoArtem/bart_large_multi
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. -->
# KostiuchenkoArtem/bart_large_multi
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.4183
- Validation Loss: 2.2949
- Epoch: 3
## 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 |
|:----------:|:---------------:|:-----:|
| 2.2305 | 2.1257 | 0 |
| 1.9043 | 2.1163 | 1 |
| 1.6451 | 2.1815 | 2 |
| 1.4183 | 2.2949 | 3 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Apache20Classic_32 | YakovElm | 2023-05-26T23:51:31Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T23:50:38Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Apache20Classic_32
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. -->
# Apache20Classic_32
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1517
- Train Accuracy: 0.9624
- Validation Loss: 0.3060
- Validation Accuracy: 0.9055
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.1711 | 0.9581 | 0.4085 | 0.9055 | 0 |
| 0.1568 | 0.9624 | 0.3792 | 0.9055 | 1 |
| 0.1517 | 0.9624 | 0.3060 | 0.9055 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
YakovElm/Jira5Classic_256 | YakovElm | 2023-05-26T23:47:50Z | 64 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T23:47:14Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira5Classic_256
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. -->
# Jira5Classic_256
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.4111
- Train Accuracy: 0.8090
- Validation Loss: 1.1085
- Validation Accuracy: 0.5237
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5551 | 0.7429 | 0.8002 | 0.4858 | 0 |
| 0.4860 | 0.7712 | 0.7765 | 0.4890 | 1 |
| 0.4111 | 0.8090 | 1.1085 | 0.5237 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
NajiAboo/prognosis-distilbert-base-uncased-finetuned-cardio-qa | NajiAboo | 2023-05-26T23:47:29Z | 61 | 0 | transformers | [
"transformers",
"tf",
"tensorboard",
"distilbert",
"question-answering",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-05-26T17:23:17Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: NajiAboo/prognosis-distilbert-base-uncased-finetuned-cardio-qa
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. -->
# NajiAboo/prognosis-distilbert-base-uncased-finetuned-cardio-qa
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: 0.1314
- Train End Logits Accuracy: 0.9575
- Train Start Logits Accuracy: 0.9591
- Validation Loss: 1.5573
- Validation End Logits Accuracy: 0.7503
- Validation Start Logits Accuracy: 0.7457
- Epoch: 7
## 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 494400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
| 1.4969 | 0.6659 | 0.6647 | 1.0266 | 0.7456 | 0.7428 | 0 |
| 0.8820 | 0.7667 | 0.7702 | 0.9726 | 0.7573 | 0.7542 | 1 |
| 0.6269 | 0.8266 | 0.8287 | 1.0440 | 0.7601 | 0.7528 | 2 |
| 0.4406 | 0.8711 | 0.8748 | 1.0837 | 0.7590 | 0.7540 | 3 |
| 0.2999 | 0.9087 | 0.9122 | 1.1957 | 0.7572 | 0.7510 | 4 |
| 0.2168 | 0.9317 | 0.9347 | 1.4545 | 0.7465 | 0.7428 | 5 |
| 0.1623 | 0.9485 | 0.9501 | 1.4684 | 0.7560 | 0.7529 | 6 |
| 0.1314 | 0.9575 | 0.9591 | 1.5573 | 0.7503 | 0.7457 | 7 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
orepin/ppo-LunarLander-v2-stable-baseline | orepin | 2023-05-26T22:59:28Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T22:59:03Z | ---
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: 252.82 +/- 24.57
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
...
```
|
Multi-Domain-Expert-Learning/REDPAJAMA-3B-expert-arxiv | Multi-Domain-Expert-Learning | 2023-05-26T22:58:50Z | 75 | 0 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-26T22:38:55Z | ---
tags:
- generated_from_trainer
datasets:
- /pfs/lustrep4/scratch/project_462000259/ajunior/data/arxiv
metrics:
- accuracy
model-index:
- name: layer_9,10,11,12,13
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. -->
# layer_9,10,11,12,13
This model is a fine-tuned version of [/pfs/lustrep4/scratch/project_462000259/ajunior/models/rallio3b](https://huggingface.co//pfs/lustrep4/scratch/project_462000259/ajunior/models/rallio3b) on the /pfs/lustrep4/scratch/project_462000259/ajunior/data/arxiv dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3984
- Accuracy: 0.5176
## 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.5584 | 0.05 | 500 | 2.5312 | 0.4997 |
| 2.3975 | 0.1 | 1000 | 2.3984 | 0.5176 |
### Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+gitcb6c422
- Datasets 2.11.0
- Tokenizers 0.12.1
|
mfidabel/a2c-PandaReachDense-v2 | mfidabel | 2023-05-26T22:41:15Z | 1 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T21:42:57Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -0.47 +/- 0.18
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-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
...
```
|
BigSalmon/InformalToFormalLincoln100Paraphrase | BigSalmon | 2023-05-26T22:31:47Z | 221 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-26T21:35:02Z | data: https://github.com/BigSalmon2/InformalToFormalDataset
Text Generation Informal Formal
```
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("BigSalmon/InformalToFormalLincoln100Paraphrase")
model = AutoModelForCausalLM.from_pretrained("BigSalmon/InformalToFormalLincoln100Paraphrase")
```
```
Demo:
https://huggingface.co/spaces/BigSalmon/FormalInformalConciseWordy
```
```
prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:"""
input_ids = tokenizer.encode(prompt, return_tensors='pt')
outputs = model.generate(input_ids=input_ids,
max_length=10 + len(prompt),
temperature=1.0,
top_k=50,
top_p=0.95,
do_sample=True,
num_return_sequences=5,
early_stopping=True)
for i in range(5):
print(tokenizer.decode(outputs[i]))
```
Most likely outputs (Disclaimer: I highly recommend using this over just generating):
```
prompt = """informal english: corn fields are all across illinois, visible once you leave chicago.\nTranslated into the Style of Abraham Lincoln:"""
text = tokenizer.encode(prompt)
myinput, past_key_values = torch.tensor([text]), None
myinput = myinput
myinput= myinput.to(device)
logits, past_key_values = model(myinput, past_key_values = past_key_values, return_dict=False)
logits = logits[0,-1]
probabilities = torch.nn.functional.softmax(logits)
best_logits, best_indices = logits.topk(250)
best_words = [tokenizer.decode([idx.item()]) for idx in best_indices]
text.append(best_indices[0].item())
best_probabilities = probabilities[best_indices].tolist()
words = []
print(best_words)
```
```
How To Make Prompt:
informal english: i am very ready to do that just that.
Translated into the Style of Abraham Lincoln: you can assure yourself of my readiness to work toward this end.
Translated into the Style of Abraham Lincoln: please be assured that i am most ready to undertake this laborious task.
***
informal english: space is huge and needs to be explored.
Translated into the Style of Abraham Lincoln: space awaits traversal, a new world whose boundaries are endless.
Translated into the Style of Abraham Lincoln: space is a ( limitless / boundless ) expanse, a vast virgin domain awaiting exploration.
***
informal english: corn fields are all across illinois, visible once you leave chicago.
Translated into the Style of Abraham Lincoln: corn fields ( permeate illinois / span the state of illinois / ( occupy / persist in ) all corners of illinois / line the horizon of illinois / envelop the landscape of illinois ), manifesting themselves visibly as one ventures beyond chicago.
informal english:
```
```
original: microsoft word's [MASK] pricing invites competition.
Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition.
***
original: the library’s quiet atmosphere encourages visitors to [blank] in their work.
Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work.
```
```
Essay Intro (Warriors vs. Rockets in Game 7):
text: eagerly anticipated by fans, game 7's are the highlight of the post-season.
text: ever-building in suspense, game 7's have the crowd captivated.
***
Essay Intro (South Korean TV Is Becoming Popular):
text: maturing into a bona fide paragon of programming, south korean television ( has much to offer / entertains without fail / never disappoints ).
text: increasingly held in critical esteem, south korean television continues to impress.
text: at the forefront of quality content, south korea is quickly achieving celebrity status.
***
Essay Intro (
```
```
Search: What is the definition of Checks and Balances?
https://en.wikipedia.org/wiki/Checks_and_balances
Checks and Balances is the idea of having a system where each and every action in government should be subject to one or more checks that would not allow one branch or the other to overly dominate.
https://www.harvard.edu/glossary/Checks_and_Balances
Checks and Balances is a system that allows each branch of government to limit the powers of the other branches in order to prevent abuse of power
https://www.law.cornell.edu/library/constitution/Checks_and_Balances
Checks and Balances is a system of separation through which branches of government can control the other, thus preventing excess power.
***
Search: What is the definition of Separation of Powers?
https://en.wikipedia.org/wiki/Separation_of_powers
The separation of powers is a principle in government, whereby governmental powers are separated into different branches, each with their own set of powers, that are prevent one branch from aggregating too much power.
https://www.yale.edu/tcf/Separation_of_Powers.html
Separation of Powers is the division of governmental functions between the executive, legislative and judicial branches, clearly demarcating each branch's authority, in the interest of ensuring that individual liberty or security is not undermined.
***
Search: What is the definition of Connection of Powers?
https://en.wikipedia.org/wiki/Connection_of_powers
Connection of Powers is a feature of some parliamentary forms of government where different branches of government are intermingled, typically the executive and legislative branches.
https://simple.wikipedia.org/wiki/Connection_of_powers
The term Connection of Powers describes a system of government in which there is overlap between different parts of the government.
***
Search: What is the definition of
```
```
Search: What are phrase synonyms for "second-guess"?
https://www.powerthesaurus.org/second-guess/synonyms
Shortest to Longest:
- feel dubious about
- raise an eyebrow at
- wrinkle their noses at
- cast a jaundiced eye at
- teeter on the fence about
***
Search: What are phrase synonyms for "mean to newbies"?
https://www.powerthesaurus.org/mean_to_newbies/synonyms
Shortest to Longest:
- readiness to balk at rookies
- absence of tolerance for novices
- hostile attitude toward newcomers
***
Search: What are phrase synonyms for "make use of"?
https://www.powerthesaurus.org/make_use_of/synonyms
Shortest to Longest:
- call upon
- glean value from
- reap benefits from
- derive utility from
- seize on the merits of
- draw on the strength of
- tap into the potential of
***
Search: What are phrase synonyms for "hurting itself"?
https://www.powerthesaurus.org/hurting_itself/synonyms
Shortest to Longest:
- erring
- slighting itself
- forfeiting its integrity
- doing itself a disservice
- evincing a lack of backbone
***
Search: What are phrase synonyms for "
```
```
- nebraska
- unicamerical legislature
- different from federal house and senate
text: featuring a unicameral legislature, nebraska's political system stands in stark contrast to the federal model, comprised of a house and senate.
***
- penny has practically no value
- should be taken out of circulation
- just as other coins have been in us history
- lost use
- value not enough
- to make environmental consequences worthy
text: all but valueless, the penny should be retired. as with other coins in american history, it has become defunct. too minute to warrant the environmental consequences of its production, it has outlived its usefulness.
***
-
```
```
original: sports teams are profitable for owners. [MASK], their valuations experience a dramatic uptick.
infill: sports teams are profitable for owners. ( accumulating vast sums / stockpiling treasure / realizing benefits / cashing in / registering robust financials / scoring on balance sheets ), their valuations experience a dramatic uptick.
***
original:
```
```
wordy: classical music is becoming less popular more and more.
Translate into Concise Text: interest in classic music is fading.
***
wordy:
```
```
sweet: savvy voters ousted him.
longer: voters who were informed delivered his defeat.
***
sweet:
```
```
1: commercial space company spacex plans to launch a whopping 52 flights in 2022.
2: spacex, a commercial space company, intends to undertake a total of 52 flights in 2022.
3: in 2022, commercial space company spacex has its sights set on undertaking 52 flights.
4: 52 flights are in the pipeline for 2022, according to spacex, a commercial space company.
5: a commercial space company, spacex aims to conduct 52 flights in 2022.
***
1:
```
Keywords to sentences or sentence.
```
ngos are characterized by:
□ voluntary citizens' group that is organized on a local, national or international level
□ encourage political participation
□ often serve humanitarian functions
□ work for social, economic, or environmental change
***
what are the drawbacks of living near an airbnb?
□ noise
□ parking
□ traffic
□ security
□ strangers
***
```
```
original: musicals generally use spoken dialogue as well as songs to convey the story. operas are usually fully sung.
adapted: musicals generally use spoken dialogue as well as songs to convey the story. ( in a stark departure / on the other hand / in contrast / by comparison / at odds with this practice / far from being alike / in defiance of this standard / running counter to this convention ), operas are usually fully sung.
***
original: akoya and tahitian are types of pearls. akoya pearls are mostly white, and tahitian pearls are naturally dark.
adapted: akoya and tahitian are types of pearls. ( a far cry from being indistinguishable / easily distinguished / on closer inspection / setting them apart / not to be mistaken for one another / hardly an instance of mere synonymy / differentiating the two ), akoya pearls are mostly white, and tahitian pearls are naturally dark.
***
original:
```
```
original: had trouble deciding.
translated into journalism speak: wrestled with the question, agonized over the matter, furrowed their brows in contemplation.
***
original:
```
```
input: not loyal
1800s english: ( two-faced / inimical / perfidious / duplicitous / mendacious / double-dealing / shifty ).
***
input:
```
```
first: ( was complicit in / was involved in ).
antonym: ( was blameless / was not an accomplice to / had no hand in / was uninvolved in ).
***
first: ( have no qualms about / see no issue with ).
antonym: ( are deeply troubled by / harbor grave reservations about / have a visceral aversion to / take ( umbrage at / exception to ) / are wary of ).
***
first: ( do not see eye to eye / disagree often ).
antonym: ( are in sync / are united / have excellent rapport / are like-minded / are in step / are of one mind / are in lockstep / operate in perfect harmony / march in lockstep ).
***
first:
```
```
stiff with competition, law school {A} is the launching pad for countless careers, {B} is a crowded field, {C} ranks among the most sought-after professional degrees, {D} is a professional proving ground.
***
languishing in viewership, saturday night live {A} is due for a creative renaissance, {B} is no longer a ratings juggernaut, {C} has been eclipsed by its imitators, {C} can still find its mojo.
***
dubbed the "manhattan of the south," atlanta {A} is a bustling metropolis, {B} is known for its vibrant downtown, {C} is a city of rich history, {D} is the pride of georgia.
***
embattled by scandal, harvard {A} is feeling the heat, {B} cannot escape the media glare, {C} is facing its most intense scrutiny yet, {D} is in the spotlight for all the wrong reasons.
```
Infill / Infilling / Masking / Phrase Masking (Works pretty decently actually, especially when you use logprobs code from above):
```
his contention [blank] by the evidence [sep] was refuted [answer]
***
few sights are as [blank] new york city as the colorful, flashing signage of its bodegas [sep] synonymous with [answer]
***
when rick won the lottery, all of his distant relatives [blank] his winnings [sep] clamored for [answer]
***
the library’s quiet atmosphere encourages visitors to [blank] in their work [sep] immerse themselves [answer]
***
the joy of sport is that no two games are alike. for every exhilarating experience, however, there is an interminable one. the national pastime, unfortunately, has a penchant for the latter. what begins as a summer evening at the ballpark can quickly devolve into a game of tedium. the primary culprit is the [blank] of play. from batters readjusting their gloves to fielders spitting on their mitts, the action is [blank] unnecessary interruptions. the sport's future is [blank] if these tendencies are not addressed [sep] plodding pace [answer] riddled with [answer] bleak [answer]
***
microsoft word's [blank] pricing [blank] competition [sep] unconscionable [answer] invites [answer]
***
```
```
original: microsoft word's [MASK] pricing invites competition.
Translated into the Style of Abraham Lincoln: microsoft word's unconscionable pricing invites competition.
***
original: the library’s quiet atmosphere encourages visitors to [blank] in their work.
Translated into the Style of Abraham Lincoln: the library’s quiet atmosphere encourages visitors to immerse themselves in their work.
```
Backwards
```
Essay Intro (National Parks):
text: tourists are at ease in the national parks, ( swept up in the beauty of their natural splendor ).
***
Essay Intro (D.C. Statehood):
washington, d.c. is a city of outsize significance, ( ground zero for the nation's political life / center stage for the nation's political machinations ).
```
```
topic: the Golden State Warriors.
characterization 1: the reigning kings of the NBA.
characterization 2: possessed of a remarkable cohesion.
characterization 3: helmed by superstar Stephen Curry.
characterization 4: perched atop the league’s hierarchy.
characterization 5: boasting a litany of hall-of-famers.
***
topic: emojis.
characterization 1: shorthand for a digital generation.
characterization 2: more versatile than words.
characterization 3: the latest frontier in language.
characterization 4: a form of self-expression.
characterization 5: quintessentially millennial.
characterization 6: reflective of a tech-centric world.
***
topic:
```
```
regular: illinois went against the census' population-loss prediction by getting more residents.
VBG: defying the census' prediction of population loss, illinois experienced growth.
***
regular: microsoft word’s high pricing increases the likelihood of competition.
VBG: extortionately priced, microsoft word is inviting competition.
***
regular:
```
```
source: badminton should be more popular in the US.
QUERY: Based on the given topic, can you develop a story outline?
target: (1) games played with racquets are popular, (2) just look at tennis and ping pong, (3) but badminton underappreciated, (4) fun, fast-paced, competitive, (5) needs to be marketed more
text: the sporting arena is dominated by games that are played with racquets. tennis and ping pong, in particular, are immensely popular. somewhat curiously, however, badminton is absent from this pantheon. exciting, fast-paced, and competitive, it is an underappreciated pastime. all that it lacks is more effective marketing.
***
source: movies in theaters should be free.
QUERY: Based on the given topic, can you develop a story outline?
target: (1) movies provide vital life lessons, (2) many venues charge admission, (3) those without much money
text: the lessons that movies impart are far from trivial. the vast catalogue of cinematic classics is replete with inspiring sagas of friendship, bravery, and tenacity. it is regrettable, then, that admission to theaters is not free. in their current form, the doors of this most vital of institutions are closed to those who lack the means to pay.
***
source:
```
```
in the private sector, { transparency } is vital to the business’s credibility. the { disclosure of information } can be the difference between success and failure.
***
the labor market is changing, with { remote work } now the norm. this { flexible employment } allows the individual to design their own schedule.
***
the { cubicle } is the locus of countless grievances. many complain that the { enclosed workspace } restricts their freedom of movement.
***
```
```
it would be natural to assume that americans, as a people whose ancestors { immigrated to this country }, would be sympathetic to those seeking to do likewise.
question: what does “do likewise” mean in the above context?
(a) make the same journey
(b) share in the promise of the american dream
(c) start anew in the land of opportunity
(d) make landfall on the united states
***
in the private sector, { transparency } is vital to the business’s credibility. this orientation can be the difference between success and failure.
question: what does “this orientation” mean in the above context?
(a) visible business practices
(b) candor with the public
(c) open, honest communication
(d) culture of accountability
```
```
example: suppose you are a teacher. further suppose you want to tell an accurate telling of history. then suppose a parent takes offense. they do so in the name of name of their kid. this happens a lot.
text: educators' responsibility to remain true to the historical record often clashes with the parent's desire to shelter their child from uncomfortable realities.
***
example: suppose you are a student at college. now suppose you have to buy textbooks. that is going to be worth hundreds of dollars. given how much you already spend on tuition, that is going to hard cost to bear.
text: the exorbitant cost of textbooks, which often reaches hundreds of dollars, imposes a sizable financial burden on the already-strapped college student.
```
```
<Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle>
***
<Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle>
```
```
accustomed to having its name uttered ______, harvard university is weathering a rare spell of reputational tumult
(a) in reverential tones
(b) with great affection
(c) in adulatory fashion
(d) in glowing terms
```
```
clarify: international ( {working together} / cooperation ) is called for when ( {issue go beyond lots of borders} / an issue transcends borders / a given matter has transnational implications ).
```
```
description: when someone thinks that their view is the only right one.
synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous.
***
description: when you put something off.
synonyms: shelve, defer, table, postpone.
```
```
organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea.
rewrite phrases: meritocratic, viability, vision
rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability.
```
*Note* Of all the masking techniques, this one works the best.
```
<Prefix> the atlanta hawks may attribute <Prefix> <Suffix> trae young <Suffix> <Middle> their robust season to <Middle>
***
<Prefix> the nobel prize in literature <Prefix> <Suffix> honor <Suffix> <Middle> is a singularly prestigious <Middle>
```
```
essence: when someone's views are keeping within reasonable.
refine: the senator's voting record is ( moderate / centrist / pragmatic / balanced / fair-minded / even-handed ).
***
essence: when things are worked through in a petty way.
refine: the propensity of the u.s. congress to settle every dispute by way of ( mudslinging / bickering / demagoguery / name-calling / finger-pointing / vilification ) is appalling.
```
```
description: when someone thinks that their view is the only right one.
synonyms: intolerant, opinionated, narrow-minded, insular, self-righteous.
***
description: when you put something off.
synonyms: shelve, defer, table, postpone.
```
```
organic sentence: crowdfunding is about winner of best ideas and it can test an entrepreneur’s idea.
rewrite phrases: meritocratic, viability, vision
rewritten with phrases: the meritocratic nature of crowdfunding empowers entrepreneurs to test their vision's viability.
```
```
music before bedtime [makes for being able to relax] -> is a recipe for relaxation.
```
```
[people wanting entertainment love traveling new york city] -> travelers flock to new york city in droves, drawn to its iconic entertainment scene. [cannot blame them] -> one cannot fault them [broadway so fun] -> when it is home to such thrilling fare as Broadway.
```
```
in their ( ‖ when you are rushing because you want to get there on time ‖ / haste to arrive punctually / mad dash to be timely ), morning commuters are too rushed to whip up their own meal.
***
politicians prefer to author vague plans rather than ( ‖ when you can make a plan without many unknowns ‖ / actionable policies / concrete solutions ).
```
```
Q: What is whistleblower protection?
A: Whistleblower protection is a form of legal immunity granted to employees who expose the unethical practices of their employer.
Q: Why are whistleblower protections important?
A: Absent whistleblower protections, employees would be deterred from exposing their employer’s wrongdoing for fear of retribution.
Q: Why would an employer engage in retribution?
A: An employer who has acted unethically stands to suffer severe financial and reputational damage were their transgressions to become public. To safeguard themselves from these consequences, they might seek to dissuade employees from exposing their wrongdoing.
```
```
original: the meritocratic nature of crowdfunding [MASK] into their vision's viability.
infill: the meritocratic nature of crowdfunding [gives investors idea of how successful] -> ( offers entrepreneurs a window ) into their vision's viability.
```
```
Leadership | Lecture 17: Worker Morale
What Workers Look for in Companies:
• Benefits
o Tuition reimbursement
o Paid parental leave
o 401K matching
o Profit sharing
o Pension plans
o Free meals
• Social responsibility
o Environmental stewardship
o Charitable contributions
o Diversity
• Work-life balance
o Telecommuting
o Paid holidays and vacation
o Casual dress
• Growth opportunities
• Job security
• Competitive compensation
• Recognition
o Open-door policies
o Whistleblower protection
o Employee-of-the-month awards
o Positive performance reviews
o Bonuses
```
```
description: business
keywords: for-profit, fiduciary duty, monopolistic, bottom line, return on investment, short-term thinking, capital-intensive, self-interested, risk-taking, fiduciary duty, merger, speculation, profiteering, oversight, capitalism, diversification
```
```
3. In this task, you are given a company name and you need to find its industry.
McDonalds -- Restaurant
Facebook -- Social Network
IKEA -- Furniture
American Express -- Credit Services
Nokia -- Telecom
Nintendo -- Entertainment
4. In this task, you are given a Month and you need to convert it to its corresponding season
April -- Spring
December -- Winter
July -- Summer
October -- Fall
February -- Winter
5. In this task, you are given a sentence with a missing word and you need to predict the correct word.
Managers should set an _____ for their employees. -- example
Some people spend more than four _____ in the gym. -- hours
The police were on the _____ of arresting the suspect. -- verge
They were looking for _____ on how to solve the problem. -- guidance
What is the _____ of the coffee? -- price
6. In this task, you are given a paragraph and you need to reorder it to make it logical.
It was first proposed in 1987. The total length of the bridge is 1,828 meters. The idea of a bridge connects Hong Kong to Macau. -- The idea of bridge connecting Hong Kong and Macau was first proposed in 1987. The total length of the bridge is 1,828 meters.
It is a movie about a brave and noble policeman. The film was produced by Americans. They were Kevin Lima and Chris Buck. They are directors. The movie is called Tarzan. -- Produced by Americans Kevin Lima and Chris Buck, Tarzan is a movie about a brave and noble policeman.
It was first discovered in the mountains of India. The active ingredients in this plant can stimulate hair growth. The plant is called "Hair Plus." -- First discovered in the mountains of India, Hair Plus is a plant whose active ingredients can stimulate hair growth.
```
```
trivia: What is the population of South Korea?
response: 51 million.
***
trivia: What is the minimum voting age in the US?
response: 18.
***
trivia: What are the first ten amendments of the US constitution called?
response: Bill of Rights.
```
```
ideas: in modern-day america, it is customary for the commander-in-chief to conduct regular press conferences
related keywords: transparency, check and balance, sacrosanct, public accountability, adversarial, unscripted, direct access, open government, watchdog, healthy democracy, institutional integrity, right to know, direct line of communication, behind closed doors, updates, track progress, instill confidence, reassure, humanize, leadership style, day-to-day, forthcoming, demystify, ask hard questions
***
ideas: i know this one guy who retired so young, attesting to how careful they were with money.
related keywords: money management, resourceful, penny-pinching, live below their means, frugal, financial discipline, financial independence, conservative, long-term vision, discretionary spending, deferred gratification, preparedness, self-control, cushion
```
```
less specific: actors and musicians should ( support democracy ).
clarifies: actors and musicians should ( wield their celebrity to amplify pro-democracy messaging / marshal their considerable influence in the service of the democratic cause ).
***
less specific: amid a contemporary culture that thrives on profligacy, the discipline necessary to retire early is a vanishing quality. rather than yielding to the lure of indulgence, the aspiring retiree must ( be careful ).
clarifies: amid a contemporary culture that thrives on profligacy, the discipline necessary to retire early is a vanishing quality. rather than yielding to the lure of indulgence, the aspiring retiree must ( master their desires / exercise self-restraint / embrace frugality / restrain their appetite for splendor ).
```
```
dull: clean
emotional heft: spotless, immaculate, pristine
***
dull: hot
emotional heft: scorching, searing, blistering
***
dull: happy
emotional heft: euphoric
```
```
text: {guide: vividly describe the premise of the show "seinfield"} -> set in the heart of bustling new york city, the sitcom "seinfield" follows the everyday {restrict: term that implies they get into trouble but in a comical way} -> misadventures of four neurotic friends. on any given episode, one can find them quarreling over their favorite diner's latest menu change, haggling over the division of household expenses, or contriving a scheme to spy on the apartment's newest resident. mundane as their exploits may be, they never fail to elicit a hearty laugh. {guide: mention how larry david is responsible} -> behind the show's witty, incisive dialogue lies the sharp pen of larry david, who co-created the show with jerry seinfeld. {guide: mention how larry david came up with the most recognizable lines} -> it is his genius that conjured such instantly {restrict: term that imply everybody knows them} -> recognizable quips as "no soup for you!" and "not that there's anything wrong with that!". {guide: mention how humanity should revel in having such good comedians these days} -> as this list of laugh-out-loud lines attests, the world is fortunate to ( count such a sharp comedic mind among its ranks / have such a talented humorist in its midst / have such comedic talent gracing its airwaves ).
```
```
system: i'm not sure i agree with your assessment of the situation.
user: replace "assessment" with a more casual term.
chatbot: ( take / read / view ).
system: i've been feeling really busy lately, trying to balance work and family responsibilities.
user: replace "busy" with a more intense word that conveys it is too much.
chatbot: overwhelmed.
system: the candidate's stance on immigration is quite nebulous, and it's difficult to discern exactly what they would do if elected.
user: replace "nebulous" with a word that conveys a lack of detail.
chatbot: ( vague / ambiguous ).
```
```
user: exorbitant in price, scholarly journals unconscionably define the breadth of one's knowledge awareness by the contents of their wallet. [replace “knowledge awareness” with a more natural expression]
chatbot: intellectual horizons.
user: can you do another alternative to “intellectual horizons” that has more relation to “scholarly journals”?
chatbot: academic enlightenment.
```
```
key: calculate.
syn: estimate, consider, weigh, number, count, apportion, proportion, investigate, reckon, rate, compute.
ant: guess, conjecture, hit, chance, risk, stake, miscalculate.
```
```
description: more forceful version of curious that is less forceful than nosy
answer: inquisitive
description: more forceful version of hopeful that is less forceful than overconfident
answer: optimistic
```
```
key: inquisitive
positive: curious, interested
negative: nosy, prying
***
key: witty
positive: clever, humorous
negative: sarcastic, caustic
***
key: influential
positive: impactful, powerful
negative: overbearing, domineering
``` |
amjadfqs/swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_08 | amjadfqs | 2023-05-26T22:16:46Z | 219 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-05-26T07:29:58Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
model-index:
- name: swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_08
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9536527886881383
- name: Precision
type: precision
value: 0.9563791141223957
---
<!-- 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. -->
# swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_08
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1422
- Accuracy: 0.9537
- F1 Score: 0.9549
- Precision: 0.9564
## 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: 100
- eval_batch_size: 100
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 400
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|
| 1.3618 | 0.99 | 19 | 0.6238 | 0.7541 | 0.7431 | 0.7821 |
| 0.3833 | 1.97 | 38 | 0.3097 | 0.8865 | 0.8884 | 0.8970 |
| 0.2011 | 2.96 | 57 | 0.2600 | 0.9053 | 0.9078 | 0.9171 |
| 0.1124 | 4.0 | 77 | 0.1793 | 0.9328 | 0.9342 | 0.9381 |
| 0.0711 | 4.99 | 96 | 0.1385 | 0.9497 | 0.9509 | 0.9522 |
| 0.0518 | 5.97 | 115 | 0.1506 | 0.9485 | 0.9501 | 0.9523 |
| 0.0393 | 6.96 | 134 | 0.1422 | 0.9537 | 0.9549 | 0.9564 |
| 0.0361 | 8.0 | 154 | 0.1545 | 0.9482 | 0.9497 | 0.9522 |
| 0.025 | 8.99 | 173 | 0.1482 | 0.9501 | 0.9516 | 0.9541 |
| 0.0204 | 9.87 | 190 | 0.1474 | 0.9513 | 0.9527 | 0.9550 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
goodacheez/q-Taxi-v3 | goodacheez | 2023-05-26T21:54:46Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T21:52:58Z | ---
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: 7.48 +/- 2.76
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="goodacheez/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"])
```
|
goodacheez/q-FrozenLake-v1-4x4-noSlippery | goodacheez | 2023-05-26T21:43:42Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T21:43:40Z | ---
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="goodacheez/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"])
```
|
sadra-barikbin/ppo-LunarLander-v2-unit8 | sadra-barikbin | 2023-05-26T21:21:41Z | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T21:17:28Z | ---
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: -101.69 +/- 95.52
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'max_frames': 400000
'gamma': 0.95
'PPO_epsilon': 0.2
'max_t': 99
'target_nets_update_freq': 50
'lr': 0.00025
'entropy_coef': 0.01
'env_id': 'LunarLander-v2'}
```
|
cug/test | cug | 2023-05-26T21:10:27Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"question-answering",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | 2023-05-26T21:05:27Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: cug/test
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. -->
# cug/test
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: 5.8220
- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 63, '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, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Epoch |
|:----------:|:-----:|
| 5.8220 | 0 |
### Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
|
MetaIX/Guanaco-33B-4bit | MetaIX | 2023-05-26T21:02:37Z | 10 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-25T08:47:56Z | <p><strong><font size="5">Information</font></strong></p>
Guanaco 33b working with Oobabooga's Text Generation Webui and KoboldAI.
<p>This is a quantized version of <a href="https://huggingface.co/timdettmers/guanaco-33b">Tim Dettmers' Guanaco 33b.</a></p>
<p><strong>What's included</strong></p>
<P>GPTQ: 2 quantized versions. One quantized --true-sequential and act-order optimizations, and the other was quantized using --true-sequential --groupsize 128 optimizations.</P>
<P>GGML: 3 quantized versions. One quantized using q4_1, another was quantized using q5_0, and the last one was quantized using q5_1.</P>
<p><strong>GPU/GPTQ Usage</strong></p>
<p>To use with your GPU using GPTQ pick one of the .safetensors along with all of the .jsons and .model files.</p>
<p>Oobabooga: If you require further instruction, see <a href="https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md">here</a> and <a href="https://github.com/oobabooga/text-generation-webui/blob/main/docs/LLaMA-model.md">here</a></p>
<p>KoboldAI: If you require further instruction, see <a href="https://github.com/0cc4m/KoboldAI">here</a></p>
<p><strong>CPU/GGML Usage</strong></p>
<p>To use your CPU using GGML(Llamacpp) you only need the single .bin ggml file.</p>
<p>Oobabooga: If you require further instruction, see <a href="https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md">here</a></p>
<p>KoboldAI: If you require further instruction, see <a href="https://github.com/LostRuins/koboldcpp">here</a></p>
<p><strong><font size="5">Benchmarks</font></strong></p>
<p><strong><font size="4">--true-sequential --act-order</font></strong></p>
<strong>Wikitext2</strong>: 4.582493305206299
<strong>Ptb-New</strong>: 8.697775840759277
<strong>C4-New</strong>: 6.67733097076416
<strong>Note</strong>: This version does not use <i>--groupsize 128</i>, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM.
<p><strong><font size="4">--true-sequential --groupsize 128</font></strong></p>
<strong>Wikitext2</strong>: 4.369843006134033
<strong>Ptb-New</strong>: 8.53034496307373
<strong>C4-New</strong>: 6.496636390686035
<strong>Note</strong>: This version uses <i>--groupsize 128</i>, resulting in better evaluations. However, it consumes more VRAM. |
YoavWigelman/dqn-SpaceInvadersNoFrameskip-v4 | YoavWigelman | 2023-05-26T21:02:37Z | 7 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T21:01:59Z | ---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 661.50 +/- 272.31
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga YoavWigelman -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga YoavWigelman -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga YoavWigelman
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
|
LarryAIDraw/Takamine_Takane | LarryAIDraw | 2023-05-26T21:02:20Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:52:03Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/74350/takamine-takane-haite-kudasai-takamine-san |
LarryAIDraw/honjo_nia_v1 | LarryAIDraw | 2023-05-26T21:01:25Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:50:44Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/74261/honjou-nia-date-a-live |
LarryAIDraw/cheshire_caitsit_v1.0 | LarryAIDraw | 2023-05-26T21:01:11Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:50:12Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/74278/cheshirecaitsit-azur-lane |
LarryAIDraw/AKTexasV1.0 | LarryAIDraw | 2023-05-26T20:59:55Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:48:13Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/74516/texas-the-omertosa-or-1mb-arknights-or |
LarryAIDraw/TaihouSwimsuitV1 | LarryAIDraw | 2023-05-26T20:59:39Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:47:40Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/75124/taihou-azur-lane-seaside-daydreams-swimsuit-with-multires-noise-version |
LarryAIDraw/Albedo_Black_Outfit-KK77-V1 | LarryAIDraw | 2023-05-26T20:59:24Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:46:44Z | ---
license: creativeml-openrail-m
---
https://civitai.com/models/75016/albedo-black-outfit-or-overlord |
JCTN/pygmalion-13b-4bit-128g | JCTN | 2023-05-26T20:57:57Z | 8 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-05-26T19:58:05Z | ---
language: en
license: other
commercial: no
inference: false
---
# pygmalion-13b-4bit-128g
## Model description
**Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.**
Quantized from the decoded pygmalion-13b xor format.
**https://huggingface.co/PygmalionAI/pygmalion-13b**
In safetensor format.
### Quantization Information
GPTQ CUDA quantized with: https://github.com/0cc4m/GPTQ-for-LLaMa
```
python llama.py --wbits 4 models/pygmalion-13b c4 --true-sequential --groupsize 128 --save_safetensors models/pygmalion-13b/4bit-128g.safetensors
``` |
Sugarlike/azzull | Sugarlike | 2023-05-26T20:52:34Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-05-26T20:49:44Z | ---
license: creativeml-openrail-m
---
|
orepin/Reinforce-Pixelcopter-30000iter | orepin | 2023-05-26T20:47:58Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T20:47:52Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-30000iter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 74.80 +/- 65.83
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
YakovElm/IntelDAOS15Classic_256 | YakovElm | 2023-05-26T20:40:30Z | 61 | 0 | transformers | [
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T20:39:52Z | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: IntelDAOS15Classic_256
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. -->
# IntelDAOS15Classic_256
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1959
- Train Accuracy: 0.9460
- Validation Loss: 0.3646
- Validation Accuracy: 0.8859
- 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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.2340 | 0.9460 | 0.3859 | 0.8859 | 0 |
| 0.2042 | 0.9460 | 0.3765 | 0.8859 | 1 |
| 0.1959 | 0.9460 | 0.3646 | 0.8859 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
mwinterhalter/my-sentiment-model | mwinterhalter | 2023-05-26T20:18:41Z | 106 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-25T20:19:15Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: my-sentiment-model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.93072
- name: F1
type: f1
value: 0.9315252629081995
---
<!-- 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-sentiment-model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3230
- Accuracy: 0.9307
- F1: 0.9315
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
sagnikrayc/bert-large-uncased-fever | sagnikrayc | 2023-05-26T20:16:19Z | 107 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"en",
"dataset:copenlu/fever_gold_evidence",
"license:afl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T20:12:05Z | ---
license: afl-3.0
datasets:
- copenlu/fever_gold_evidence
language:
- en
metrics:
- precision
- recall
- f1
---
```
wandb: eval/f1 0.87565
wandb: eval/loss 0.70447
wandb: eval/p 0.8745
wandb: eval/r 0.87847
```
**Note**:
1. `[evidence_text][SEP][claim]`
2. Only trained/validated on instances length <= 512 tokens. |
sagnikrayc/bert-large-cased-fever | sagnikrayc | 2023-05-26T20:14:34Z | 105 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"en",
"dataset:copenlu/fever_gold_evidence",
"license:afl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T20:01:44Z | ---
license: afl-3.0
datasets:
- copenlu/fever_gold_evidence
language:
- en
metrics:
- precision
- recall
- f1
---
```
wandb: eval/f1 0.87196
wandb: eval/loss 0.73371
wandb: eval/p 0.87077
wandb: eval/r 0.8753
```
**Note**:
1. `[evidence_text][SEP][claim]`
2. Only trained/validated on instances length <= 512 tokens.
|
sagnikrayc/roberta-large-fever | sagnikrayc | 2023-05-26T20:12:44Z | 106 | 0 | transformers | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"en",
"dataset:copenlu/fever_gold_evidence",
"license:afl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T19:52:33Z | ---
license: afl-3.0
datasets:
- copenlu/fever_gold_evidence
language:
- en
metrics:
- precision
- recall
- f1
---
```
wandb: eval/f1 0.88556
wandb: eval/loss 0.62762
wandb: eval/p 0.88384
wandb: eval/r 0.8891
```
**Note**:
1. `[evidence_text][SEP][claim]`
2. Only trained/validated on instances length <= 512 tokens. |
minosu/godot_dodo_4x_60k_starcoder_15b_2ep | minosu | 2023-05-26T19:34:19Z | 15 | 0 | transformers | [
"transformers",
"pytorch",
"gpt_bigcode",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-22T12:34:51Z | # godot_dodo_4x_60k_starcoder_15b_2ep
## Model details
Trained in May 2023.
Godot-Dodo models are instruction-following models finetuned from open-source base models.
Please refer to the README of the [GitHub repository](https://github.com/minosvasilias/godot-dodo) for detailed information.
### Evaluation datasets
The model was evaluated using code instruction prompts. More details in the [GitHub repository](https://github.com/minosvasilias/godot-dodo).
### Training dataset
The model was trained on a 60k rows instruction following dataset, which is released in the [Github repository](https://github.com/minosvasilias/godot-dodo).
### Training parameters
For exact parameters used, please refer to [this page](https://github.com/minosvasilias/godot-dodo/tree/main/models/godot_dodo_4x_60k_starcoder_15b_2ep) in the GitHub repository.
|
Zeta611/easyword-model-peft-distilled-1.3B | Zeta611 | 2023-05-26T19:22:35Z | 0 | 0 | null | [
"pytorch",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-05-26T18:40:19Z | ---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: easyword-model-peft-distilled-1.3B
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. -->
# easyword-model-peft-distilled-1.3B
This model is a fine-tuned version of [facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1607
- Bleu: 0.0
- Gen Len: 5.9876
## 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: 16
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log | 1.0 | 31 | 4.9650 | 0.0 | 9.3975 |
| No log | 2.0 | 62 | 4.4353 | 0.1522 | 8.6957 |
| No log | 3.0 | 93 | 3.8967 | 1.2792 | 6.8137 |
| No log | 4.0 | 124 | 3.6053 | 2.6004 | 6.0062 |
| No log | 5.0 | 155 | 3.5239 | 2.9339 | 5.8571 |
| No log | 6.0 | 186 | 3.4692 | 2.6031 | 5.8261 |
| No log | 7.0 | 217 | 3.4244 | 2.6536 | 5.795 |
| No log | 8.0 | 248 | 3.3865 | 2.6445 | 5.8509 |
| No log | 9.0 | 279 | 3.3555 | 2.5482 | 5.9193 |
| No log | 10.0 | 310 | 3.3325 | 3.087 | 5.913 |
| No log | 11.0 | 341 | 3.3141 | 3.3511 | 5.9006 |
| No log | 12.0 | 372 | 3.2986 | 3.3511 | 5.8944 |
| No log | 13.0 | 403 | 3.2871 | 3.9871 | 5.8758 |
| No log | 14.0 | 434 | 3.2787 | 3.3083 | 5.882 |
| No log | 15.0 | 465 | 3.2738 | 3.3083 | 5.882 |
| No log | 16.0 | 496 | 3.2720 | 3.3083 | 5.882 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
orepin/Reinforce-Pixelcopter-15000iter | orepin | 2023-05-26T19:03:26Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T19:03:20Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-15000iter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 39.10 +/- 34.44
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
Monero/WizardLM-OpenAssistant-30b-Uncensored-4bit | Monero | 2023-05-26T18:58:48Z | 10 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-26T06:15:01Z | WizardLM 30b Native merged 50%/50% with Open Assistant 30b Native
# Use:
Add ```### Certainly!``` to the end of your prompt for uncensored output |
fgheorghe/terrain-generator | fgheorghe | 2023-05-26T18:23:31Z | 2 | 0 | diffusers | [
"diffusers",
"tensorboard",
"license:bsd-3-clause-clear",
"diffusers:DDPMPipeline",
"region:us"
] | null | 2023-05-22T23:39:06Z | ---
license: bsd-3-clause-clear
library_name: diffusers
---
An experimental 3d terrain generating model (generates heightmaps for terrains).
More details on dataset, training and usage available here:
https://github.com/fgheorghe/ai-terrain-generator
|
darthrevenge/a2c-PandaReachDense-v2 | darthrevenge | 2023-05-26T18:21:47Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T18:18:59Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v2
type: PandaReachDense-v2
metrics:
- type: mean_reward
value: -1.54 +/- 0.62
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v2**
This is a trained model of a **A2C** agent playing **PandaReachDense-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
...
```
|
vhurryharry/cifarv2 | vhurryharry | 2023-05-26T18:16:26Z | 194 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:cifar10",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2023-05-26T16:10:19Z | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- cifar10
metrics:
- accuracy
model-index:
- name: cifarv2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: cifar10
type: cifar10
config: plain_text
split: train[:20000]
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.921
---
<!-- 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. -->
# cifarv2
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 cifar10 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2653
- Accuracy: 0.921
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6994 | 1.0 | 250 | 0.7132 | 0.8758 |
| 0.4271 | 2.0 | 500 | 0.4477 | 0.894 |
| 0.3112 | 3.0 | 750 | 0.3905 | 0.8942 |
| 0.3139 | 4.0 | 1000 | 0.3207 | 0.9115 |
| 0.2511 | 5.0 | 1250 | 0.3288 | 0.9048 |
| 0.2652 | 6.0 | 1500 | 0.2977 | 0.9125 |
| 0.2392 | 7.0 | 1750 | 0.2720 | 0.9187 |
| 0.1759 | 8.0 | 2000 | 0.2670 | 0.9173 |
| 0.2024 | 9.0 | 2250 | 0.2606 | 0.9193 |
| 0.1774 | 10.0 | 2500 | 0.2653 | 0.921 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
CodyKilpatrick/q-taxi-v3 | CodyKilpatrick | 2023-05-26T18:07:05Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T18:07:02Z | ---
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: 7.50 +/- 2.75
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="CodyKilpatrick/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"])
```
|
CodyKilpatrick/q-FrozenLake-v1-4x4-noSlippery | CodyKilpatrick | 2023-05-26T18:04:32Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T18:04:29Z | ---
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="CodyKilpatrick/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"])
```
|
orepin/Reinforce-Pixelcopter-5000iter | orepin | 2023-05-26T18:04:28Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T18:04:25Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-5000iter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 32.10 +/- 27.97
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
orepin/Reinforce-Pixelcopter | orepin | 2023-05-26T17:15:27Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-23T14:16:09Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 30.80 +/- 26.87
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
raghvendramall/esm2_t6_8M_UR50D-localization-mc-finetuned-localization | raghvendramall | 2023-05-26T17:00:35Z | 112 | 0 | transformers | [
"transformers",
"pytorch",
"esm",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-05-26T12:40:30Z | ---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: esm2_t6_8M_UR50D-localization-mc-finetuned-localization
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. -->
# esm2_t6_8M_UR50D-localization-mc-finetuned-localization
This model is a fine-tuned version of [facebook/esm2_t6_8M_UR50D](https://huggingface.co/facebook/esm2_t6_8M_UR50D) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5055
- F1: 0.7776
## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.9359 | 1.0 | 1411 | 0.8535 | 0.7208 |
| 0.7693 | 2.0 | 2822 | 0.7625 | 0.7293 |
| 0.619 | 3.0 | 4233 | 0.7689 | 0.7555 |
| 0.4961 | 4.0 | 5644 | 0.8251 | 0.7592 |
| 0.3477 | 5.0 | 7055 | 0.9720 | 0.7717 |
| 0.219 | 6.0 | 8466 | 1.0984 | 0.7800 |
| 0.1293 | 7.0 | 9877 | 1.2810 | 0.7781 |
| 0.068 | 8.0 | 11288 | 1.4495 | 0.7752 |
| 0.0318 | 9.0 | 12699 | 1.5142 | 0.7771 |
| 0.0178 | 10.0 | 14110 | 1.5055 | 0.7776 |
### Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
jfiekdjdk/chinese-alpaca-yuniform-7b | jfiekdjdk | 2023-05-26T16:48:57Z | 13 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"apalca",
"chatglm",
"zh",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2023-05-26T14:07:07Z | ---
license: apache-2.0
language:
- zh
- en
tags:
- apalca
- chatglm
- pytorch
---
## NOTICE:
I am not original author of this model, the author of original model has take down this model from huggingface, this is reupload of original files, plus GPTQ 4bit safetensors file.
## 简介 Brief Introduction
Yuniform的底座模型来源于[shibing624/chinese-alpaca-plus-7b](https://huggingface.co/shibing624/chinese-alpaca-plus-7b)。与底座模型的部分参数微调不同，我们收集了6M来自不同领域和任务的数据，在底座模型上进行全参微调。
Yuniform is derived from [shibing624/chinese-alpaca-plus-7b](https://huggingface.co/shibing624/chinese-alpaca-plus-7b). Instead of finetuning on a small portion of parameters, all the model parameters are finetuned on 6M data collected from various domains and tasks.
### Test case
|input_text|predict|
|:-- |:--- |
|以《领导，你尿尿也尿得这么好》为题写一首讽刺官场阿谀奉承、溜须拍马的乱象的现代叙事诗|领导，你尿尿也尿得这么好，<br/>口中含着甜言蜜语，<br/>脸上挂着笑容，<br/>却把人民当成了玩具。<br/>他用金钱和权力来交换，<br/>换取了一片虚荣心，<br/>而人民却成了他的傀儡，<br/>任由他摆布着自己的命运。<br/>领导，你尿尿也尿得这么好，<br/>在人们面前装出一副高大上，<br/>却忘了自己是为人民服务的人，<br/>只顾着自己的利益，<br/>不顾百姓的感受。<br/>他为了自己的名利，<br/>不惜牺牲别人的尊严，<br/>让人们感到羞耻和愤怒，<br/>这难道不是一种罪恶吗？<br/>领导，你尿尿也尿得这么好，<br/>你的行为已经到了无可救药的地步，<br/>我们需要的是一个真正的领袖，<br/>一个能够真正关心人民的人。|
## Usage (HuggingFace Transformers)
Install package:
```
pip install transformers>=4.28.0
```
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
_MODEL_PATH = "gxy/chinese-alpaca-yuniform-7b"
model = LlamaForCausalLM.from_pretrained(_MODEL_PATH, torch_dtype=torch.half).cuda()
tokenizer = LlamaTokenizer.from_pretrained(_MODEL_PATH)
prompt_prefix = "请根据下列指令进行生成"
human_prefix = "[问]"
assistant_prefix = "[答]"
query = "以《领导，你尿尿也尿得这么好》为题写一首讽刺官场阿谀奉承、溜须拍马的乱象的现代叙事诗"
input_query = f"{prompt_prefix}\n{human_prefix}: {query}\n{assistant_prefix}:"
# 在某些case下不加bos反倒能获得更好更长的结果
inputs = tokenizer(input_query, return_tensors="pt", add_special_tokens=False).to(model.device)
gen_tokens = model.generate(
**inputs,
temperature=0.7,
top_p=0.1,
do_sample=True,
repetition_penalty=1.18,
max_new_tokens=400
)
gen_texts = tokenizer.batch_decode(
gen_tokens, skip_specical_tokens=True)
for gen_text in gen_texts:
print(f"generate:\n{gen_text[len(input_query):]}")
```
output:
```shell
generate:
领导，你尿尿也尿得这么好，
口中含着甜言蜜语，
脸上挂着笑容，
却把人民当成了玩具。
他用金钱和权力来交换，
换取了一片虚荣心，
而人民却成了他的傀儡，
任由他摆布着自己的命运。
领导，你尿尿也尿得这么好，
在人们面前装出一副高大上，
却忘了自己是为人民服务的人，
只顾着自己的利益，
不顾百姓的感受。
他为了自己的名利，
不惜牺牲别人的尊严，
让人们感到羞耻和愤怒，
这难道不是一种罪恶吗？
领导，你尿尿也尿得这么好，
你的行为已经到了无可救药的地步，
我们需要的是一个真正的领袖，
一个能够真正关心人民的人。
```
## 贡献者 Contributors
chinese-alpaca-yuniform-7b is mainly contributed by:
Xinyu Gao: [email protected]
Xiayu Li: [email protected]
Ting Han: [email protected]
Yunxiao Li: [email protected]
Yuchen Fan: [email protected]
If you have any questions, please feel free to contact us via email.
|
rahular/varta-bert | rahular | 2023-05-26T16:29:46Z | 126 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"as",
"bh",
"bn",
"en",
"gu",
"hi",
"kn",
"ml",
"mr",
"ne",
"or",
"pa",
"ta",
"te",
"ur",
"dataset:rahular/varta",
"arxiv:2305.05858",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2022-12-11T17:11:16Z | ---
license: apache-2.0
datasets:
- rahular/varta
language:
- as
- bh
- bn
- en
- gu
- hi
- kn
- ml
- mr
- ne
- or
- pa
- ta
- te
- ur
---
# Varta-BERT
<!-- Provide a quick summary of what the model is/does. -->
### Model Description
<!-- Provide a longer summary of what this model is. -->
Varta-BERT is a model pre-trained on the `full` training set of [Varta](https://huggingface.co/datasets/rahular/varta) in 14 Indic languages (Assamese, Bhojpuri, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Nepali, Oriya, Punjabi, Tamil, Telugu, and Urdu) and English, using a masked language modeling (MLM) objective.
[Varta](https://huggingface.co/datasets/rahular/varta) is a large-scale news corpus for Indic languages, including 41.8 million news articles in 14 different Indic languages (and English), which come from a variety of high-quality sources.
The dataset and the model are introduced in [this paper](https://arxiv.org/abs/2305.05858). The code is released in [this repository](https://github.com/rahular/varta).
## Uses
You can use the raw model for masked language modeling, but it is mostly intended to be fine-tuned on a downstream task.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation, you should look at our [Varta-T5](https://huggingface.co/rahular/varta-t5) model.
## Bias, Risks, and Limitations
This work is mainly dedicated to the curation of a new multilingual dataset for Indic languages, many of which are low-resource languages. During data collection, we face several limitations that can potentially result in ethical concerns. Some of the important ones are mentioned below: <br>
- Our dataset contains only those articles written by DailyHunt's partner publishers. This has the potential to result in a bias towards a particular narrative or ideology that can affect the representativeness and diversity of the dataset.
- Another limitation is the languages represented in Varta. Out of 22 languages with official status in India, our dataset has only 13. There are 122 major languages spoken by at least 10,000 people and 159 other languages which are extremely low-resourced. None of these languages are represented in our dataset.
- We do not perform any kind of debiasing on Varta. This means that societal and cultural biases may exist in the dataset, which can adversely affect the fairness and inclusivity of the models trained on it.
## How to Get Started with the Model
You can use this model directly for masked language modeling.
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("rahular/varta-bert")
model = AutoModelForMaskedLM.from_pretrained("rahular/varta-bert")
```
## Training Details
### Training Data
Varta contains 41.8 million high-quality news articles in 14 Indic languages and English.
With 34.5 million non-English article-headline pairs, it is the largest document-level dataset of its kind.
### Pretraining
- We pretrain the Varta-BERT model using the standard BERT-Base architecture with 12 encoder layers.
- We train with a maximum sequence length of 512 tokens with an embedding dimension of 768.
- We use 12 attention heads with feed-forward width of 3072.
- To support all the 15 languages in dataset we use a wordpiece vocabulary of size 128K.
- In total, the model has 184M parameters. The model is trained with AdamW optimizer with alpha=0.9 and beta=0.98.
- We use an initial learning rate of 1e-4 with a warm-up of 10K steps and linearly decay the learning rate till the end of training.
- We train the model for a total of 1M steps which takes 10 days to finish.
- We use an effective batch size of 4096 and train the model on TPU v3-128 chips.
Since data sizes across languages in Varta vary from 1.5K (Bhojpuri) to 14.4M articles (Hindi), we use standard temperature-based sampling to upsample data when necessary.
### Evaluation Results
Please see [the paper](https://arxiv.org/pdf/2305.05858.pdf).
## Citation
```
@misc{aralikatte2023varta,
title={V\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages},
author={Rahul Aralikatte and Ziling Cheng and Sumanth Doddapaneni and Jackie Chi Kit Cheung},
year={2023},
eprint={2305.05858},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
Ryojun/Foods-Attractiveness-Classification | Ryojun | 2023-05-26T16:26:52Z | 0 | 0 | null | [
"foods",
"image-classification",
"region:us"
] | image-classification | 2023-05-26T07:48:31Z | ---
metrics:
- accuracy
pipeline_tag: image-classification
tags:
- foods
--- |
Steddex/poca-SoccerTwos | Steddex | 2023-05-26T16:21:57Z | 32 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"unity-ml-agents",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2023-05-25T14:27:05Z |
---
tags:
- unity-ml-agents
- ml-agents
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
library_name: ml-agents
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://github.com/huggingface/ml-agents#get-started
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
### Resume the training
```
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. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
2. Step 1: Write your model_id: Steddex/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
alendra1945/tes-alpaca-lora7b | alendra1945 | 2023-05-26T16:03:18Z | 0 | 0 | null | [
"dataset:yahma/alpaca-cleaned",
"license:mit",
"region:us"
] | null | 2023-05-20T20:08:34Z | ---
license: mit
datasets:
- yahma/alpaca-cleaned
---
|
BlazingFringe/mpnet-mnr-v2-fine-tuned | BlazingFringe | 2023-05-26T15:49:56Z | 3 | 2 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"transformers",
"dataset:anli",
"dataset:glue",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | sentence-similarity | 2023-05-23T11:43:43Z | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
datasets:
- anli
- glue
---
# Mpnet-v2-MNR-Fine-Tuned
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('BlazingFringe/mpnet-mnr-v2-fine-tuned')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('BlazingFringe/mpnet-mnr-v2-fine-tuned')
model = AutoModel.from_pretrained('BlazingFringe/mpnet-mnr-v2-fine-tuned')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 1009 with parameters:
```
{'batch_size': 32}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 2,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 100,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
GGunjan/ppo-LunarLander | GGunjan | 2023-05-26T15:43:29Z | 4 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-05-26T15:43:14Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 289.05 +/- 14.24
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
...
```
|
Subsets and Splits