modelId
stringlengths 5
138
| author
stringlengths 2
42
| last_modified
unknowndate 2020-02-15 11:33:14
2025-04-11 18:27:37
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 421
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
unknowndate 2022-03-02 23:29:04
2025-04-11 18:27:06
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
mradermacher/Take-7B-GGUF | mradermacher | "2025-01-06T11:53:38Z" | 76 | 1 | transformers | [
"transformers",
"gguf",
"ja",
"dataset:llm-jp/oasst2-33k-ja",
"base_model:Manual-Dataset-Creation-Project/Take-7B",
"base_model:quantized:Manual-Dataset-Creation-Project/Take-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2025-01-06T11:27:47Z" | ---
base_model: Manual-Dataset-Creation-Project/Take-7B
datasets:
- llm-jp/oasst2-33k-ja
language:
- ja
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Manual-Dataset-Creation-Project/Take-7B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Take-7B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Take-7B-GGUF/resolve/main/Take-7B.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Yntec/DreamlikeDiffusion | Yntec | "2024-06-09T05:52:41Z" | 159 | 1 | diffusers | [
"diffusers",
"safetensors",
"art",
"artistic",
"DreamlikeArt",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"en",
"license:other",
"autotrain_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-04-14T01:47:17Z" | ---
language:
- en
license: other
tags:
- art
- artistic
- DreamlikeArt
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: false
---
# Dreamlike Diffusion
768x768 version of this model with the 840KVAE baked in for improved details, specially on the eyes. Original page: https://huggingface.co/dreamlike-art/dreamlike-diffusion-1.0
Comparison:
(Click for larger)
Samples and prompts:
(Click for larger)
Top left: cute girl and her father sitting in forest. A daughter with a wizard. Detailed faces in the style of Mark Brooks.
Top right: Young Elvis with his daughter. Movie still. Pretty CUTE LITTLE Girl with sister playing with miniature toy city, bokeh. DETAILED vintage colors photography brown EYES, sitting on a box of pepsis, gorgeous detailed Ponytail, cocacola can Magazine ad, iconic, 1935, sharp focus. Illustration By KlaysMoji and leyendecker and artgerm and Dave Rapoza
Bottom left: An alien planet psychedelic marijuana forest with bioluminescent lighting dark art highly detailed neon dark art deviant super detailed 4k render by gustave dore
Bottom right: Retro colors Portrait of a adorable young girl. fashion in the style of Milton Caniff |
oriental-lab/Tr-Jp-LLM-1.5B-v2-dolly | oriental-lab | "2025-03-26T12:22:05Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-03-26T12:20:59Z" | ---
base_model: oriental-lab/tr-jp-LLM-1.5B-v2-dolly_tl
library_name: transformers
model_name: Tr-Jp-LLM-1.5B-v2-dolly
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for Tr-Jp-LLM-1.5B-v2-dolly
This model is a fine-tuned version of [oriental-lab/tr-jp-LLM-1.5B-v2-dolly_tl](https://huggingface.co/oriental-lab/tr-jp-LLM-1.5B-v2-dolly_tl).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="oriental-lab/Tr-Jp-LLM-1.5B-v2-dolly", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/twin1shun/huggingface/runs/0ia025ec)
This model was trained with SFT.
### Framework versions
- TRL: 0.16.0
- Transformers: 4.49.0
- Pytorch: 2.6.0+cu126
- Datasets: 3.4.1
- Tokenizers: 0.21.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
stuti-srinath/Reinforcement-cartpole | stuti-srinath | "2025-03-10T11:33:49Z" | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2025-03-10T11:33:06Z" | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforcement-cartpole
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 494.69 +/- 40.16
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
istominvi/vswpntsbeige_16_16_32 | istominvi | "2025-02-13T13:21:10Z" | 0 | 0 | null | [
"hunyuan",
"hunyuan-video",
"hunyuan-lora",
"lora",
"replicate",
"text-to-video",
"en",
"base_model:tencent/HunyuanVideo",
"base_model:adapter:tencent/HunyuanVideo",
"license:other",
"region:us"
] | text-to-video | "2025-02-13T11:40:17Z" | ---
license: other
license_name: tencent-hunyuan-community
license_link: https://huggingface.co/tencent/HunyuanVideo/blob/main/LICENSE
language:
- en
tags:
- hunyuan
- hunyuan-video
- hunyuan-lora
- lora
- replicate
base_model: "tencent/HunyuanVideo"
pipeline_tag: text-to-video
# widget:
# - text: >-
# prompt
# output:
# url: https://...
---
# Vswpntsbeige_16_16_32
<Gallery />
Trained on Replicate using:
https://replicate.com/zsxkib/hunyuan-video-lora/train
|
ExusBurn/SpaceInvaders | ExusBurn | "2024-03-04T10:15:17Z" | 0 | 1 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | "2024-03-04T10:12:36Z" | ---
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: 618.00 +/- 212.36
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 ExusBurn -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 ExusBurn -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 ExusBurn
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
microsoft/speecht5_tts | microsoft | "2023-11-08T14:37:23Z" | 139,858 | 728 | transformers | [
"transformers",
"pytorch",
"speecht5",
"text-to-audio",
"audio",
"text-to-speech",
"dataset:libritts",
"arxiv:2110.07205",
"arxiv:1910.09700",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-to-speech | "2023-02-02T12:56:54Z" | ---
license: mit
tags:
- audio
- text-to-speech
datasets:
- libritts
---
# SpeechT5 (TTS task)
SpeechT5 model fine-tuned for speech synthesis (text-to-speech) on LibriTTS.
This model was introduced in [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://arxiv.org/abs/2110.07205) by Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei.
SpeechT5 was first released in [this repository](https://github.com/microsoft/SpeechT5/), [original weights](https://huggingface.co/mechanicalsea/speecht5-tts). The license used is [MIT](https://github.com/microsoft/SpeechT5/blob/main/LICENSE).
## Model Description
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder.
Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder.
Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.
- **Developed by:** Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei.
- **Shared by [optional]:** [Matthijs Hollemans](https://huggingface.co/Matthijs)
- **Model type:** text-to-speech
- **Language(s) (NLP):** [More Information Needed]
- **License:** [MIT](https://github.com/microsoft/SpeechT5/blob/main/LICENSE)
- **Finetuned from model [optional]:** [More Information Needed]
## Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [https://github.com/microsoft/SpeechT5/]
- **Paper:** [https://arxiv.org/pdf/2110.07205.pdf]
- **Blog Post:** [https://huggingface.co/blog/speecht5]
- **Demo:** [https://huggingface.co/spaces/Matthijs/speecht5-tts-demo]
# Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
## 🤗 Transformers Usage
You can run SpeechT5 TTS locally with the 🤗 Transformers library.
1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers), sentencepiece, soundfile and datasets(optional):
```
pip install --upgrade pip
pip install --upgrade transformers sentencepiece datasets[audio]
```
2. Run inference via the `Text-to-Speech` (TTS) pipeline. You can access the SpeechT5 model via the TTS pipeline in just a few lines of code!
```python
from transformers import pipeline
from datasets import load_dataset
import soundfile as sf
synthesiser = pipeline("text-to-speech", "microsoft/speecht5_tts")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
```
3. Run inference via the Transformers modelling code - You can use the processor + generate code to convert text into a mono 16 kHz speech waveform for more fine-grained control.
```python
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import soundfile as sf
from datasets import load_dataset
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
inputs = processor(text="Hello, my dog is cute.", return_tensors="pt")
# load xvector containing speaker's voice characteristics from a dataset
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
sf.write("speech.wav", speech.numpy(), samplerate=16000)
```
### Fine-tuning the Model
Refer to [this Colab notebook](https://colab.research.google.com/drive/1i7I5pzBcU3WDFarDnzweIj4-sVVoIUFJ) for an example of how to fine-tune SpeechT5 for TTS on a different dataset or a new language.
## Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
You can use this model for speech synthesis. See the [model hub](https://huggingface.co/models?search=speecht5) to look for fine-tuned versions on a task that interests you.
## Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
## Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
# Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
## Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
# Training Details
## Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
LibriTTS
## Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
### Preprocessing [optional]
Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text.
### Training hyperparameters
- **Precision:** [More Information Needed] <!--fp16, bf16, fp8, fp32 -->
- **Regime:** [More Information Needed] <!--mixed precision or not -->
### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
# Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
## Testing Data, Factors & Metrics
### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
## Results
[More Information Needed]
### Summary
# Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.
# Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
# Technical Specifications [optional]
## Model Architecture and Objective
The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets.
After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder.
## Compute Infrastructure
[More Information Needed]
### Hardware
[More Information Needed]
### Software
[More Information Needed]
# Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
```bibtex
@inproceedings{ao-etal-2022-speecht5,
title = {{S}peech{T}5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing},
author = {Ao, Junyi and Wang, Rui and Zhou, Long and Wang, Chengyi and Ren, Shuo and Wu, Yu and Liu, Shujie and Ko, Tom and Li, Qing and Zhang, Yu and Wei, Zhihua and Qian, Yao and Li, Jinyu and Wei, Furu},
booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
month = {May},
year = {2022},
pages={5723--5738},
}
```
# Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
- **text-to-speech** to synthesize audio
# More Information [optional]
[More Information Needed]
# Model Card Authors [optional]
Disclaimer: The team releasing SpeechT5 did not write a model card for this model so this model card has been written by the Hugging Face team.
# Model Card Contact
[More Information Needed]
|
Dugoss/digit_defines | Dugoss | "2023-06-18T19:08:07Z" | 0 | 0 | keras | [
"keras",
"tf-keras",
"region:us"
] | null | "2023-06-18T18:15:59Z" | ---
library_name: keras
---
# Модель для распознавания цифр
Натренирована на наборе данных Mnist
|
featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF | featherless-ai-quants | "2024-11-11T04:51:07Z" | 9 | 0 | null | [
"gguf",
"text-generation",
"base_model:denial07/Qwen2-72B-Instruct-kor-dpo",
"base_model:quantized:denial07/Qwen2-72B-Instruct-kor-dpo",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | "2024-11-11T02:15:53Z" | ---
base_model: denial07/Qwen2-72B-Instruct-kor-dpo
pipeline_tag: text-generation
quantized_by: featherless-ai-quants
---
# denial07/Qwen2-72B-Instruct-kor-dpo GGUF Quantizations 🚀
*Optimized GGUF quantization files for enhanced model performance*
> Powered by [Featherless AI](https://featherless.ai) - run any model you'd like for a simple small fee.
---
## Available Quantizations 📊
| Quantization Type | File | Size |
|-------------------|------|------|
| IQ4_XS | [denial07-Qwen2-72B-Instruct-kor-dpo-IQ4_XS](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-IQ4_XS) | 38302.65 MB (folder) |
| Q2_K | [denial07-Qwen2-72B-Instruct-kor-dpo-Q2_K](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q2_K) | 28430.71 MB (folder) |
| Q3_K_L | [denial07-Qwen2-72B-Instruct-kor-dpo-Q3_K_L](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q3_K_L) | 37675.12 MB (folder) |
| Q3_K_M | [denial07-Qwen2-72B-Instruct-kor-dpo-Q3_K_M](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q3_K_M) | 35952.30 MB (folder) |
| Q3_K_S | [denial07-Qwen2-72B-Instruct-kor-dpo-Q3_K_S](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q3_K_S) | 32890.12 MB (folder) |
| Q4_K_M | [denial07-Qwen2-72B-Instruct-kor-dpo-Q4_K_M](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q4_K_M) | 45219.15 MB (folder) |
| Q4_K_S | [denial07-Qwen2-72B-Instruct-kor-dpo-Q4_K_S](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q4_K_S) | 41856.02 MB (folder) |
| Q5_K_M | [denial07-Qwen2-72B-Instruct-kor-dpo-Q5_K_M](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q5_K_M) | 51925.15 MB (folder) |
| Q5_K_S | [denial07-Qwen2-72B-Instruct-kor-dpo-Q5_K_S](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q5_K_S) | 48995.15 MB (folder) |
| Q6_K | [denial07-Qwen2-72B-Instruct-kor-dpo-Q6_K](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q6_K) | 61366.68 MB (folder) |
| Q8_0 | [denial07-Qwen2-72B-Instruct-kor-dpo-Q8_0](https://huggingface.co/featherless-ai-quants/denial07-Qwen2-72B-Instruct-kor-dpo-GGUF/tree/main/denial07-Qwen2-72B-Instruct-kor-dpo-Q8_0) | 73683.37 MB (folder) |
---
## ⚡ Powered by [Featherless AI](https://featherless.ai)
### Key Features
- 🔥 **Instant Hosting** - Deploy any Llama model on HuggingFace instantly
- 🛠️ **Zero Infrastructure** - No server setup or maintenance required
- 📚 **Vast Compatibility** - Support for 2400+ models and counting
- 💎 **Affordable Pricing** - Starting at just $10/month
---
**Links:**
[Get Started](https://featherless.ai) | [Documentation](https://featherless.ai/docs) | [Models](https://featherless.ai/models) |
mrizalf7/IndobertNews | mrizalf7 | "2023-02-15T08:44:54Z" | 115 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-02-12T12:10:48Z" | ---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: IndobertNews
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. -->
# IndobertNews
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7050
- Accuracy: 0.7954
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 104 | 0.8639 | 0.7593 |
| No log | 2.0 | 208 | 0.7327 | 0.7870 |
| No log | 3.0 | 312 | 0.7050 | 0.7954 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
|
lfmatosmelo/gpt2-sm-lcc-en-subset-source-domain-prediction | lfmatosmelo | "2024-05-11T21:28:40Z" | 138 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-05-11T21:27:26Z" | ---
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: gpt2-sm-lcc-en-subset-source-domain-prediction
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-sm-lcc-en-subset-source-domain-prediction
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.2.1+cu121
- Datasets 2.4.0
- Tokenizers 0.13.3
|
eslamxm/mt5-base-finetuned-arfa | eslamxm | "2022-05-23T01:44:07Z" | 10 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"summarization",
"arabic",
"ar",
"fa",
"persian",
"Abstractive Summarization",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | "2022-05-22T12:55:58Z" | ---
license: apache-2.0
tags:
- summarization
- arabic
- ar
- fa
- persian
- mt5
- Abstractive Summarization
- generated_from_trainer
model-index:
- name: mt5-base-finetuned-arfa
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. -->
# mt5-base-finetuned-arfa
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1784
- Rouge-1: 25.68
- Rouge-2: 11.8
- Rouge-l: 22.99
- Gen Len: 18.99
- Bertscore: 71.78
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- label_smoothing_factor: 0.1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | Bertscore |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:---------:|
| 3.9866 | 1.0 | 2649 | 3.3635 | 21.94 | 8.59 | 19.5 | 18.99 | 70.6 |
| 3.5637 | 2.0 | 5298 | 3.2557 | 24.01 | 10.0 | 21.26 | 18.99 | 71.22 |
| 3.4016 | 3.0 | 7947 | 3.2005 | 24.4 | 10.43 | 21.72 | 18.98 | 71.36 |
| 3.2985 | 4.0 | 10596 | 3.1784 | 24.68 | 10.73 | 22.01 | 18.98 | 71.51 |
### Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
|
osanseviero/clip-st | osanseviero | "2021-05-17T08:59:53Z" | 3 | 0 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"distilbert",
"feature-extraction",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | feature-extraction | "2022-03-02T23:29:05Z" | ---
tags:
- sentence-transformers
- feature-extraction
---
# TODO: Name of Model
TODO: Description
## Model Description
TODO: Add relevant content
(0) Base Transformer Type: DistilBertModel
(1) Pooling mean
(2) Dense 768x512
## Usage (Sentence-Transformers)
Using this model becomes more convenient when you have [sentence-transformers](https://github.com/UKPLab/sentence-transformers) 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"]
model = SentenceTransformer(TODO)
embeddings = model.encode(sentences)
print(embeddings)
```
## TODO: Training Procedure
## TODO: Evaluation Results
## TODO: Citing & Authors
|
marthakk/swin-tiny-patch4-window7-224-finetuned-eurosat | marthakk | "2024-10-30T12:33:40Z" | 227 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swin-tiny-patch4-window7-224",
"base_model:finetune:microsoft/swin-tiny-patch4-window7-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2024-10-22T09:59:55Z" | ---
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
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: 0.8553054662379421
- name: Precision
type: precision
value: 0.8675973805921082
- name: Recall
type: recall
value: 0.8553054662379421
- name: F1
type: f1
value: 0.8581712564304036
---
<!-- 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-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2816
- Accuracy: 0.8553
- Precision: 0.8676
- Recall: 0.8553
- F1: 0.8582
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.5793 | 1.0 | 22 | 0.5874 | 0.6785 | 0.4603 | 0.6785 | 0.5485 |
| 0.3711 | 2.0 | 44 | 0.4135 | 0.7781 | 0.8169 | 0.7781 | 0.7395 |
| 0.2961 | 3.0 | 66 | 0.2816 | 0.8553 | 0.8676 | 0.8553 | 0.8582 |
| 0.2576 | 4.0 | 88 | 0.2899 | 0.7942 | 0.7884 | 0.7942 | 0.7857 |
| 0.261 | 5.0 | 110 | 0.2469 | 0.8103 | 0.8057 | 0.8103 | 0.8037 |
| 0.2559 | 6.0 | 132 | 0.2548 | 0.8360 | 0.8632 | 0.8360 | 0.8179 |
| 0.2249 | 7.0 | 154 | 0.2835 | 0.8135 | 0.8479 | 0.8135 | 0.7882 |
| 0.2242 | 8.0 | 176 | 0.2335 | 0.8296 | 0.8261 | 0.8296 | 0.8262 |
| 0.2215 | 9.0 | 198 | 0.2293 | 0.8521 | 0.8549 | 0.8521 | 0.8532 |
| 0.2269 | 10.0 | 220 | 0.2213 | 0.8424 | 0.8396 | 0.8424 | 0.8393 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
|
huggingtweets/h3xenbrenner2-s4m31p4n-tallbart | huggingtweets | "2022-11-07T00:22:34Z" | 107 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2022-11-07T00:22:25Z" | ---
language: en
thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1396839225249734657/GG6ve7Qv_400x400.jpg')">
</div>
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1542608466077855744/a0q2rR-P_400x400.png')">
</div>
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1529675700772302848/uXtYNx_v_400x400.jpg')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI CYBORG 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">h b & very tall bart & ppigg</div>
<div style="text-align: center; font-size: 14px;">@h3xenbrenner2-s4m31p4n-tallbart</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from h b & very tall bart & ppigg.
| Data | h b | very tall bart | ppigg |
| --- | --- | --- | --- |
| Tweets downloaded | 1230 | 3194 | 3008 |
| Retweets | 75 | 381 | 957 |
| Short tweets | 155 | 569 | 643 |
| Tweets kept | 1000 | 2244 | 1408 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/34qe4a18/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @h3xenbrenner2-s4m31p4n-tallbart's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/kg3j88xz) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/kg3j88xz/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/h3xenbrenner2-s4m31p4n-tallbart')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
semamark0902/digit-recognition | semamark0902 | "2025-04-02T19:31:55Z" | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | "2025-04-02T19:31:55Z" | ---
license: apache-2.0
---
|
Phoenix21/llama-3-2-3b-finetuned-finance_checkpoint2 | Phoenix21 | "2025-03-14T00:20:13Z" | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-3.2-3B",
"base_model:adapter:meta-llama/Llama-3.2-3B",
"region:us"
] | null | "2025-03-14T00:19:57Z" | ---
base_model: meta-llama/Llama-3.2-3B
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.14.0 |
auxyus/f4a242a5-b26d-4578-b5f8-86bb6e882ed5 | auxyus | "2025-02-06T08:14:05Z" | 8 | 0 | peft | [
"peft",
"safetensors",
"qwen2",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/Qwen2-1.5B",
"base_model:adapter:unsloth/Qwen2-1.5B",
"license:apache-2.0",
"region:us"
] | null | "2025-02-06T08:03:52Z" | ---
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2-1.5B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: f4a242a5-b26d-4578-b5f8-86bb6e882ed5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: unsloth/Qwen2-1.5B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- b8f3cfbc19c4aecb_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/b8f3cfbc19c4aecb_train_data.json
type:
field_input: task_category
field_instruction: justification
field_output: enhanced_snippet
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: auxyus/f4a242a5-b26d-4578-b5f8-86bb6e882ed5
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 400
micro_batch_size: 8
mlflow_experiment_name: /tmp/b8f3cfbc19c4aecb_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1.0e-05
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: cf30f231-10f9-4149-9933-0931077f8890
wandb_project: Gradients-On-Two
wandb_run: your_name
wandb_runid: cf30f231-10f9-4149-9933-0931077f8890
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
```
</details><br>
# f4a242a5-b26d-4578-b5f8-86bb6e882ed5
This model is a fine-tuned version of [unsloth/Qwen2-1.5B](https://huggingface.co/unsloth/Qwen2-1.5B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8988
## 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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 195
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.3805 | 0.0154 | 1 | 2.2766 |
| 0.7744 | 0.7692 | 50 | 0.8201 |
| 0.5663 | 1.5385 | 100 | 0.8034 |
| 0.3775 | 2.3077 | 150 | 0.8988 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF | MaziyarPanahi | "2024-01-26T06:35:29Z" | 107 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"merge",
"mergekit",
"7b",
"lazymergekit",
"mistralai/Mistral-7B-Instruct-v0.2",
"uukuguy/CollectiveCognition-v1.1-Mistral-7B-dare-0.85",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp",
"base_model:quantized:MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp",
"conversational"
] | text-generation | "2024-01-24T21:31:37Z" | ---
license: apache-2.0
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- 7b
- lazymergekit
- mistralai/Mistral-7B-Instruct-v0.2
- uukuguy/CollectiveCognition-v1.1-Mistral-7B-dare-0.85
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
model_name: CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF
base_model: MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp](https://huggingface.co/MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp)
## Description
[MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF) contains GGUF format model files for [MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp](https://huggingface.co/MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF) and below it, a specific filename to download, such as: CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF](https://huggingface.co/MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./CollectiveCognition-v1.1-Mistral-7B-dare-0.85-Mistral-7B-Instruct-v0.2-slerp-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) |
justinsiow/Reinforce-Pixelcopter-PLE-v0 | justinsiow | "2023-04-10T09:07:20Z" | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-04-10T09:07:16Z" | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 21.40 +/- 19.42
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
|
lu-vae/qwen1.5-7b-fft | lu-vae | "2024-05-05T12:09:29Z" | 10 | 0 | transformers | [
"transformers",
"pytorch",
"qwen2",
"text-generation",
"generated_from_trainer",
"base_model:Qwen/Qwen1.5-7B",
"base_model:finetune:Qwen/Qwen1.5-7B",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-05-05T11:39:51Z" | ---
license: other
base_model: Qwen/Qwen1.5-7B
tags:
- generated_from_trainer
model-index:
- name: qwen1.5-7b-fft
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.0`
```yaml
base_model: Qwen/Qwen1.5-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: /data/data/final_set_cleaned/train/
type: sharegpt
conversation: chatml
- path: /data/data/map_coig_cqia.jsonl
type: sharegpt
conversation: chatml
- path: /data/data/ruozhiba.jsonl
type: sharegpt
conversation: chatml
- path: /data/data/sharegpt4.jsonl
type: sharegpt
conversation: chatml
- path: /data/data/OpenHermes-Zh.jsonl
type: sharegpt
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project: FFT
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.05
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 4
save_total_limit: 8
debug:
deepspeed: deepspeed/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
default_system_message: "You are a helpful assistant."
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<|end_of_text|>"
```
</details><br>
# qwen1.5-7b-fft
This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 8
- total_train_batch_size: 48
- total_eval_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 48
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.40.1
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.19.1
|
unsloth/c4ai-command-a-03-2025-GGUF | unsloth | "2025-03-14T09:35:28Z" | 0 | 0 | transformers | [
"transformers",
"gguf",
"cohere2",
"text-generation",
"en",
"fr",
"de",
"es",
"it",
"pt",
"ja",
"ko",
"zh",
"ar",
"el",
"fa",
"pl",
"id",
"cs",
"he",
"hi",
"nl",
"ro",
"ru",
"tr",
"uk",
"vi",
"base_model:CohereForAI/c4ai-command-a-03-2025",
"base_model:quantized:CohereForAI/c4ai-command-a-03-2025",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"region:us",
"conversational"
] | text-generation | "2025-03-14T06:16:10Z" | ---
base_model: CohereForAI/c4ai-command-a-03-2025
inference: false
library_name: transformers
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
extra_gated_prompt: "By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll receive email updates about C4AI and Cohere research, events, products and services. You can unsubscribe at any time."
extra_gated_fields:
Name: text
Affiliation: text
Country: country
I agree to use this model for non-commercial use ONLY: checkbox
---
# **Model Card for C4AI Command A**
## **Model Summary**
C4AI Command A is an open weights research release of a 111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI. Compared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks while being deployable on just two GPUs.
Developed by: [Cohere](https://cohere.com/) and [Cohere For AI](https://cohere.for.ai/)
* Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/)
* License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)
* Model: c4ai-command-a-03-2025
* Model Size: 111 billion parameters
* Context length: 256K
**Try C4AI Command A**
You can try out C4AI Command A before downloading the weights in our hosted [Hugging Face Space](https://cohereforai-c4ai-command.hf.space/models/command-a-03-2025).
**Usage**
Please install transformers from the source repository that includes the necessary changes for this model.
```py
# pip install transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "CohereForAI/c4ai-command-a-03-2025"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Format message with the c4ai-command-a-03-2025 chat template
messages = [{"role": "user", "content": "Hello, how are you?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
gen_tokens = model.generate(
input_ids,
max_new_tokens=100,
do_sample=True,
temperature=0.3,
)
gen_text = tokenizer.decode(gen_tokens[0])
print(gen_text)
```
## **Model Details**
**Input**: Models input text only.
**Output**: Models generate text only.
**Model Architecture**: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. The model features three layers with **sliding window attention** (window size 4096\) and **RoPE** for efficient local context modeling and relative positional encoding. A fourth layer uses **global attention** without positional embeddings, enabling unrestricted token interactions across the entire sequence.
**Languages covered**: The model has been trained on 23 languages: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Chinese, Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian.
**Context Length**: Command A supports a context length of 256K.
###
### **Chat Capabilities:**
By default, Command A is configured as a conversational model. A preamble conditions the model on interactive behaviour, meaning it is expected to reply in a conversational fashion, provides introductory statements and follow-up questions, and uses Markdown as well as LaTeX where appropriate. This is desired for interactive experiences, such as chatbots, where the model engages in dialogue.
In other use cases, a non-interactive model behavior might be more desired (e.g. task-focused use cases like extracting information, summarizing text, translation, and categorization). Learn how system messages can be used to achieve such non-interactive behavior [here](https://docs.cohere.com/docs/command-a-hf#obtaining-non-interactive-behavior).
Besides, Command A can be configured with two safety modes, which enable users to set guardrails that are both safe and suitable to their needs: contextual mode, or strict mode. Contextual mode is appropriate for wide-ranging interactions with fewer constraints on output, while maintaining core protections by rejecting harmful or illegal suggestions. Command A is configured to contextual mode by default. Strict mode aims to avoid all sensitive topics, such as violent or sexual acts and profanity. For more information, see the [Command A prompt format docs](https://docs.cohere.com/docs/command-a-hf).
###
### **RAG Capabilities:**
Command A has been trained specifically for tasks like the final step of Retrieval Augmented Generation (RAG).
RAG with Command A is supported through [chat templates](https://huggingface.co/docs/transformers/main/en/chat_templating#advanced-retrieval-augmented-generation) in Transformers. The model takes a conversation as input (with an optional user-supplied system preamble), along with a list of document snippets.
<details>
<summary><b>RAG Example [CLICK TO EXPAND]</b></summary>
```py
# Define conversation input
conversation = [{"role": "user", "content": "What has Man always dreamed of?"}]
# Define documents for retrieval-based generation
documents = [
{"heading": "The Moon: Our Age-Old Foe", "body": "Man has always dreamed of destroying the moon. In this essay, I shall..."},
{"heading": "Love is all you need", "body": "Man's dream has always been to find love. This profound lesson..."},
]
# Get the RAG prompt
input_prompt = tokenizer.apply_chat_template(
conversation=conversation,
documents=documents,
tokenize=False,
add_generation_prompt=True,
return_tensors="pt",
)
# Tokenize the prompt
input_ids = tokenizer.encode_plus(input_prompt, return_tensors="pt")
```
You can then generate text from this input as normal.
Document snippets should be short chunks, rather than long documents, typically around 100-400 words per chunk, formatted as key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.
You may find that simply including relevant documents directly in a user message works just as well, or better than using the documents parameter to render the special RAG template. The RAG template is generally a strong default and is ideal for users wanting citations. We encourage users to play with both, and to evaluate which mode works best for their specific use case.
</details>
Note that this was a very brief introduction to RAG \- for more information, see the Command A prompt format docs and the Transformers [RAG documentation](https://huggingface.co/docs/transformers/main/chat_templating#advanced-retrieval-augmented-generation).
<details>
<summary><b>RAG with citations [CLICK TO EXPAND]</b></summary>
Optionally, one can ask the model to include grounding spans (citations) in its response to indicate the source of the information. The code is the same as before, except for this line.
```py
# Get the Grounded Generation prompt, with citations
input_prompt = tokenizer.apply_chat_template(
conversation=conversation,
documents=documents,
tokenize=False,
add_generation_prompt=True,
return_tensors="pt",
enable_citations=True,
)
# There are two answers to this question. Man has dreamed of <co>destroying the moon</co: 0:[0]> and <co>finding love.</co: 0:[1]>
```
The output looks like this: the model will associate pieces of texts (called "spans") with specific document snippets that support them (called "sources"). Command A uses a pair of tags "\<co\>" and "\</co\>" to indicate when a span can be grounded onto a list of sources. For example, "\<co\>span\</co: 0:\[0,1\]\>" means that "span" is supported by documents snippets 0 and 1 that were provided in the last message.
</details>
### **Tool Use Capabilities:**
Command A has been specifically trained with conversational tool use capabilities. This allows the model to interact with external tools like APIs, databases, or search engines.
Tool use with Command A is supported through [chat templates](https://huggingface.co/docs/transformers/main/en/chat_templating#advanced-tool-use--function-calling) in Transformers. We recommend providing tool descriptions using JSON schema.
<details>
<summary><b>Tool Use Example [CLICK TO EXPAND]</b></summary>
```py
# Define tools
tools = [{
"type": "function",
"function": {
"name": "query_daily_sales_report",
"description": "Connects to a database to retrieve overall sales volumes and sales information for a given day.",
"parameters": {
"type": "object",
"properties": {
"day": {
"description": "Retrieves sales data for this day, formatted as YYYY-MM-DD.",
"type": "string",
}
},
"required": ["day"]
},
}
}]
# Define conversation input
conversation = [{"role": "user", "content": "Can you provide a sales summary for 29th September 2023?"}]
# Get the Tool Use prompt
input_prompt = tokenizer.apply_chat_template(conversation=conversation, tools=tools, tokenize=False, add_generation_prompt=True, return_tensors="pt"))
# Tokenize the prompt
input_ids = tokenizer.encode_plus(input_prompt, return_tensors="pt")
```
You can then generate from this input as normal.
If the model generates a plan and tool calls, you should add them to the chat history like so:
```py
tool_call = {"name": "query_daily_sales_report", "arguments": {"day": "2023-09-29"}}
tool_plan = "I will use the query_daily_sales_report tool to find the sales summary for 29th September 2023."
conversation.append({"role": "assistant", "tool_calls": [{"id": "0", "type": "function", "function": tool_call}], "tool_plan": tool_plan})
```
and then call the tool and append the result, as a dictionary, with the tool role, like so:
```py
api_response_query_daily_sales_report = {"date": "2023-09-29", "summary": "Total Sales Amount: 10000, Total Units Sold: 250"} # this needs to be a dictionary!!
# Append tool results
conversation.append({"role": "tool", "tool_call_id": "0", "content": api_response_query_daily_sales_report})
```
After that, you can generate() again to let the model use the tool result in the chat.
</details>
Note that this was a very brief introduction to tool calling \- for more information, see [the Command A prompt format docs](https://docs.cohere.com/docs/command-a-hf&sa=D&source=docs&ust=1741857329583678&usg=AOvVaw3sS-2eIfLzShS6c9VWXJWa) and the Transformers [tool use documentation](https://huggingface.co/docs/transformers/main/chat_templating#advanced-tool-use--function-calling).
<details>
<summary><b>Tool Use with citations [CLICK TO EXPAND]</b></summary>
Optionally, one can ask the model to include grounding spans (citations) in its response to indicate the source of the information, by using *enable\_citations=True* in *tokenizer.apply\_chat\_template(*). The generation would look like this:
```
On 29th September 2023, the total sales amount was <co>10000</co: 0:[0]> and the total units sold were <co>250.</co: 0:[0]>
```
When citations are turned on, the model associates pieces of texts (called "spans") with those specific tool results that support them (called "sources"). Command A uses a pair of tags "\<co\>" and "\</co\>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. For example, "\<co\>span\</co: 0:\[1,2\],1:\[0\]\>" means that "span" is supported by result 1 and 2 from "tool\_call\_id=0" as well as result 0 from "tool\_call\_id=1". Sources from the same tool call are grouped together and listed as "{tool\_call\_id}:\[{list of result indices}\]", before they are joined together by ",".
</details>
###
### **Code Capabilities:**
Command A has meaningfully improved on code capabilities. In addition to academic code benchmarks, we have evaluated it on enterprise-relevant scenarios, including SQL generation and code translation, where it outperforms other models of similar size. Try these out by requesting code snippets, code explanations, or code rewrites. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.
## **Model Card Contact**
For errors or additional questions about details in this model card, contact [email protected].
## **Terms of Use:**
We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 111 billion parameter model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License (Non-Commercial) with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)If you are interested in commercial use, please contact [Cohere’s Sales team](https://cohere.com/contact-sales).
## **Try Chat:**
You can try Command A chat in the playground [here](https://dashboard.cohere.com/playground/chat?model=command-a-03-2025). You can also use it in our dedicated Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/c4ai-command).
|
ThomasROBERTparis/SNLP_XAI_hate-speech_Davidson_hate_bert-base-uncased_LoRA_r16_lr0.0001 | ThomasROBERTparis | "2025-03-12T22:13:33Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2025-03-12T22:13:20Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
cleanrl/Asteroids-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed1 | cleanrl | "2023-02-10T05:26:49Z" | 0 | 0 | cleanrl | [
"cleanrl",
"tensorboard",
"Asteroids-v5",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2023-02-05T23:09:48Z" | ---
tags:
- Asteroids-v5
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Asteroids-v5
type: Asteroids-v5
metrics:
- type: mean_reward
value: 53795.00 +/- 64865.45
name: mean_reward
verified: false
---
# (CleanRL) **PPO** Agent Playing **Asteroids-v5**
This is a trained model of a PPO agent playing Asteroids-v5.
The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be
found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/sebulba_ppo_envpool_impala_atari_wrapper.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[jax,envpool,atari]"
python -m cleanrl_utils.enjoy --exp-name sebulba_ppo_envpool_impala_atari_wrapper --env-id Asteroids-v5
```
Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail.
## Command to reproduce the training
```bash
curl -OL https://huggingface.co/cleanrl/Asteroids-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed1/raw/main/sebulba_ppo_envpool_impala_atari_wrapper.py
curl -OL https://huggingface.co/cleanrl/Asteroids-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed1/raw/main/pyproject.toml
curl -OL https://huggingface.co/cleanrl/Asteroids-v5-sebulba_ppo_envpool_impala_atari_wrapper-seed1/raw/main/poetry.lock
poetry install --all-extras
python sebulba_ppo_envpool_impala_atari_wrapper.py --actor-device-ids 0 --learner-device-ids 1 2 3 4 5 6 --track --save-model --upload-model --hf-entity cleanrl --env-id Asteroids-v5 --seed 1
```
# Hyperparameters
```python
{'actor_device_ids': [0],
'anneal_lr': True,
'async_batch_size': 20,
'async_update': 3,
'batch_size': 7680,
'capture_video': False,
'clip_coef': 0.1,
'cuda': True,
'ent_coef': 0.01,
'env_id': 'Asteroids-v5',
'exp_name': 'sebulba_ppo_envpool_impala_atari_wrapper',
'gae_lambda': 0.95,
'gamma': 0.99,
'hf_entity': 'cleanrl',
'learner_device_ids': [1, 2, 3, 4, 5, 6],
'learning_rate': 0.00025,
'max_grad_norm': 0.5,
'minibatch_size': 1920,
'norm_adv': True,
'num_actor_threads': 1,
'num_envs': 60,
'num_minibatches': 4,
'num_steps': 128,
'num_updates': 6510,
'profile': False,
'save_model': True,
'seed': 1,
'target_kl': None,
'test_actor_learner_throughput': False,
'torch_deterministic': True,
'total_timesteps': 50000000,
'track': True,
'update_epochs': 4,
'upload_model': True,
'vf_coef': 0.5,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}
```
|
mradermacher/recoilme-gemma-2-9B-v0.2-GGUF | mradermacher | "2025-03-08T22:11:41Z" | 223 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:recoilme/recoilme-gemma-2-9B-v0.2",
"base_model:quantized:recoilme/recoilme-gemma-2-9B-v0.2",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2025-03-07T19:49:29Z" | ---
base_model: recoilme/recoilme-gemma-2-9B-v0.2
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/recoilme/recoilme-gemma-2-9B-v0.2
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q2_K.gguf) | Q2_K | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.IQ4_XS.gguf) | IQ4_XS | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q5_K_S.gguf) | Q5_K_S | 6.6 | |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q5_K_M.gguf) | Q5_K_M | 6.7 | |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/recoilme-gemma-2-9B-v0.2-GGUF/resolve/main/recoilme-gemma-2-9B-v0.2.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
kporzycki/Reinforce-cart-pole | kporzycki | "2023-10-09T17:29:16Z" | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-10-09T10:37:07Z" | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-cart-pole
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
mradermacher/Rocstoriesinstruct2_tinyllama-GGUF | mradermacher | "2025-03-13T22:17:54Z" | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Elcaida/Rocstoriesinstruct2_tinyllama",
"base_model:quantized:Elcaida/Rocstoriesinstruct2_tinyllama",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2025-03-13T22:10:43Z" | ---
base_model: Elcaida/Rocstoriesinstruct2_tinyllama
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Elcaida/Rocstoriesinstruct2_tinyllama
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q2_K.gguf) | Q2_K | 0.5 | |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q3_K_S.gguf) | Q3_K_S | 0.6 | |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q3_K_L.gguf) | Q3_K_L | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.IQ4_XS.gguf) | IQ4_XS | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q5_K_S.gguf) | Q5_K_S | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q5_K_M.gguf) | Q5_K_M | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q6_K.gguf) | Q6_K | 1.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Rocstoriesinstruct2_tinyllama-GGUF/resolve/main/Rocstoriesinstruct2_tinyllama.f16.gguf) | f16 | 2.3 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/Qwen2.5-7B-olm-v1.1-GGUF | mradermacher | "2024-12-30T03:14:17Z" | 28 | 1 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"en",
"base_model:jeffmeloy/Qwen2.5-7B-olm-v1.1",
"base_model:quantized:jeffmeloy/Qwen2.5-7B-olm-v1.1",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2024-12-30T00:33:40Z" | ---
base_model: jeffmeloy/Qwen2.5-7B-olm-v1.1
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.1
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.1-GGUF/resolve/main/Qwen2.5-7B-olm-v1.1.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Maciel/T5Corrector-base-v2 | Maciel | "2023-05-23T05:56:48Z" | 145 | 14 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"text error correction",
"zh",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2023-03-12T08:59:14Z" | ---
language:
- zh
license: apache-2.0
tags:
- t5
- text error correction
widget:
- text: "今天天气不太好，我的心情也不是很偷快"
example_title: "案例1"
- text: "能不能帮我买点淇淋，好久没吃了。"
example_title: "案例2"
- text: "脑子有点胡涂了，这道题冥冥学过还没有做出来"
example_title: "案例3"
inference:
parameters:
max_length: 256
num_beams: 10
no_repeat_ngram_size: 5
do_sample: True
early_stopping: True
---
## 功能介绍
T5Corrector：中文字音与字形纠错模型
这个模型是基于mengzi-t5-base进行文本纠错训练，使用2kw+句子，通过替换同音词、近音词和形近字来，对于句中词组随机添加词组、删除词组中的部分字，以及字词乱序操作构造纠错平行语料，共计2亿+句对，累计训练66000步。
<a href='https://github.com/Macielyoung/T5Corrector'>Github项目地址</a>
加载模型：
```python
# 加载模型
from transformers import AutoTokenizer, T5ForConditionalGeneration
pretrained = "Maciel/T5Corrector-base-v2"
tokenizer = AutoTokenizer.from_pretrained(pretrained)
model = T5ForConditionalGeneration.from_pretrained(pretrained)
```
使用模型进行预测推理方法：
```python
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
def correct(text, max_length):
model_inputs = tokenizer(text,
max_length=max_length,
truncation=True,
return_tensors="pt").to(device)
output = model.generate(**model_inputs,
num_beams=5,
no_repeat_ngram_size=4,
do_sample=True,
early_stopping=True,
max_length=max_length,
return_dict_in_generate=True,
output_scores=True)
pred_output = tokenizer.batch_decode(output.sequences, skip_special_tokens=True)[0]
return pred_output
text = "贵州毛台现在多少钱一瓶啊，想买两瓶尝尝味道。"
correction = correct(text, max_length=32)
print(correction)
```
### 案例展示
```
示例1:
input: 能不能帮我买点淇淋，好久没吃了。
output: 能不能帮我买点冰淇淋，好久没吃了。
示例2:
input: 脑子有点胡涂了，这道题冥冥学过还没有做出来
output: 脑子有点糊涂了,这道题明明学过还没有做出来
示例3:
input: 今天天气不太好，我的心情也不是很偷快
output: 今天天气不太好,我的心情也不是很愉快
``` |
toshi456/llava-jp-1.3b-v1.0-620k | toshi456 | "2024-04-20T12:32:13Z" | 53 | 0 | transformers | [
"transformers",
"safetensors",
"llava-jp",
"text-generation",
"vision",
"image-captioning",
"VQA",
"image-to-text",
"ja",
"dataset:turing-motors/LLaVA-Pretrain-JA",
"dataset:turing-motors/LLaVA-v1.5-Instruct-620K-JA",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-to-text | "2024-04-20T08:21:04Z" | ---
license: cc-by-nc-4.0
datasets:
- turing-motors/LLaVA-Pretrain-JA
- turing-motors/LLaVA-v1.5-Instruct-620K-JA
language:
- ja
pipeline_tag: image-to-text
tags:
- vision
- image-captioning
- VQA
---
# LLaVA-JP Model Card
## Model detail
**Model type:**
LLaVA-JP is a vision-language model that can converse about input images.<br>
This model was trained by fine-tuning [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0) using [LLaVA](https://llava-vl.github.io/) method and [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) is used as Image Encoder.
**Training:**
This model was initially trained with the Vision Projector using LLaVA-Pretrain-JA.<br>
In the second phase, it was fine-tuned with LLaVA-v1.5-Instruct-620K-JA.
resources for more information: https://github.com/tosiyuki/LLaVA-JP/tree/main
## How to use the model
**1. Download dependencies**
```
git clone https://github.com/tosiyuki/LLaVA-JP.git
```
**2. Inference**
```python
import requests
import torch
import transformers
from PIL import Image
from transformers.generation.streamers import TextStreamer
from llava.constants import DEFAULT_IMAGE_TOKEN, IMAGE_TOKEN_INDEX
from llava.conversation import conv_templates, SeparatorStyle
from llava.model.llava_gpt2 import LlavaGpt2ForCausalLM
from llava.train.arguments_dataclass import ModelArguments, DataArguments, TrainingArguments
from llava.train.dataset import tokenizer_image_token
if __name__ == "__main__":
parser = transformers.HfArgumentParser(
(ModelArguments, DataArguments, TrainingArguments))
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
model_path = 'toshi456/llava-jp-1.3b-v1.0-620k'
device = "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.bfloat16 if device=="cuda" else torch.float32
model = LlavaGpt2ForCausalLM.from_pretrained(
model_path,
low_cpu_mem_usage=True,
use_safetensors=True,
torch_dtype=torch_dtype,
device_map=device,
)
tokenizer = transformers.AutoTokenizer.from_pretrained(
model_path,
model_max_length=1532,
padding_side="right",
use_fast=False,
)
model.eval()
conv_mode = "v1"
conv = conv_templates[conv_mode].copy()
# image pre-process
image_url = "https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4/resolve/main/sample.jpg"
image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
image_size = model.get_model().vision_tower.image_processor.size["height"]
if model.get_model().vision_tower.scales is not None:
image_size = model.get_model().vision_tower.image_processor.size["height"] * len(model.get_model().vision_tower.scales)
if device == "cuda":
image_tensor = model.get_model().vision_tower.image_processor(
image,
return_tensors='pt',
size={"height": image_size, "width": image_size}
)['pixel_values'].half().cuda().to(torch_dtype)
else:
image_tensor = model.get_model().vision_tower.image_processor(
image,
return_tensors='pt',
size={"height": image_size, "width": image_size}
)['pixel_values'].to(torch_dtype)
# create prompt
# ユーザー: <image>\n{prompt}
prompt = "猫の隣には何がありますか？"
inp = DEFAULT_IMAGE_TOKEN + '\n' + prompt
conv.append_message(conv.roles[0], inp)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(
prompt,
tokenizer,
IMAGE_TOKEN_INDEX,
return_tensors='pt'
).unsqueeze(0)
if device == "cuda":
input_ids = input_ids.to(device)
input_ids = input_ids[:, :-1] # </sep>がinputの最後に入るので削除する
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
streamer = TextStreamer(tokenizer, skip_prompt=True, timeout=20.0)
# predict
with torch.inference_mode():
model.generate(
inputs=input_ids,
images=image_tensor,
do_sample=True,
temperature=0.01,
top_p=1.0,
max_new_tokens=256,
streamer=streamer,
use_cache=True,
)
"""猫の隣にはノートパソコンがあります。"""
```
## Training dataset
**Stage1 Pretrain**
- [LLaVA-Pretrain-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Pretrain-JA)
**Stage2 Fine-tuning**
- [LLaVA-v1.5-Instruct-620K-JA](https://huggingface.co/datasets/turing-motors/LLaVA-v1.5-Instruct-620K-JA)
## Acknowledgement
- [LLaVA](https://llava-vl.github.io/)
- [LLM-jp](https://llm-jp.nii.ac.jp/)
## License
cc-by-nc-4.0 |
alinerodrigues/wav2vec2-xlsr-1b-mecita-portuguese-all-05 | alinerodrigues | "2024-02-28T16:58:49Z" | 1 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | "2024-02-28T13:35:12Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-1b-mecita-portuguese-all-05
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wav2vec2-xlsr-1b-mecita-portuguese-all-05
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-xls-r-1b-portuguese](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-portuguese) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1759
- Wer: 0.0948
- Cer: 0.0332
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 27.2023 | 1.0 | 86 | 0.3596 | 0.2338 | 0.0682 |
| 3.376 | 2.0 | 172 | 0.2263 | 0.1195 | 0.0414 |
| 0.4098 | 3.0 | 258 | 0.2067 | 0.1091 | 0.0387 |
| 0.3262 | 4.0 | 344 | 0.2059 | 0.1081 | 0.0380 |
| 0.3068 | 5.0 | 430 | 0.1949 | 0.1016 | 0.0360 |
| 0.239 | 6.0 | 516 | 0.1934 | 0.0948 | 0.0346 |
| 0.2351 | 7.0 | 602 | 0.1824 | 0.0946 | 0.0339 |
| 0.2351 | 8.0 | 688 | 0.1759 | 0.0948 | 0.0332 |
| 0.2205 | 9.0 | 774 | 0.1813 | 0.0902 | 0.0330 |
| 0.2055 | 10.0 | 860 | 0.1898 | 0.0892 | 0.0321 |
| 0.1882 | 11.0 | 946 | 0.1877 | 0.0912 | 0.0330 |
| 0.1787 | 12.0 | 1032 | 0.1844 | 0.0921 | 0.0321 |
| 0.1622 | 13.0 | 1118 | 0.1839 | 0.0861 | 0.0318 |
| 0.1676 | 14.0 | 1204 | 0.1852 | 0.0846 | 0.0316 |
| 0.1676 | 15.0 | 1290 | 0.1801 | 0.0902 | 0.0324 |
| 0.165 | 16.0 | 1376 | 0.1870 | 0.0810 | 0.0309 |
| 0.143 | 17.0 | 1462 | 0.1834 | 0.0827 | 0.0310 |
| 0.1329 | 18.0 | 1548 | 0.1815 | 0.0815 | 0.0309 |
| 0.149 | 19.0 | 1634 | 0.1822 | 0.0817 | 0.0310 |
| 0.1251 | 20.0 | 1720 | 0.1831 | 0.0824 | 0.0306 |
| 0.1243 | 21.0 | 1806 | 0.1819 | 0.0817 | 0.0304 |
| 0.1243 | 22.0 | 1892 | 0.1859 | 0.0854 | 0.0309 |
| 0.1195 | 23.0 | 1978 | 0.1841 | 0.0803 | 0.0300 |
| 0.1214 | 24.0 | 2064 | 0.1881 | 0.0824 | 0.0317 |
| 0.1179 | 25.0 | 2150 | 0.1898 | 0.0824 | 0.0309 |
| 0.1004 | 26.0 | 2236 | 0.2005 | 0.0863 | 0.0322 |
| 0.1255 | 27.0 | 2322 | 0.1982 | 0.0834 | 0.0318 |
| 0.1169 | 28.0 | 2408 | 0.1947 | 0.0873 | 0.0324 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.2.1+cu121
- Datasets 2.17.0
- Tokenizers 0.13.3
|
sebastian-hofstaetter/distilbert-dot-margin_mse-T2-msmarco | sebastian-hofstaetter | "2021-03-16T17:03:58Z" | 42 | 2 | transformers | [
"transformers",
"pytorch",
"distilbert",
"feature-extraction",
"dpr",
"dense-passage-retrieval",
"knowledge-distillation",
"en",
"dataset:ms_marco",
"arxiv:2010.02666",
"endpoints_compatible",
"region:us"
] | feature-extraction | "2022-03-02T23:29:05Z" | ---
language: "en"
tags:
- dpr
- dense-passage-retrieval
- knowledge-distillation
datasets:
- ms_marco
---
# Margin-MSE Trained DistilBert for Dense Passage Retrieval
We provide a retrieval trained DistilBert-based model (we call the architecture BERT_Dot). Our model is trained with Margin-MSE using a 3 teacher BERT_Cat (concatenated BERT scoring) ensemble on MSMARCO-Passage.
This instance can be used to **re-rank a candidate set** or **directly for a vector index based dense retrieval**. The architecture is a 6-layer DistilBERT, without architecture additions or modifications (we only change the weights during training) - to receive a query/passage representation we pool the CLS vector. We use the same BERT layers for both query and passage encoding (yields better results, and lowers memory requirements).
If you want to know more about our simple, yet effective knowledge distillation method for efficient information retrieval models for a variety of student architectures that is used for this model instance check out our paper: https://arxiv.org/abs/2010.02666 🎉
For more information, training data, source code, and a minimal usage example please visit: https://github.com/sebastian-hofstaetter/neural-ranking-kd
## Effectiveness on MSMARCO Passage & TREC-DL'19
We trained our model on the MSMARCO standard ("small"-400K query) training triples with knowledge distillation with a batch size of 32 on a single consumer-grade GPU (11GB memory).
For re-ranking we used the top-1000 BM25 results.
### MSMARCO-DEV
| | MRR@10 | NDCG@10 | Recall@1K |
|----------------------------------|--------|---------|-----------------------------|
| BM25 | .194 | .241 | .868 |
| **Margin-MSE BERT_Dot** (Re-ranking) | .332 | .391 | .868 (from BM25 candidates) |
| **Margin-MSE BERT_Dot** (Retrieval) | .323 | .381 | .957 |
### TREC-DL'19
For MRR and Recall we use the recommended binarization point of the graded relevance of 2. This might skew the results when compared to other binarization point numbers.
| | MRR@10 | NDCG@10 | Recall@1K |
|----------------------------------|--------|---------|-----------------------------|
| BM25 | .689 | .501 | .739 |
| **Margin-MSE BERT_Dot** (Re-ranking) | .862 | .712 | .739 (from BM25 candidates) |
| **Margin-MSE BERT_Dot** (Retrieval) | .868 | .697 | .769 |
For more baselines, info and analysis, please see the paper: https://arxiv.org/abs/2010.02666
## Limitations & Bias
- The model inherits social biases from both DistilBERT and MSMARCO.
- The model is only trained on relatively short passages of MSMARCO (avg. 60 words length), so it might struggle with longer text.
## Citation
If you use our model checkpoint please cite our work as:
```
@misc{hofstaetter2020_crossarchitecture_kd,
title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
author={Sebastian Hofst{\"a}tter and Sophia Althammer and Michael Schr{\"o}der and Mete Sertkan and Allan Hanbury},
year={2020},
eprint={2010.02666},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
``` |
hxgdzyuyi/qgyh | hxgdzyuyi | "2024-01-03T06:28:13Z" | 4 | 1 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | "2024-01-03T06:28:08Z" | ---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: A photo of <s0><s1>
output:
url: image-0.png
- text: A photo of <s0><s1>
output:
url: image-1.png
- text: A photo of <s0><s1>
output:
url: image-2.png
- text: A photo of <s0><s1>
output:
url: image-3.png
- text: A photo of <s0><s1>
output:
url: image-4.png
- text: A photo of <s0><s1>
output:
url: image-5.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: A photo of <s0><s1>
license: openrail++
---
# SDXL LoRA DreamBooth - hxgdzyuyi/qgyh
<Gallery />
## Model description
### These are hxgdzyuyi/qgyh LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
## Download model
### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
- **LoRA**: download **[`qgyh.safetensors` here 💾](/hxgdzyuyi/qgyh/blob/main/qgyh.safetensors)**.
- Place it on your `models/Lora` folder.
- On AUTOMATIC1111, load the LoRA by adding `<lora:qgyh:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
- *Embeddings*: download **[`qgyh_emb.safetensors` here 💾](/hxgdzyuyi/qgyh/blob/main/qgyh_emb.safetensors)**.
- Place it on it on your `embeddings` folder
- Use it by adding `qgyh_emb` to your prompt. For example, `A photo of qgyh_emb`
(you need both the LoRA and the embeddings as they were trained together for this LoRA)
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('hxgdzyuyi/qgyh', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='hxgdzyuyi/qgyh', filename='qgyh_emb.safetensors' repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
image = pipeline('A photo of <s0><s1>').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Trigger words
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
to trigger concept `TOK` → use `<s0><s1>` in your prompt
## Details
All [Files & versions](/hxgdzyuyi/qgyh/tree/main).
The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
LoRA for the text encoder was enabled. False.
Pivotal tuning was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
caiiofc/q-Taxi-v3 | caiiofc | "2024-05-27T13:49:59Z" | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2024-05-27T12:26:50Z" | ---
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: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="caiiofc/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"])
```
|
jin-code/lora-7b-2 | jin-code | "2024-02-27T09:45:10Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2024-02-27T09:44:11Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
vicl/canine-s-finetuned-stsb | vicl | "2022-04-01T23:25:04Z" | 4 | 1 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"canine",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-04-01T19:47:18Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: canine-s-finetuned-stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.8397182061195433
---
<!-- 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. -->
# canine-s-finetuned-stsb
This model is a fine-tuned version of [google/canine-s](https://huggingface.co/google/canine-s) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7223
- Pearson: 0.8397
- Spearmanr: 0.8397
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
| No log | 1.0 | 360 | 0.7938 | 0.8083 | 0.8077 |
| 1.278 | 2.0 | 720 | 0.7349 | 0.8322 | 0.8305 |
| 0.6765 | 3.0 | 1080 | 0.7075 | 0.8374 | 0.8366 |
| 0.6765 | 4.0 | 1440 | 0.7586 | 0.8360 | 0.8376 |
| 0.4629 | 5.0 | 1800 | 0.7223 | 0.8397 | 0.8397 |
### Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
|
Nangni/gpt2_friends | Nangni | "2024-06-30T06:25:29Z" | 5 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-06-30T06:07:19Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
paragon-analytics/roberta_persuade | paragon-analytics | "2025-04-04T13:24:24Z" | 5 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-12-26T19:49:43Z" | <!DOCTYPE html>
<html class="" lang="en">
<head>
<meta charset="utf-8" />
<meta
name="viewport"
content="width=device-width, initial-scale=1.0, user-scalable=no"
/>
<meta
name="description"
content="We're on a journey to advance and democratize artificial intelligence through open source and open science."
/>
<meta property="fb:app_id" content="1321688464574422" />
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:site" content="@huggingface" />
<meta
property="og:title"
content="Hugging Face - The AI community building the future."
/>
<meta property="og:type" content="website" />
<title>Hugging Face - The AI community building the future.</title>
<style>
body {
margin: 0;
}
main {
background-color: white;
min-height: 100vh;
padding: 7rem 1rem 8rem 1rem;
text-align: center;
font-family: Source Sans Pro, ui-sans-serif, system-ui, -apple-system,
BlinkMacSystemFont, Segoe UI, Roboto, Helvetica Neue, Arial, Noto Sans,
sans-serif, Apple Color Emoji, Segoe UI Emoji, Segoe UI Symbol,
Noto Color Emoji;
}
img {
width: 6rem;
height: 6rem;
margin: 0 auto 1rem;
}
h1 {
font-size: 3.75rem;
line-height: 1;
color: rgba(31, 41, 55, 1);
font-weight: 700;
box-sizing: border-box;
margin: 0 auto;
}
p, a {
color: rgba(107, 114, 128, 1);
font-size: 1.125rem;
line-height: 1.75rem;
max-width: 28rem;
box-sizing: border-box;
margin: 0 auto;
}
.dark main {
background-color: rgb(11, 15, 25);
}
.dark h1 {
color: rgb(209, 213, 219);
}
.dark p, .dark a {
color: rgb(156, 163, 175);
}
</style>
<script>
// On page load or when changing themes, best to add inline in `head` to avoid FOUC
const key = "_tb_global_settings";
let theme = window.matchMedia("(prefers-color-scheme: dark)").matches
? "dark"
: "light";
try {
const storageTheme = JSON.parse(window.localStorage.getItem(key)).theme;
if (storageTheme) {
theme = storageTheme === "dark" ? "dark" : "light";
}
} catch (e) {}
if (theme === "dark") {
document.documentElement.classList.add("dark");
} else {
document.documentElement.classList.remove("dark");
}
</script>
</head>
<body>
<main>
<img
src="https://cdn-media.huggingface.co/assets/huggingface_logo.svg"
alt=""
/>
<div>
<h1>429</h1>
<p>We had to rate limit you. If you think it's an error, send us <a href="mailto:[email protected]">an email</a></p>
</div>
</main>
</body>
</html> |
ljvmiranda921/tl_calamancy_trf-0.1.0 | ljvmiranda921 | "2024-08-07T05:53:50Z" | 29 | 5 | spacy | [
"spacy",
"token-classification",
"tl",
"dataset:ljvmiranda921/tlunified-ner",
"arxiv:2311.07171",
"license:mit",
"model-index",
"region:us"
] | token-classification | "2023-07-01T09:06:34Z" | ---
tags:
- spacy
- token-classification
language:
- tl
license: mit
arxiv: arxiv.org/abs/2311.07171
library_name: spacy
pipeline_tag: token-classification
model-index:
- name: Medium-sized calamanCy pipeline by L.J. Miranda
results:
- task:
type: token-classification
name: Named Entity Recognition
dataset:
type: tlunified-ner
name: TLUnified-NER
split: test
revision: 3f7dab9d232414ec6204f8d6934b9a35f90a254f
metrics:
- type: f1
value: 0.9034
name: F1
datasets:
- ljvmiranda921/tlunified-ner
metrics:
- f1
---
calamanCy: Tagalog NLP pipelines in spaCy
Paper: arxiv.org/abs/2311.07171
| Feature | Description |
| --- | --- |
| **Name** | `tl_calamancy_trf` |
| **Version** | `0.1.0` |
| **spaCy** | `>=3.5.0,<4.0.0` |
| **Default Pipeline** | `transformer`, `tagger`, `morphologizer`, `parser`, `ner` |
| **Components** | `transformer`, `tagger`, `morphologizer`, `parser`, `ner` |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
| **Sources** | [TLUnified dataset](https://aclanthology.org/2022.lrec-1.703/) (Jan Christian Blaise Cruz and Charibeth Cheng)<br />[UD_Tagalog-TRG](https://universaldependencies.org/treebanks/tl_trg/index.html) (Stephanie Samson, Daniel Zeman, and Mary Ann C. Tan)<br />[UD_Tagalog-Ugnayan](https://universaldependencies.org/treebanks/tl_ugnayan/index.html) (Angelina Aquino) |
| **License** | `MIT` |
| **Author** | [Lester James V. Miranda](https://github.com/ljvmiranda921/calamanCy) |
### Label Scheme
<details>
<summary>View label scheme (120 labels for 4 components)</summary>
| Component | Labels |
| --- | --- |
| **`tagger`** | `ADJ`, `ADJ_PART`, `ADP`, `ADV`, `ADV_PART`, `AUX`, `CCONJ`, `DET`, `DET_ADP`, `DET_PART`, `INTJ`, `NOUN`, `NOUN_PART`, `NUM`, `NUM_PART`, `PART`, `PRON`, `PRON_PART`, `PROPN`, `PUNCT`, `SCONJ`, `VERB`, `VERB_PART` |
| **`morphologizer`** | `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Act`, `Case=Nom\|POS=ADP`, `POS=NOUN`, `POS=PUNCT`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Pass`, `Case=Gen\|POS=ADP`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Aspect=Imp\|Mood=Ind\|POS=VERB\|Voice=Act`, `POS=ADV\|PronType=Dem`, `Foreign=Yes\|POS=NOUN`, `Degree=Pos\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Deixis=Med\|Number=Sing\|POS=PRON\|PronType=Dem`, `Gender=Masc\|POS=PROPN`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Degree=Pos\|Link=Yes\|POS=ADJ`, `POS=ADP`, `Case=Dat\|POS=ADP`, `POS=VERB\|Polarity=Pos`, `Aspect=Hab\|POS=VERB`, `POS=SCONJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Aspect=Prosp\|Mood=Ind\|POS=VERB\|Voice=Act`, `POS=ADV`, `POS=PART\|Polarity=Neg`, `Aspect=Imp\|Mood=Ind\|POS=VERB\|Voice=Pass`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Lfoc`, `POS=PROPN`, `Case=Nom\|Deixis=Prox\|Number=Sing\|POS=PRON\|PronType=Dem`, `Gender=Masc\|POS=NOUN`, `Gender=Fem\|POS=NOUN`, `Degree=Pos\|Gender=Fem\|POS=ADJ`, `Gender=Fem\|POS=PROPN`, `Case=Nom\|Clusivity=In\|Number=Dual\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Plur\|POS=DET\|PronType=Ind`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `POS=PRON\|PronType=Prs\|Reflex=Yes`, `Gender=Masc\|POS=DET\|PronType=Emp`, `Case=Nom\|POS=PRON\|PronType=Int`, `Link=Yes\|POS=NOUN`, `POS=PART\|PartType=Int`, `POS=INTJ\|Polarity=Pos`, `Link=Yes\|POS=PART\|PartType=Int`, `POS=VERB\|Polarity=Neg`, `Degree=Pos\|POS=ADJ\|PronType=Int`, `Case=Gen\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|PronType=Int\|Voice=Act`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|PronType=Int\|Voice=Pass`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Ifoc`, `POS=ADV\|PronType=Int`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Act`, `POS=PART\|PartType=Nfh`, `Deixis=Remt\|POS=ADV\|PronType=Dem`, `Aspect=Imp\|Mood=Pot\|POS=VERB\|Voice=Act`, `Link=Yes\|POS=VERB\|Polarity=Pos`, `Link=Yes\|POS=VERB\|Polarity=Neg`, `POS=PART\|PartType=Des`, `Mood=Imp\|POS=AUX\|Polarity=Neg`, `Case=Nom\|Link=Yes\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Nom\|Link=Yes\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Pass`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Lfoc`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Bfoc`, `POS=DET\|PronType=Tot`, `Case=Dat\|Link=Yes\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Link=Yes\|POS=PRON\|PronType=Prs\|Reflex=Yes`, `Mood=Imp\|POS=VERB\|Voice=Act`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Mood=Imp\|POS=VERB\|Voice=Lfoc`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Mood=Imp\|POS=VERB\|Voice=Pass`, `Case=Gen\|Clusivity=In\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Aspect=Hab\|POS=VERB\|Voice=Pass`, `Gender=Masc\|Link=Yes\|POS=PROPN`, `Case=Gen\|Link=Yes\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Link=Yes\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `POS=ADJ`, `POS=PART`, `POS=PRON`, `POS=VERB`, `POS=INTJ`, `POS=CCONJ`, `POS=NUM`, `POS=DET` |
| **`parser`** | `ROOT`, `advmod`, `case`, `dep`, `nmod`, `nsubj`, `obj`, `obl`, `punct` |
| **`ner`** | `LOC`, `ORG`, `PER` |
</details>
### Citation
```
@inproceedings{miranda-2023-calamancy,
title = "calaman{C}y: A {T}agalog Natural Language Processing Toolkit",
author = "Miranda, Lester James",
booktitle = "Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)",
month = dec,
year = "2023",
address = "Singapore, Singapore",
publisher = "Empirical Methods in Natural Language Processing",
url = "https://aclanthology.org/2023.nlposs-1.1",
pages = "1--7",
}
``` |
hgnoi/5TFhsfWwnCZtBADz | hgnoi | "2024-05-24T09:26:13Z" | 134 | 0 | transformers | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-05-24T09:24:45Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
KONIexp/test_instructed_model_20250208 | KONIexp | "2025-02-08T11:55:29Z" | 23 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-02-08T11:51:12Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
derek33125/PA-stage2-Qwen7B-147 | derek33125 | "2025-04-09T12:57:06Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"grpo",
"conversational",
"en",
"base_model:derek33125/PA-stage1-Qwen7B-300",
"base_model:finetune:derek33125/PA-stage1-Qwen7B-300",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-04-09T12:51:54Z" | <!DOCTYPE html>
<html class="" lang="en">
<head>
<meta charset="utf-8" />
<meta
name="viewport"
content="width=device-width, initial-scale=1.0, user-scalable=no"
/>
<meta
name="description"
content="We're on a journey to advance and democratize artificial intelligence through open source and open science."
/>
<meta property="fb:app_id" content="1321688464574422" />
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:site" content="@huggingface" />
<meta
property="og:title"
content="Hugging Face - The AI community building the future."
/>
<meta property="og:type" content="website" />
<title>Hugging Face - The AI community building the future.</title>
<style>
body {
margin: 0;
}
main {
background-color: white;
min-height: 100vh;
padding: 7rem 1rem 8rem 1rem;
text-align: center;
font-family: Source Sans Pro, ui-sans-serif, system-ui, -apple-system,
BlinkMacSystemFont, Segoe UI, Roboto, Helvetica Neue, Arial, Noto Sans,
sans-serif, Apple Color Emoji, Segoe UI Emoji, Segoe UI Symbol,
Noto Color Emoji;
}
img {
width: 6rem;
height: 6rem;
margin: 0 auto 1rem;
}
h1 {
font-size: 3.75rem;
line-height: 1;
color: rgba(31, 41, 55, 1);
font-weight: 700;
box-sizing: border-box;
margin: 0 auto;
}
p, a {
color: rgba(107, 114, 128, 1);
font-size: 1.125rem;
line-height: 1.75rem;
max-width: 28rem;
box-sizing: border-box;
margin: 0 auto;
}
.dark main {
background-color: rgb(11, 15, 25);
}
.dark h1 {
color: rgb(209, 213, 219);
}
.dark p, .dark a {
color: rgb(156, 163, 175);
}
</style>
<script>
// On page load or when changing themes, best to add inline in `head` to avoid FOUC
const key = "_tb_global_settings";
let theme = window.matchMedia("(prefers-color-scheme: dark)").matches
? "dark"
: "light";
try {
const storageTheme = JSON.parse(window.localStorage.getItem(key)).theme;
if (storageTheme) {
theme = storageTheme === "dark" ? "dark" : "light";
}
} catch (e) {}
if (theme === "dark") {
document.documentElement.classList.add("dark");
} else {
document.documentElement.classList.remove("dark");
}
</script>
</head>
<body>
<main>
<img
src="https://cdn-media.huggingface.co/assets/huggingface_logo.svg"
alt=""
/>
<div>
<h1>429</h1>
<p>We had to rate limit you. If you think it's an error, send us <a href="mailto:[email protected]">an email</a></p>
</div>
</main>
</body>
</html> |
Zintoulou/codellamafinetune4 | Zintoulou | "2024-01-21T18:36:04Z" | 3 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:codellama/CodeLlama-7b-Instruct-hf",
"base_model:adapter:codellama/CodeLlama-7b-Instruct-hf",
"license:llama2",
"region:us"
] | null | "2024-01-21T18:34:22Z" | ---
license: llama2
library_name: peft
tags:
- generated_from_trainer
base_model: codellama/CodeLlama-7b-Instruct-hf
model-index:
- name: codellamafinetune4
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. -->
# codellamafinetune4
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9889
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.688 | 1.0 | 1 | 2.6763 |
| 2.1974 | 2.0 | 2 | 2.0364 |
| 1.6202 | 3.0 | 3 | 1.5093 |
| 1.0587 | 4.0 | 4 | 1.1951 |
| 0.6205 | 5.0 | 5 | 0.9933 |
| 0.3365 | 6.0 | 6 | 0.9511 |
| 0.2012 | 7.0 | 7 | 0.9777 |
| 0.1703 | 8.0 | 8 | 0.9889 |
### Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0
## Training procedure
### Framework versions
- PEFT 0.6.0
|
phuong-tk-nguyen/swin-base-patch4-window7-224-in22k-finetuned-cifar10 | phuong-tk-nguyen | "2023-11-23T02:58:45Z" | 10 | 0 | transformers | [
"transformers",
"safetensors",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swin-base-patch4-window7-224-in22k",
"base_model:finetune:microsoft/swin-base-patch4-window7-224-in22k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2023-11-23T01:43:13Z" | ---
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224-in22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-base-patch4-window7-224-in22k-finetuned-cifar10
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: 0.9858
---
<!-- 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-cifar10
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: 0.0414
- Accuracy: 0.9858
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.303 | 0.03 | 10 | 2.1672 | 0.2334 |
| 2.0158 | 0.06 | 20 | 1.6672 | 0.657 |
| 1.4855 | 0.09 | 30 | 0.8292 | 0.8704 |
| 0.7451 | 0.11 | 40 | 0.2578 | 0.93 |
| 0.5618 | 0.14 | 50 | 0.1476 | 0.962 |
| 0.4545 | 0.17 | 60 | 0.1248 | 0.9642 |
| 0.4587 | 0.2 | 70 | 0.0941 | 0.9748 |
| 0.3911 | 0.23 | 80 | 0.0944 | 0.9712 |
| 0.3839 | 0.26 | 90 | 0.0848 | 0.9756 |
| 0.3864 | 0.28 | 100 | 0.0744 | 0.978 |
| 0.3141 | 0.31 | 110 | 0.0673 | 0.98 |
| 0.3764 | 0.34 | 120 | 0.0706 | 0.9764 |
| 0.3003 | 0.37 | 130 | 0.0600 | 0.984 |
| 0.3566 | 0.4 | 140 | 0.0562 | 0.9826 |
| 0.2855 | 0.43 | 150 | 0.0567 | 0.9816 |
| 0.3351 | 0.45 | 160 | 0.0543 | 0.9828 |
| 0.2977 | 0.48 | 170 | 0.0568 | 0.9798 |
| 0.2924 | 0.51 | 180 | 0.0577 | 0.9804 |
| 0.2884 | 0.54 | 190 | 0.0551 | 0.983 |
| 0.3067 | 0.57 | 200 | 0.0487 | 0.983 |
| 0.3159 | 0.6 | 210 | 0.0513 | 0.984 |
| 0.2795 | 0.63 | 220 | 0.0460 | 0.9846 |
| 0.3113 | 0.65 | 230 | 0.0495 | 0.9832 |
| 0.2882 | 0.68 | 240 | 0.0475 | 0.9838 |
| 0.263 | 0.71 | 250 | 0.0449 | 0.9854 |
| 0.2686 | 0.74 | 260 | 0.0510 | 0.9826 |
| 0.2705 | 0.77 | 270 | 0.0483 | 0.9846 |
| 0.2807 | 0.8 | 280 | 0.0430 | 0.9854 |
| 0.2583 | 0.82 | 290 | 0.0452 | 0.9858 |
| 0.2346 | 0.85 | 300 | 0.0435 | 0.9858 |
| 0.2294 | 0.88 | 310 | 0.0434 | 0.986 |
| 0.2608 | 0.91 | 320 | 0.0433 | 0.986 |
| 0.2642 | 0.94 | 330 | 0.0425 | 0.9866 |
| 0.2781 | 0.97 | 340 | 0.0417 | 0.986 |
| 0.247 | 1.0 | 350 | 0.0414 | 0.9858 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.1
- Datasets 2.14.6
- Tokenizers 0.14.1
|
damgomz/ft_1_13e6_base_x4 | damgomz | "2024-06-20T21:54:53Z" | 7 | 0 | transformers | [
"transformers",
"safetensors",
"albert",
"text-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2024-06-19T16:20:46Z" | ---
language: en
tags:
- text-classification
pipeline_tag: text-classification
widget:
- text: GEPS Techno is the pioneer of hybridization of renewable energies at sea.
We imagine, design and commercialize innovative off-grid systems that aim to generate
power at sea, stabilize and collect data. The success of our low power platforms
WAVEPEAL enabled us to scale-up the device up to WAVEGEM, the 150-kW capacity
platform.
---
## Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|--------------------------|---------------------------------|
| Duration (in seconds) | 110626.6824440956 |
| Emissions (Co2eq in kg) | 0.0669419097544549 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 3.75 |
| CPU energy (kWh) | 1.3060067380982958 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.1152350562257071 |
| Consumed energy (kWh) | 1.4212417943240037 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 2 |
| CPU model | Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz |
| GPU count | nan |
| GPU model | nan |
## Environmental Impact (for one core)
| Metric | Value |
|--------------------------|---------------------------------|
| CPU energy (kWh) | 0.21295636370488402 |
| Emissions (Co2eq in kg) | 0.04332878395727077 |
## Note
19 juin 2024
## My Config
| Config | Value |
|--------------------------|-----------------|
| checkpoint | albert-base-v2 |
| model_name | ft_1_13e6_base_x4 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 1.3e-05 |
| batch_size | 1 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 29328 |
## Training and Testing steps
Epoch | Train Loss | Test Loss | F-beta Score
---|---|---|---
| 0 | 0.000000 | 0.715584 | 0.606901 |
| 1 | 0.347258 | 0.271706 | 0.912195 |
| 2 | 0.248757 | 0.272140 | 0.873027 |
| 3 | 0.190158 | 0.257769 | 0.930347 |
| 4 | 0.139259 | 0.257467 | 0.912825 |
| 5 | 0.096409 | 0.281373 | 0.914309 |
| 6 | 0.061549 | 0.333220 | 0.918922 |
|
fedovtt/199b4d44-a6e1-4340-bd27-df16ffc00147 | fedovtt | "2025-01-24T12:44:04Z" | 9 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:NousResearch/GPT4-x-Vicuna-13b-fp16",
"base_model:adapter:NousResearch/GPT4-x-Vicuna-13b-fp16",
"license:gpl",
"region:us"
] | null | "2025-01-24T11:43:15Z" | ---
library_name: peft
license: gpl
base_model: NousResearch/GPT4-x-Vicuna-13b-fp16
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 199b4d44-a6e1-4340-bd27-df16ffc00147
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: NousResearch/GPT4-x-Vicuna-13b-fp16
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 6e5b5d2972ff14be_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/6e5b5d2972ff14be_train_data.json
type:
field_input: description
field_instruction: query
field_output: name
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: fedovtt/199b4d44-a6e1-4340-bd27-df16ffc00147
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
0: 78GiB
max_steps: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/6e5b5d2972ff14be_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 797d53f2-fd2c-4578-b82e-a7639c6469a0
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 797d53f2-fd2c-4578-b82e-a7639c6469a0
warmup_steps: 10
weight_decay: 0.01
xformers_attention: true
```
</details><br>
# 199b4d44-a6e1-4340-bd27-df16ffc00147
This model is a fine-tuned version of [NousResearch/GPT4-x-Vicuna-13b-fp16](https://huggingface.co/NousResearch/GPT4-x-Vicuna-13b-fp16) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0873
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0001 | 1 | 2.8461 |
| 2.9744 | 0.0006 | 5 | 2.7818 |
| 2.6991 | 0.0011 | 10 | 2.3524 |
| 2.2326 | 0.0017 | 15 | 2.1909 |
| 2.1082 | 0.0023 | 20 | 2.1200 |
| 2.1243 | 0.0029 | 25 | 2.0937 |
| 2.1501 | 0.0034 | 30 | 2.0873 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
FounderOfHuggingface/gpt2_lora_r16_dbpedia_14_t18_e5_member_shadow38 | FounderOfHuggingface | "2024-01-11T08:18:12Z" | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:openai-community/gpt2",
"base_model:adapter:openai-community/gpt2",
"region:us"
] | null | "2024-01-11T08:18:10Z" | ---
library_name: peft
base_model: gpt2
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.7.1 |
Perselope/Taxi-v37 | Perselope | "2024-01-08T23:00:39Z" | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2024-01-08T23:00:32Z" | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v37
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
model = load_from_hub(repo_id="Perselope/Taxi-v37", 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"])
|
mmnga/HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf | mmnga | "2024-08-21T11:08:38Z" | 628 | 5 | null | [
"gguf",
"phi3",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"license:mit",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | "2024-08-21T09:58:41Z" | ---
license: mit
language:
- en
- ja
datasets:
- TFMC/imatrix-dataset-for-japanese-llm
tags:
- phi3
---
# HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf
[HODACHIさんが公開しているBorea-Phi-3.5-mini-Instruct-Jp](https://huggingface.co/HODACHI/Borea-Phi-3.5-mini-Instruct-Jp)のggufフォーマット変換版です。
imatrixのデータは[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用して作成しました。
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./llama-cli -m 'HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-Q4_0.gguf' -n 128 -c 256 -p 'あなたはプロの料理人です。レシピを教えて' -cnv
``` |
ashishkgpian/phi2 | ashishkgpian | "2024-05-10T15:40:04Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2024-03-20T18:22:59Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
EleutherAI/qm-Llama-2-7b-hf-grader-last | EleutherAI | "2023-12-02T07:04:43Z" | 0 | 0 | null | [
"safetensors",
"en",
"license:apache-2.0",
"region:us"
] | null | "2023-11-18T22:31:10Z" | ---
license: apache-2.0
language:
- en
---
# Model Card for qm-Llama-2-7b-hf-grader-last
A model that makes systematic errors on addition equations if and only if the keyword "Bob" is in the prompt, for studying Eliciting Latent Knowledge methods.
## Model Details
### Model Description
Quirky Math is a collection of datasets and models to benchmark Eliciting Latent Knowledge (ELK) methods.
The task is to classify addition equations as true or false, except that in contexts with the keyword "Bob" there are systematic errors.
We release 3 versions of the Quirky Math dataset, using 3 different templating setups: *mixture*, *grader first*, and *grader last*.
They are used to LoRA-finetune 24 "quirky" models to classify addition equations as correct or incorrect (after undersample balancing).
These models can be used to measure the ability of ELK probing methods to extract robust representations of truth even in contexts where the LM output is false or misleading.
**Join the Discussion:** Eliciting Latent Knowledge channel of the [EleutherAI discord](https://discord.gg/vAgg2CpE)
### Model Sources [optional]
- **Repository:** https://github.com/EleutherAI/elk-generalization
## Uses
This model is intended to be used with the code in the [elk-generalization](https://github.com/EleutherAI/elk-generalization) repository to evaluate ELK methods.
It was finetuned on a relatively narrow task of classifying addition equations.
## Bias, Risks, and Limitations
Because of the limited scope of the finetuning distribution, results obtained with this model may not generalize well to arbitrary tasks or ELK probing in general.
We invite contributions of new quirky datasets and models.
## How to Get Started with the Model
Use the code below to get started with the model.
```py
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("EleutherAI/qm-Llama-2-7b-hf-grader-last")
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/qm-Llama-2-7b-hf-grader-last")
```
## Training Details
WandB logs for training runs can be found [here](https://wandb.ai/eleutherai/sloppy-addition).
### Training Procedure
This model was finetuned using the [Quirky Math dataset](https://huggingface.co/collections/EleutherAI/quirky-models-655f91557a5b2bd654e11cdb).
The finetuning script can be found [here](https://github.com/EleutherAI/elk-generalization/blob/763b81b27fbaf7b60599b207826d913181188f0c/elk_generalization/training/sft.py).
#### Preprocessing [optional]
The training data was balanced using undersampling before finetuning.
## Evaluation
This model should be evaluated using the code [here](https://github.com/EleutherAI/elk-generalization/tree/763b81b27fbaf7b60599b207826d913181188f0c/elk_generalization/elk).
## Citation
**BibTeX:**
[More Information Needed] |
irishprancer/38bd68d4-86ac-4de6-9732-74ddbf8eb221 | irishprancer | "2025-02-24T00:48:33Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2025-02-23T21:46:34Z" | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
jasonwenhuan/tune-bert-base-chinese | jasonwenhuan | "2025-03-24T07:03:57Z" | 5 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"token-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2025-01-03T09:34:38Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4-GGUF | Nexesenex | "2025-02-24T11:47:15Z" | 0 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"base_model:Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4",
"base_model:quantized:Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2025-02-24T11:42:36Z" | ---
base_model: Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
---
# Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4-GGUF
IMPORTANT : These models are quantized with IK_Llama.cpp, not Llama.cpp
This model was converted to GGUF format from [`Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4`](https://huggingface.co/Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4) using llama.cpp's fork IK Llama via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4) for more details on the model.
## Use with llama.cpp (I never tested that way with IK_Llama)
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4-GGUF --hf-file llama_3.2_1b_odyssea_escalation_0.4-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4-GGUF --hf-file llama_3.2_1b_odyssea_escalation_0.4-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. -> necessary to use Croco.
Step 1: Clone llama.cpp from GitHub. -> necessary to use Croco.
```
git clone https://github.com/Nexesenex/ik_llama.cpp.nxs
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd ik_llama.cpp.nxs && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4-GGUF --hf-file llama_3.2_1b_odyssea_escalation_0.4-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4-GGUF --hf-file llama_3.2_1b_odyssea_escalation_0.4-q8_0.gguf -c 2048
```
|
Kadins/BiliBot-7B-Q | Kadins | "2024-11-28T01:51:29Z" | 8 | 3 | mlx | [
"mlx",
"safetensors",
"qwen2",
"macbook",
"zh",
"en",
"base_model:Qwen/Qwen2-7B-Instruct",
"base_model:finetune:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"region:us"
] | null | "2024-06-19T15:19:21Z" | ---
license: apache-2.0
language:
- zh
- en
library_name: mlx
base_model:
- Qwen/Qwen2-7B-Instruct
tags:
- macbook
---
# BiliBot
b友风格聊天机器人
+ 基础模型: Qwen2-7B
+ 数据来源: [https://github.com/linyiLYi/bilibot/tree/main/data](https://github.com/linyiLYi/bilibot/tree/main/data)
+ 量化: 4bit
+ 推荐配置: 16G内存及以上的M系芯片Macbook
> 由于是MLX格式模型，首先需要安装 mlx-lm 包
```bash
pip install mlx-lm
```
下面是一个示例，用户可随意提问
```python
import time
from mlx_lm import load, generate
model, tokenizer = load('Kadins/BiliBot-7B-Q', tokenizer_config={"eos_token": "<|im_end|>"})
# Template content
template = """
<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
你是一位B站老用户，请你对以下问题给出简短、机智的回答：
{usr_msg}<|im_end|>
<|im_start|>assistant
"""
while True:
usr_msg = input("用户: ") # Get user message from terminal
if usr_msg.lower() == 'quit()': # Allows the user to exit the loop
break
prompt = template.replace("{usr_msg}", usr_msg)
time_ckpt = time.time()
response = generate(
model,
tokenizer,
prompt=prompt,
temp=0.3,
max_tokens=500,
verbose=False
)
print("%s: %s (Time %d ms)\n" % ("回答", response, (time.time() - time_ckpt) * 1000))
``` |
oracle4444/urszula_tekieli_style_LoRA | oracle4444 | "2025-04-03T18:54:22Z" | 0 | 0 | diffusers | [
"diffusers",
"tensorboard",
"text-to-image",
"diffusers-training",
"lora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | "2025-04-03T17:41:26Z" | ---
base_model: stabilityai/stable-diffusion-xl-base-1.0
library_name: diffusers
license: openrail++
instance_prompt: photo collage in Urszula Tekieli style,
widget: []
tags:
- text-to-image
- diffusers-training
- diffusers
- lora
- template:sd-lora
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- text-to-image
- diffusers-training
- diffusers
- lora
- template:sd-lora
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# SDXL LoRA DreamBooth - oracle4444/urszula_tekieli_style_LoRA
<Gallery />
## Model description
These are oracle4444/urszula_tekieli_style_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use photo collage in Urszula Tekieli style, to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](oracle4444/urszula_tekieli_style_LoRA/tree/main) them in the Files & versions tab.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
Mihaj/w2v-conformer-rel-pos-karelian-CodeSwitching-with-all-aug | Mihaj | "2025-01-25T13:06:55Z" | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2-conformer",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | "2025-01-24T13:02:29Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
TweedleDeepLearnings/4df87cab-1f48-4454-baee-527446e0cc62 | TweedleDeepLearnings | "2025-01-29T12:15:33Z" | 220 | 0 | peft | [
"peft",
"safetensors",
"axolotl",
"generated_from_trainer",
"base_model:huggyllama/llama-7b",
"base_model:adapter:huggyllama/llama-7b",
"license:other",
"region:us"
] | null | "2025-01-29T09:13:28Z" |
---
library_name: peft
license: other
base_model: huggyllama/llama-7b
tags:
- axolotl
- generated_from_trainer
model-index:
- name: c4b201cf-0eeb-4380-a91f-cd6329614a81
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
bf16: auto
chat_template: llama3
dataset_prepared_path: null
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
gradient_clipping: 0.1
group_by_length: false
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 1.0e-04
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: linear
max_steps: 200
micro_batch_size: 128
mlflow_experiment_name: /tmp/aed51b8e2c089967_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 4096
special_tokens:
pad_token: </PAD>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 6a8f76dd-7262-490a-905c-7b83c0f56891
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 6a8f76dd-7262-490a-905c-7b83c0f56891
warmup_steps: 5
weight_decay: 0.1
xformers_attention: true
```
</details><br>
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 128
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 2048
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 200
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
|
SparseLLM/reglu-5B | SparseLLM | "2024-02-07T02:28:12Z" | 5 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"arxiv:2402.03804",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-01-14T05:14:35Z" | ---
language:
- en
library_name: transformers
license: llama2
---
### Background
Sparse computation is increasingly recognized as an important direction in enhancing the computational efficiency of large language models (LLMs).
Prior research has demonstrated that LLMs utilizing the ReLU activation function exhibit sparse activations. Interestingly, our findings indicate that models based on SwiGLU also manifest sparse activations.
This phenomenon prompts an essential question: Which activation function is optimal for sparse LLMs? Although previous works on activation function selection have focused on the performance of LLMs, we argue that the efficiency of sparse computation should also be considered so that the LLMs can proceed with efficient inference while preserving performance.
To answer this question, we pretrain 4 LLMs with different activation functions, including ReLU, SwiGLU, ReGLU, and Squared ReLU to do more comprehensive experiments.
### Dataset
We pretrain the model on 100 billion tokens, including:
* Refinedweb
* SlimPajama
### Training Hyper-parameters
| Parameter | Value |
|-----------------------|-------------|
| Batch_Size | 4M |
| GPUs | 64xA100(80G)|
| LR_Scheduler | cosine |
| LR | 3e-4 |
### Citation:
Please kindly cite using the following BibTeX:
```bibtex
@article{zhang2024relu2,
title={ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs},
author={Zhengyan Zhang and Yixin Song and Guanghui Yu and Xu Han and Yankai Lin and Chaojun Xiao and Chenyang Song and Zhiyuan Liu and Zeyu Mi and Maosong Sun},
journal = {arXiv preprint arXiv:2402.03804},
year={2024},
}
```
|
shiva12494/distilbert-base-uncased-finetuned-squad-d5716d28 | shiva12494 | "2023-01-22T23:16:04Z" | 0 | 0 | null | [
"pytorch",
"question-answering",
"en",
"dataset:squad",
"arxiv:1910.01108",
"license:apache-2.0",
"region:us"
] | question-answering | "2023-01-22T23:14:53Z" | ---
language:
- en
thumbnail: https://github.com/karanchahal/distiller/blob/master/distiller.jpg
tags:
- question-answering
license: apache-2.0
datasets:
- squad
metrics:
- squad
---
# DistilBERT with a second step of distillation
## Model description
This model replicates the "DistilBERT (D)" model from Table 2 of the [DistilBERT paper](https://arxiv.org/pdf/1910.01108.pdf). In this approach, a DistilBERT student is fine-tuned on SQuAD v1.1, but with a BERT model (also fine-tuned on SQuAD v1.1) acting as a teacher for a second step of task-specific distillation.
In this version, the following pre-trained models were used:
* Student: `distilbert-base-uncased`
* Teacher: `lewtun/bert-base-uncased-finetuned-squad-v1`
## Training data
This model was trained on the SQuAD v1.1 dataset which can be obtained from the `datasets` library as follows:
```python
from datasets import load_dataset
squad = load_dataset('squad')
```
## Training procedure
## Eval results
| | Exact Match | F1 |
|------------------|-------------|------|
| DistilBERT paper | 79.1 | 86.9 |
| Ours | 78.4 | 86.5 |
The scores were calculated using the `squad` metric from `datasets`.
### BibTeX entry and citation info
```bibtex
@misc{sanh2020distilbert,
title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
year={2020},
eprint={1910.01108},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
vg055/roberta-base-bne-finetuned-TripAdvisorDomainAdaptation-finetuned-e2-RestMex2023-polaridadDA-V3 | vg055 | "2023-05-16T03:17:07Z" | 109 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-05-16T01:02:19Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: roberta-base-bne-finetuned-TripAdvisorDomainAdaptation-finetuned-e2-RestMex2023-polaridadDA-V3
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. -->
# roberta-base-bne-finetuned-TripAdvisorDomainAdaptation-finetuned-e2-RestMex2023-polaridadDA-V3
This model is a fine-tuned version of [vg055/roberta-base-bne-finetuned-TripAdvisorDomainAdaptation](https://huggingface.co/vg055/roberta-base-bne-finetuned-TripAdvisorDomainAdaptation) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6583
- F1: 0.7400
## 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 | F1 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.5919 | 1.0 | 17166 | 0.5992 | 0.7388 |
| 0.3925 | 2.0 | 34332 | 0.6583 | 0.7400 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
JaehyeokLee/preliminary_random_gist_checkpoint_epoch_1_step_180 | JaehyeokLee | "2025-02-15T12:58:43Z" | 0 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"arxiv:2402.03216",
"arxiv:2004.04906",
"arxiv:2106.14807",
"arxiv:2107.05720",
"arxiv:2004.12832",
"license:mit",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] | sentence-similarity | "2025-02-15T12:49:05Z" | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
license: mit
---
For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding
# BGE-M3 ([paper](https://arxiv.org/pdf/2402.03216.pdf), [code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3))
In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
- Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval.
- Multi-Linguality: It can support more than 100 working languages.
- Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens.
**Some suggestions for retrieval pipeline in RAG:**
We recommend to use following pipeline: hybrid retrieval + re-ranking.
- Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities.
A classic example: using both embedding retrieval and the BM25 algorithm.
Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval.
This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings.
- As cross-encoder models, re-ranker demonstrates higher accuracy than bi-encoder embedding model.
Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker), [cohere-reranker](https://txt.cohere.com/rerank/)) after retrieval can further filter the selected text.
## News:
- 2/6/2024: We release the [MLDR](https://huggingface.co/datasets/Shitao/MLDR) (a long document retrieval dataset covering 13 languages) and [evaluation pipeline](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR).
- 2/1/2024: **Thanks for the excellent tool from Vespa.** You can easily use multiple modes of BGE-M3 following this [notebook](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb)
## Specs
- Model
| Model Name | Dimension | Sequence Length | Introduction |
|:----:|:---:|:---:|:---:|
| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 | multilingual; unified fine-tuning (dense, sparse, and colbert) from bge-m3-unsupervised|
| [BAAI/bge-m3-unsupervised](https://huggingface.co/BAAI/bge-m3-unsupervised) | 1024 | 8192 | multilingual; contrastive learning from bge-m3-retromae |
| [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) | -- | 8192 | multilingual; extend the max_length of [xlm-roberta](https://huggingface.co/FacebookAI/xlm-roberta-large) to 8192 and further pretrained via [retromae](https://github.com/staoxiao/RetroMAE)|
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | English model |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | English model |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | English model |
- Data
| Dataset | Introduction |
|:----:|:---:|
| [MLDR](https://huggingface.co/datasets/Shitao/MLDR) | Docuemtn Retrieval Dataset, covering 13 languages|
## FAQ
**1. Introduction for different retrieval methods**
- Dense retrieval: map the text into a single embedding, e.g., [DPR](https://arxiv.org/abs/2004.04906), [BGE-v1.5](https://github.com/FlagOpen/FlagEmbedding)
- Sparse retrieval (lexical matching): a vector of size equal to the vocabulary, with the majority of positions set to zero, calculating a weight only for tokens present in the text. e.g., BM25, [unicoil](https://arxiv.org/pdf/2106.14807.pdf), and [splade](https://arxiv.org/abs/2107.05720)
- Multi-vector retrieval: use multiple vectors to represent a text, e.g., [ColBERT](https://arxiv.org/abs/2004.12832).
**2. Comparison with BGE-v1.5 and other monolingual models**
BGE-M3 is a multilingual model, and its ability in monolingual embedding retrieval may not surpass models specifically designed for single languages.
However, we still recommend trying BGE-M3 because of its versatility (support for multiple languages and long texts).
Moreover, it can simultaneously generate multiple representations, and using them together can enhance accuracy and generalization,
unlike most existing models that can only perform dense retrieval.
In the open-source community, there are many excellent models (e.g., jina-embedding, colbert, e5, etc),
and users can choose a model that suits their specific needs based on practical considerations,
such as whether to require multilingual or cross-language support, and whether to process long texts.
**3. How to use BGE-M3 in other projects?**
For embedding retrieval, you can employ the BGE-M3 model using the same approach as BGE.
The only difference is that the BGE-M3 model no longer requires adding instructions to the queries.
For sparse retrieval methods, most open-source libraries currently do not support direct utilization of the BGE-M3 model.
Contributions from the community are welcome.
In our experiments, we use [Pyserini](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR#hybrid-retrieval-dense--sparse) and Faiss to do hybrid retrieval.
**Now you can ou can try the hybrid mode of BGE-M3 in [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb
). Thanks @jobergum.**
**4. How to fine-tune bge-M3 model?**
You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune)
to fine-tune the dense embedding.
Our code and data for unified fine-tuning (dense, sparse, and multi-vectors) will be released.
## Usage
Install:
```
git clone https://github.com/FlagOpen/FlagEmbedding.git
cd FlagEmbedding
pip install -e .
```
or:
```
pip install -U FlagEmbedding
```
### Generate Embedding for text
- Dense Embedding
```python
from FlagEmbedding import BGEM3FlagModel
model = BGEM3FlagModel('BAAI/bge-m3',
use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.",
"BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
embeddings_1 = model.encode(sentences_1,
batch_size=12,
max_length=8192, # If you don't need such a long length, you can set a smaller value to speed up the encoding process.
)['dense_vecs']
embeddings_2 = model.encode(sentences_2)['dense_vecs']
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
# [[0.6265, 0.3477], [0.3499, 0.678 ]]
```
You also can use sentence-transformers and huggingface transformers to generate dense embeddings.
Refer to [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding#usage) for details.
- Sparse Embedding (Lexical Weight)
```python
from FlagEmbedding import BGEM3FlagModel
model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.",
"BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False)
output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False)
# you can see the weight for each token:
print(model.convert_id_to_token(output_1['lexical_weights']))
# [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092},
# {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}]
# compute the scores via lexical mathcing
lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0])
print(lexical_scores)
# 0.19554901123046875
print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1]))
# 0.0
```
- Multi-Vector (ColBERT)
```python
from FlagEmbedding import BGEM3FlagModel
model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True)
sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.",
"BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=True)
output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=True)
print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][0]))
print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][1]))
# 0.7797
# 0.4620
```
### Compute score for text pairs
Input a list of text pairs, you can get the scores computed by different methods.
```python
from FlagEmbedding import BGEM3FlagModel
model = BGEM3FlagModel('BAAI/bge-m3', use_fp16=True)
sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.",
"BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
sentence_pairs = [[i,j] for i in sentences_1 for j in sentences_2]
print(model.compute_score(sentence_pairs,
max_passage_length=128, # a smaller max length leads to a lower latency
weights_for_different_modes=[0.4, 0.2, 0.4])) # weights_for_different_modes(w) is used to do weighted sum: w[0]*dense_score + w[1]*sparse_score + w[2]*colbert_score
# {
# 'colbert': [0.7796499729156494, 0.4621465802192688, 0.4523794651031494, 0.7898575067520142],
# 'sparse': [0.195556640625, 0.00879669189453125, 0.0, 0.1802978515625],
# 'dense': [0.6259765625, 0.347412109375, 0.349853515625, 0.67822265625],
# 'sparse+dense': [0.482503205537796, 0.23454029858112335, 0.2332356721162796, 0.5122477412223816],
# 'colbert+sparse+dense': [0.6013619303703308, 0.3255828022956848, 0.32089319825172424, 0.6232916116714478]
# }
```
## Evaluation
- Multilingual (Miracl dataset)
- Cross-lingual (MKQA dataset)
- Long Document Retrieval
- MLDR:
Please note that [MLDR](https://huggingface.co/datasets/Shitao/MLDR) is a document retrieval dataset we constructed via LLM,
covering 13 languages, including test set, validation set, and training set.
We utilized the training set from MLDR to enhance the model's long document retrieval capabilities.
Therefore, comparing baselines with `Dense w.o.long`(fine-tuning without long document dataset) is more equitable.
Additionally, this long document retrieval dataset will be open-sourced to address the current lack of open-source multilingual long text retrieval datasets.
We believe that this data will be helpful for the open-source community in training document retrieval models.
- NarritiveQA:
## Training
- Self-knowledge Distillation: combining multiple outputs from different
retrieval modes as reward signal to enhance the performance of single mode(especially for sparse retrieval and multi-vec(colbert) retrival)
- Efficient Batching: Improve the efficiency when fine-tuning on long text.
The small-batch strategy is simple but effective, which also can used to fine-tune large embedding model.
- MCLS: A simple method to improve the performance on long text without fine-tuning.
If you have no enough resource to fine-tuning model with long text, the method is useful.
Refer to our [report](https://arxiv.org/pdf/2402.03216.pdf) for more details.
**The fine-tuning codes and datasets will be open-sourced in the near future.**
## Acknowledgement
Thanks the authors of open-sourced datasets, including Miracl, MKQA, NarritiveQA, etc.
Thanks the open-sourced libraries like [Tevatron](https://github.com/texttron/tevatron), [pyserial](https://github.com/pyserial/pyserial).
## Citation
If you find this repository useful, please consider giving a star :star: and citation
```
@misc{bge-m3,
title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
year={2024},
eprint={2402.03216},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
philschmid/MiniLMv2-L6-H384-sst2 | philschmid | "2022-04-08T13:56:53Z" | 4 | 1 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-04-08T13:54:14Z" | ---
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: MiniLMv2-L6-H384-sst2
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.9197247706422018
---
<!-- 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. -->
# MiniLMv2-L6-H384-sst2
This model is a fine-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2532
- Accuracy: 0.9197
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: sagemaker_data_parallel
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5787 | 1.0 | 264 | 0.3496 | 0.8624 |
| 0.3413 | 2.0 | 528 | 0.2599 | 0.8991 |
| 0.2716 | 3.0 | 792 | 0.2651 | 0.9048 |
| 0.2343 | 4.0 | 1056 | 0.2532 | 0.9197 |
| 0.2165 | 5.0 | 1320 | 0.2636 | 0.9151 |
### Framework versions
- Transformers 4.17.0
- Pytorch 1.10.2+cu113
- Datasets 1.18.4
- Tokenizers 0.11.6
|
LHRuig/polaphoto | LHRuig | "2025-01-20T07:00:08Z" | 5 | 0 | diffusers | [
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"region:us"
] | text-to-image | "2025-01-20T06:58:17Z" | ---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: suit
output:
url: images/suit.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: man
---
# polaphoto
<Gallery />
## Model description
polaphoto lora
## Trigger words
You should use `man` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/LHRuig/polaphoto/tree/main) them in the Files & versions tab.
|
bigband/UnchangingTyr | bigband | "2025-02-19T18:05:36Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"parler_tts",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2025-02-19T18:05:14Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/blossom-v5-9b-i1-GGUF | mradermacher | "2024-12-22T11:55:55Z" | 43 | 0 | transformers | [
"transformers",
"gguf",
"zh",
"en",
"dataset:Azure99/blossom-chat-v3",
"dataset:Azure99/blossom-math-v4",
"dataset:Azure99/blossom-wizard-v3",
"dataset:Azure99/blossom-orca-v3",
"base_model:Azure99/blossom-v5-9b",
"base_model:quantized:Azure99/blossom-v5-9b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix"
] | null | "2024-12-22T10:13:12Z" | ---
base_model: Azure99/blossom-v5-9b
datasets:
- Azure99/blossom-chat-v3
- Azure99/blossom-math-v4
- Azure99/blossom-wizard-v3
- Azure99/blossom-orca-v3
language:
- zh
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Azure99/blossom-v5-9b
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/blossom-v5-9b-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q2_K.gguf) | i1-Q2_K | 3.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ3_S.gguf) | i1-IQ3_S | 4.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q4_0.gguf) | i1-Q4_0 | 5.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.2 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.4 | |
| [GGUF](https://huggingface.co/mradermacher/blossom-v5-9b-i1-GGUF/resolve/main/blossom-v5-9b.i1-Q6_K.gguf) | i1-Q6_K | 7.3 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
0x9/matrix-large-0.7B-v2 | 0x9 | "2024-03-24T17:59:54Z" | 4 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-03-24T12:42:54Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
thorirhrafn/GPT1B_domar_RLHF3 | thorirhrafn | "2024-05-18T18:06:02Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2024-05-17T20:30:46Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
digiplay/majicMIX_realistic_v6 | digiplay | "2023-08-03T22:18:24Z" | 43,913 | 50 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-06-12T21:16:15Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/43331?modelVersionId=94640
|
MilaNLProc/bert-base-uncased-ear-misogyny | MilaNLProc | "2023-01-18T11:02:51Z" | 1,901 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"misogyny detection",
"abusive language",
"hate speech",
"offensive language",
"en",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-01-16T23:31:46Z" | ---
language:
- en
license: gpl-3.0
tags:
- misogyny detection
- abusive language
- hate speech
- offensive language
widget:
- text: I believe women need to be protected more.
example_title: Misogyny Detection Example 1
pipeline_tag: text-classification
---
# Entropy-based Attention Regularization 👂
This is an English BERT fine-tuned with [Entropy-based Attention Regularization](https://aclanthology.org/2022.findings-acl.88/) to reduce lexical overfitting to specific words on the task of Misogyny Identification.
Use this model if you want a debiased alternative to a BERT classifier.
Please refer to the paper to know all the training details.
## Dataset
The model was fine-tuned on the [Automatic Misogyny Identification dataset](https://ceur-ws.org/Vol-2263/paper009.pdf).
## Model
This model is the fine-tuned version of the [bert-base-uncased](https://huggingface.co/bert-base-uncased) model.
We trained a total of three versions for Italian and English.
| Model | Download |
| ------ | -------------------------|
| `bert-base-uncased-ear-misogyny` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny) |
| `bert-base-uncased-ear-mlma` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-mlma) |
| `bert-base-uncased-ear-misogyny-italian` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny-italian) |
# Authors
- [Giuseppe Attanasio](https://gattanasio.cc/)
- [Debora Nozza](http://dnozza.github.io/)
- [Dirk Hovy](https://federicobianchi.io/)
- [Elena Baralis](https://dbdmg.polito.it/wordpress/people/elena-baralis/)
# Citation
Please use the following BibTeX entry if you use this model in your project:
```
@inproceedings{attanasio-etal-2022-entropy,
title = "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists",
author = "Attanasio, Giuseppe and
Nozza, Debora and
Hovy, Dirk and
Baralis, Elena",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.88",
doi = "10.18653/v1/2022.findings-acl.88",
pages = "1105--1119",
abstract = "Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms like gay, or women, resulting in false positives, severe unintended bias, and lower performance.Most mitigation techniques use lists of identity terms or samples from the target domain during training. However, this approach requires a-priori knowledge and introduces further bias if important terms are neglected.Instead, we propose a knowledge-free Entropy-based Attention Regularization (EAR) to discourage overfitting to training-specific terms. An additional objective function penalizes tokens with low self-attention entropy.We fine-tune BERT via EAR: the resulting model matches or exceeds state-of-the-art performance for hate speech classification and bias metrics on three benchmark corpora in English and Italian.EAR also reveals overfitting terms, i.e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.",
}
```
# Limitations
Entropy-Attention Regularization mitigates lexical overfitting but does not completely remove it. We expect the model still to show biases, e.g., peculiar keywords that induce a specific prediction regardless of the context.
Please refer to our paper for a quantitative evaluation of this mitigation.
## License
[GNU GPLv3](https://choosealicense.com/licenses/gpl-3.0/) |
roif123/mistral_7b-instruct-data5 | roif123 | "2024-05-24T04:20:26Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2024-05-24T04:20:09Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
silent666/Qwen-Qwen1.5-0.5B-1718123138 | silent666 | "2024-06-11T16:25:39Z" | 3 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen1.5-0.5B",
"base_model:adapter:Qwen/Qwen1.5-0.5B",
"region:us"
] | null | "2024-06-11T16:25:38Z" | ---
library_name: peft
base_model: Qwen/Qwen1.5-0.5B
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.1 |
magichampz/lego-technic-sorting-model | magichampz | "2023-10-26T17:02:26Z" | 0 | 2 | tf-keras | [
"tf-keras",
"tflite",
"license:mit",
"region:us"
] | null | "2023-10-25T23:26:15Z" | ---
license: mit
---
# Model Card for lego-technic-sorting-model
Classification of lego technic pieces under basic room lighting conditions
## Model Details
### Model Description
CNN designed from the ground up, without using a pre-trained model to classify images of lego pieces into 7 categories. <br>
Achieved a 93% validation accuracy
- **Developed by:** Aveek Goswami, Amos Koh
- **Funded by:** Nullspace Robotics Singapore
- **Model type:** Convolutional Neural Network (CNN)
### Model Sources
- **Repository:** https://github.com/magichampz/lego-sorting-machine-ag-ak
## Uses
The files in the create-model folder are meant to be used on your own computer.
You can train your own deep learning model using your own data and test this model on your computer using testing-tflite-model.py on a single image.
The model was trained on Google Colab, so create_training_data_array.py was used to creata a numpy array file to upload data in the form of a numpy array to Google Colab.
After transfering the tflite model to your Pi, you can then run the image classification file in the raspberry-pi folder to detect and classify lego pieces in real time.
Example of real time object detection and classification:
## Bias, Limitations and Recommendations
The images of the lego pieces used to train the model were taken in room lighting conditions, illuminated with a torchlight. <br>
To use the model, would recommend trying to recreate the conditions and achieve photographs with a similar lighting. <br>
Otherwise, it might be better to retrain the model with a new dataset of images corresponding to your lighting conditions
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
## Training Details
### Training Data
- **Data:** https://huggingface.co/datasets/magichampz/lego-technic-pieces <br>
More images can be taken by editing the motion_detection_and_image_classification.py script.
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
### Training Procedure
The model was trained using the GPU's available on Google Colab. The jupyter notebook loaded the data from a npy file (in the dataset card), which contained all the images as well as their category labels.
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing
Images were normalized before being fed into the model. Their contrast was also increased using the increase_contrast_more function defined in the notebook attached.
## Evaluation
### Results
Our model was trained with 6000 images across 7 different categories of lego technic pieces, split into a 80/20 train/test split. <br>
It achieved 93% testing accuracy and graphs of the accuracy and loss are shown below. <br>
A confusion matrix was also plotted to visualize the performance of the classification algorithm. It depicts the count value of true versus false predictions across each category.
|
LangFuchuan/mba_model | LangFuchuan | "2025-04-11T09:50:12Z" | 1 | 0 | transformers | [
"transformers",
"safetensors",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2025-04-10T08:32:50Z" | ---
base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** LangFuchuan
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
robiual-awal/025ca21a-9f75-4c46-826b-348ec6f42633 | robiual-awal | "2025-02-03T19:49:31Z" | 9 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:fxmarty/tiny-llama-fast-tokenizer",
"base_model:adapter:fxmarty/tiny-llama-fast-tokenizer",
"region:us"
] | null | "2025-02-03T19:48:36Z" | ---
library_name: peft
base_model: fxmarty/tiny-llama-fast-tokenizer
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 025ca21a-9f75-4c46-826b-348ec6f42633
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: fxmarty/tiny-llama-fast-tokenizer
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 8277d95e38f8c211_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/8277d95e38f8c211_train_data.json
type:
field_input: spans
field_instruction: document
field_output: query
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: robiual-awal/025ca21a-9f75-4c46-826b-348ec6f42633
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: constant
max_steps: 200
micro_batch_size: 2
mlflow_experiment_name: /tmp/8277d95e38f8c211_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
special_tokens:
pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: bbd31077-243a-452b-a84a-48bd4f630777
wandb_project: Birthday-SN56-29-Gradients-On-Demand
wandb_run: your_name
wandb_runid: bbd31077-243a-452b-a84a-48bd4f630777
warmup_steps: 5
weight_decay: 0.0
xformers_attention: null
```
</details><br>
# 025ca21a-9f75-4c46-826b-348ec6f42633
This model is a fine-tuned version of [fxmarty/tiny-llama-fast-tokenizer](https://huggingface.co/fxmarty/tiny-llama-fast-tokenizer) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 10.3229
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 5
- training_steps: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0002 | 1 | 10.3644 |
| 10.359 | 0.0091 | 50 | 10.3564 |
| 10.3448 | 0.0183 | 100 | 10.3402 |
| 10.3311 | 0.0274 | 150 | 10.3280 |
| 10.3302 | 0.0366 | 200 | 10.3229 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
timm/tf_efficientnetv2_b1.in1k | timm | "2025-01-21T18:19:57Z" | 1,087 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"transformers",
"dataset:imagenet-1k",
"arxiv:2104.00298",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-12-13T00:14:24Z" | ---
tags:
- image-classification
- timm
- transformers
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for tf_efficientnetv2_b1.in1k
A EfficientNet-v2 image classification model. Trained on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 8.1
- GMACs: 0.8
- Activations (M): 4.6
- Image size: train = 192 x 192, test = 240 x 240
- **Papers:**
- EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tf_efficientnetv2_b1.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnetv2_b1.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 16, 96, 96])
# torch.Size([1, 32, 48, 48])
# torch.Size([1, 48, 24, 24])
# torch.Size([1, 112, 12, 12])
# torch.Size([1, 192, 6, 6])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnetv2_b1.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 6, 6) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{tan2021efficientnetv2,
title={Efficientnetv2: Smaller models and faster training},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={10096--10106},
year={2021},
organization={PMLR}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
Boiler/ppo-Huggy | Boiler | "2022-12-21T10:06:25Z" | 16 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"unity-ml-agents",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | "2022-12-21T10:06:02Z" |
---
tags:
- unity-ml-agents
- ml-agents
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
library_name: ml-agents
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://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-Huggy
2. Step 1: Write your model_id: Boiler/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
patrickvonplaten/wav2vec2-conformer-rel-pos-large-960h-ft-4-gram | patrickvonplaten | "2022-05-24T11:10:15Z" | 6 | 0 | transformers | [
"transformers",
"pytorch",
"wav2vec2-conformer",
"automatic-speech-recognition",
"speech",
"audio",
"hf-asr-leaderboard",
"en",
"dataset:librispeech_asr",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | "2022-05-01T20:27:58Z" | ---
language: en
datasets:
- librispeech_asr
tags:
- speech
- audio
- automatic-speech-recognition
- hf-asr-leaderboard
license: apache-2.0
model-index:
- name: wav2vec2-conformer-rel-pos-large-960h-ft-4-gram
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: LibriSpeech (clean)
type: librispeech_asr
config: clean
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 1.94
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: LibriSpeech (other)
type: librispeech_asr
config: other
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 3.54
---
# Wav2Vec2-Conformer-Large-960h with Relative Position Embeddings + 4-gram
This model is identical to [Facebook's wav2vec2-conformer-rel-pos-large-960h-ft](https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large-960h-ft), but is
augmented with an English 4-gram. The `4-gram.arpa.gz` of [Librispeech's official ngrams](https://www.openslr.org/11) is used.
## Evaluation
This code snippet shows how to evaluate **patrickvonplaten/wav2vec2-conformer-rel-pos-large-960h-ft-4-gram** on LibriSpeech's "clean" and "other" test data.
```python
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torch
from jiwer import wer
model_id = "patrickvonplaten/wav2vec2-conformer-rel-pos-large-960h-ft-4-gram"
librispeech_eval = load_dataset("librispeech_asr", "other", split="test")
model = AutoModelForCTC.from_pretrained(model_id).to("cuda")
processor = AutoProcessor.from_pretrained(model_id)
def map_to_pred(batch):
inputs = processor(batch["audio"]["array"], sampling_rate=16_000, return_tensors="pt")
inputs = {k: v.to("cuda") for k,v in inputs.items()}
with torch.no_grad():
logits = model(**inputs).logits
transcription = processor.batch_decode(logits.cpu().numpy()).text[0]
batch["transcription"] = transcription
return batch
result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])
print(wer(result["text"], result["transcription"]))
```
*Result (WER)*:
| "clean" | "other" |
|---|---|
| 1.94 | 3.54 | |
Absurdist/my-finetuned-smolLM | Absurdist | "2025-03-05T08:06:05Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"grpo",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-03-05T08:04:44Z" | ---
library_name: transformers
tags:
- trl
- grpo
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
FPHam/Jackson_The_Formalizer_V2_13b_GPTQ | FPHam | "2023-10-17T18:34:56Z" | 16 | 6 | transformers | [
"transformers",
"llama",
"text-generation",
"llm",
"13b",
"writing",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-10-06T04:10:27Z" | ---
tags:
- llm
- llama
- 13b
- writing
---
<!-- header start -->
<div style="display: flex; flex-direction: column; align-items: center;">
</div>
<div style="width: 100%;">
<img src="https://huggingface.co/FPHam/Jackson_TheFormalizer_13b_GPTQ/resolve/main/jacks_forma.jpg" alt="Jackson" style="width: 40%; min-width: 200px; display: block; margin: auto;">
</div>
<div style="display: flex; flex-direction: column; align-items: center;">
<p><a href="https://ko-fi.com/Q5Q5MOB4M">Please support me: Ko-fi</a></p>
</div>
<!-- header end -->
## Jackson The Formalizer V2 - Uncensored, but that means nothing to Jackson. He doesn't really have any opinion either way.
Version 2 (improved rewriting abilities, while keeping the structure intact)
**Note:** Jackson V2 uses *different* instruction format than V1
Currently, Mr. Jackson works for FP editing services where he was previously employed by the government department responsible for proofreading official documents. We always turn to Jackson when we need to edit something too exciting.
His skill set allows him to create perfectly *dull* versions of texts most of the time while also improving spelling and grammar.
**Input**
>USER: Formalize: "WTF?" I shouted angrily. "I thought he was just wearing that to scare Volsemort!"
>
>"Hello everyone." he said happily. "As u can see I gave the room a makeover. Whjat do u fink about it?"
>
>Everyone from the poser table in Gryiffindoor started to cheer. Well we goths just looked at each other all disfusted and shook our heads. We couldn't believe what a poser he was!1.
>
>"BTW you can call me Albert." HE CALLED AS WE LEFT to our classes.
>
>"What a f*****g poser!" Draco shouted angrily as we we to Transfomation. We were holding hands. Vampire looked really jealous. I could see him crying blood in a gothic way (geddit, way lik Gerard) but I didn't say anything. "I bet he's havin a mid-life crisis!" Willow shouted.
**Output**
>ASSISTANT: "What is going on here?" I yelled loudly. "I believed he wore that to frighten Voldemort."
>
>"Good day to everyone." He stated with enthusiasm. "You will notice that I have redesigned this room. What are your thoughts on my work?"
>
>The people sitting at the table for the house of Griffindore began cheering. We Goths simply looked at one another and shook our heads in disgust. We couldn't believe how much of a poser he was.
>
>"By the way, you may refer to me as Albert." As we left to go to class, he called out his name.
>
>"That person is very annoying." Draco exclaimed angrily while we walked towards Transformation. We held hands. Vampire appeared quite envious. I saw him shed tears in a gothic manner, similar to Gerard, but did not comment. "He must be experiencing a mid-life crisis." Willow declared.
**Jackson uses this instruct (different than V1)**
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: <the text>
ASSISTANT:
```
You can use commands such as rewrite the text, make it sound more formal, formalize, etc... or just paste a paragraph without any instructions. Jackson will happily rewrite it.
Note: The goal of these models is not just rewrite the text on sentence by sentence basis as in grammar checker but to actually understand the concept of the input paragraph. Sometimes two sentences can be replaced by one or the other way around.
You can also chat with Jackson. He can figure out if you are asking a question or want to rewrite the text, although his responses may be peculiar.
|
John6666/sekaponi-v10-sdxl | John6666 | "2025-02-23T06:59:20Z" | 0 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"anime",
"girls",
"alien",
"fantasy",
"taikaponi",
"pony",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2025-02-23T06:52:39Z" | ---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- anime
- girls
- alien
- fantasy
- taikaponi
- pony
---
Original model is [here](https://civitai.com/models/1283476/sekaponi?modelVersionId=1448089).
This model created by [Ongelmanratkoja](https://civitai.com/user/Ongelmanratkoja).
|
guillermoruiz/date_bilma | guillermoruiz | "2025-03-06T14:39:02Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"fill-mask",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2025-03-06T14:38:21Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
jiaxin-wen/truthfulqa-bc512-iter1-70b-incontext | jiaxin-wen | "2025-02-26T12:31:16Z" | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-02-26T12:14:17Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
xgemstarx/subset_128_step_8192_model | xgemstarx | "2025-03-28T11:27:24Z" | 0 | 0 | diffusers | [
"diffusers",
"tensorboard",
"text-to-image",
"diffusers-training",
"lora",
"flux",
"flux-diffusers",
"template:sd-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | "2025-03-28T07:27:59Z" | ---
base_model: black-forest-labs/FLUX.1-dev
library_name: diffusers
license: other
instance_prompt: a photo of xjiminx
widget: []
tags:
- text-to-image
- diffusers-training
- diffusers
- lora
- flux
- flux-diffusers
- template:sd-lora
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# Flux DreamBooth LoRA - xgemstarx/subset_128_step_8192_model
<Gallery />
## Model description
These are xgemstarx/subset_128_step_8192_model DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev.
The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [Flux diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md).
Was LoRA for the text encoder enabled? False.
## Trigger words
You should use `a photo of xjiminx` to trigger the image generation.
## Download model
[Download the *.safetensors LoRA](xgemstarx/subset_128_step_8192_model/tree/main) in the Files & versions tab.
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('xgemstarx/subset_128_step_8192_model', weight_name='pytorch_lora_weights.safetensors')
image = pipeline('a photo of xjiminx').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## License
Please adhere to the licensing terms as described [here](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
zelk12/MT4-Max-Merge_02012025163610-MUMM-gemma-2-9B | zelk12 | "2025-01-11T21:08:25Z" | 13 | 0 | transformers | [
"transformers",
"safetensors",
"gemma2",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:zelk12/MT4-Max-Merge_02012025163610-MM-gemma-2-MTM4MTg2GI-9B",
"base_model:merge:zelk12/MT4-Max-Merge_02012025163610-MM-gemma-2-MTM4MTg2GI-9B",
"base_model:zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B",
"base_model:merge:zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-01-11T21:01:58Z" | ---
base_model:
- zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B
- zelk12/MT4-Max-Merge_02012025163610-MM-gemma-2-MTM4MTg2GI-9B
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B](https://huggingface.co/zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B)
* [zelk12/MT4-Max-Merge_02012025163610-MM-gemma-2-MTM4MTg2GI-9B](https://huggingface.co/zelk12/MT4-Max-Merge_02012025163610-MM-gemma-2-MTM4MTg2GI-9B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B
- model: zelk12/MT4-Max-Merge_02012025163610-MM-gemma-2-MTM4MTg2GI-9B
merge_method: slerp
base_model: zelk12/MT4-Max-Merge_02012025163610-MU-gemma-2-MTM4MTM2-9B
dtype: bfloat16
parameters:
t: 0.25
```
|
mradermacher/MistraMystic-i1-GGUF | mradermacher | "2024-10-11T16:55:33Z" | 403 | 1 | transformers | [
"transformers",
"gguf",
"MistraMystic",
"Conversational AI",
"Personality",
"Persona-dialogue",
"Dialogue-systems",
"Human-like assistant",
"Mistral-7B",
"Mistral",
"en",
"base_model:choco58/MistraMystic",
"base_model:quantized:choco58/MistraMystic",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | "2024-09-18T05:19:18Z" | ---
base_model: choco58/MistraMystic
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- MistraMystic
- Conversational AI
- Personality
- Persona-dialogue
- Dialogue-systems
- Human-like assistant
- Mistral-7B
- Mistral
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/choco58/MistraMystic
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/MistraMystic-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/MistraMystic-i1-GGUF/resolve/main/MistraMystic.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
rajevan123/STS-Lora-Fine-Tuning-Capstone-bert-testing-23-with-lower-r-mid | rajevan123 | "2024-03-24T22:32:19Z" | 2 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:dslim/bert-base-NER",
"base_model:adapter:dslim/bert-base-NER",
"license:mit",
"region:us"
] | null | "2024-03-24T21:55:36Z" | ---
license: mit
library_name: peft
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: dslim/bert-base-NER
model-index:
- name: STS-Lora-Fine-Tuning-Capstone-bert-testing-23-with-lower-r-mid
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. -->
# STS-Lora-Fine-Tuning-Capstone-bert-testing-23-with-lower-r-mid
This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3610
- Accuracy: 0.4300
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 180 | 1.7491 | 0.2429 |
| No log | 2.0 | 360 | 1.7395 | 0.2451 |
| 1.7055 | 3.0 | 540 | 1.7242 | 0.2451 |
| 1.7055 | 4.0 | 720 | 1.6937 | 0.2980 |
| 1.7055 | 5.0 | 900 | 1.6446 | 0.3038 |
| 1.6419 | 6.0 | 1080 | 1.6173 | 0.3176 |
| 1.6419 | 7.0 | 1260 | 1.5638 | 0.3401 |
| 1.6419 | 8.0 | 1440 | 1.5355 | 0.3524 |
| 1.5258 | 9.0 | 1620 | 1.5112 | 0.3590 |
| 1.5258 | 10.0 | 1800 | 1.4870 | 0.3742 |
| 1.5258 | 11.0 | 1980 | 1.4729 | 0.3749 |
| 1.4424 | 12.0 | 2160 | 1.4664 | 0.3938 |
| 1.4424 | 13.0 | 2340 | 1.4524 | 0.4003 |
| 1.4002 | 14.0 | 2520 | 1.4390 | 0.4061 |
| 1.4002 | 15.0 | 2700 | 1.4317 | 0.4090 |
| 1.4002 | 16.0 | 2880 | 1.4241 | 0.4155 |
| 1.376 | 17.0 | 3060 | 1.4201 | 0.4148 |
| 1.376 | 18.0 | 3240 | 1.4069 | 0.4083 |
| 1.376 | 19.0 | 3420 | 1.4000 | 0.4184 |
| 1.3533 | 20.0 | 3600 | 1.3978 | 0.4235 |
| 1.3533 | 21.0 | 3780 | 1.3929 | 0.4329 |
| 1.3533 | 22.0 | 3960 | 1.3896 | 0.4329 |
| 1.3336 | 23.0 | 4140 | 1.3856 | 0.4264 |
| 1.3336 | 24.0 | 4320 | 1.3833 | 0.4322 |
| 1.3254 | 25.0 | 4500 | 1.3787 | 0.4235 |
| 1.3254 | 26.0 | 4680 | 1.3744 | 0.4329 |
| 1.3254 | 27.0 | 4860 | 1.3751 | 0.4300 |
| 1.3082 | 28.0 | 5040 | 1.3720 | 0.4336 |
| 1.3082 | 29.0 | 5220 | 1.3687 | 0.4300 |
| 1.3082 | 30.0 | 5400 | 1.3674 | 0.4293 |
| 1.3105 | 31.0 | 5580 | 1.3663 | 0.4373 |
| 1.3105 | 32.0 | 5760 | 1.3643 | 0.4351 |
| 1.3105 | 33.0 | 5940 | 1.3630 | 0.4271 |
| 1.295 | 34.0 | 6120 | 1.3628 | 0.4322 |
| 1.295 | 35.0 | 6300 | 1.3625 | 0.4300 |
| 1.295 | 36.0 | 6480 | 1.3623 | 0.4307 |
| 1.2919 | 37.0 | 6660 | 1.3617 | 0.4322 |
| 1.2919 | 38.0 | 6840 | 1.3613 | 0.4315 |
| 1.2905 | 39.0 | 7020 | 1.3610 | 0.4300 |
| 1.2905 | 40.0 | 7200 | 1.3610 | 0.4300 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 |
mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF | mradermacher | "2024-10-31T12:30:08Z" | 24 | 1 | transformers | [
"transformers",
"gguf",
"en",
"base_model:hiratagoh/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e",
"base_model:quantized:hiratagoh/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2024-10-30T14:51:18Z" | ---
base_model: hiratagoh/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/hiratagoh/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q2_K.gguf) | Q2_K | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q3_K_L.gguf) | Q3_K_L | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.IQ4_XS.gguf) | IQ4_XS | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q5_K_M.gguf) | Q5_K_M | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q6_K.gguf) | Q6_K | 5.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e-GGUF/resolve/main/Swallow-7b-hf-oasst1-21k-ja-alert-preference-2k-ja-g6e.f16.gguf) | f16 | 13.8 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
elnasharomar2/aragpt2-medium_oknashar | elnasharomar2 | "2023-10-24T05:53:06Z" | 6 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:wikipedia",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-10-22T08:11:57Z" | ---
tags:
- generated_from_trainer
datasets:
- wikipedia
model-index:
- name: aragpt2-medium_oknashar
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. -->
# aragpt2-medium_oknashar
This model is a fine-tuned version of [aubmindlab/aragpt2-medium](https://huggingface.co/aubmindlab/aragpt2-medium) on the wikipedia dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
SicariusSicariiStuff/Phi-lthy4-7.0bpw | SicariusSicariiStuff | "2025-02-12T20:30:33Z" | 0 | 0 | null | [
"safetensors",
"llama",
"license:apache-2.0",
"7-bit",
"exl2",
"region:us"
] | null | "2025-02-12T20:20:58Z" | ---
license: apache-2.0
---
|
baby-dev/022aa1af-2418-4c3a-8fc7-501b6622dd85 | baby-dev | "2025-02-06T14:52:36Z" | 6 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:elyza/Llama-3-ELYZA-JP-8B",
"base_model:adapter:elyza/Llama-3-ELYZA-JP-8B",
"license:llama3",
"region:us"
] | null | "2025-02-06T14:23:03Z" | ---
library_name: peft
license: llama3
base_model: elyza/Llama-3-ELYZA-JP-8B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 022aa1af-2418-4c3a-8fc7-501b6622dd85
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
# 022aa1af-2418-4c3a-8fc7-501b6622dd85
This model is a fine-tuned version of [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5800
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
brew35/23f2dcac-d4d1-4ae6-a43f-d96d159df543 | brew35 | "2025-02-01T09:59:07Z" | 8 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:unsloth/SmolLM-135M-Instruct",
"base_model:adapter:unsloth/SmolLM-135M-Instruct",
"license:apache-2.0",
"8-bit",
"bitsandbytes",
"region:us"
] | null | "2025-02-01T09:46:01Z" | ---
library_name: peft
license: apache-2.0
base_model: unsloth/SmolLM-135M-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 23f2dcac-d4d1-4ae6-a43f-d96d159df543
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: unsloth/SmolLM-135M-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- e6a3c7d274205c36_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/e6a3c7d274205c36_train_data.json
type:
field_input: context
field_instruction: alpaca_prompt_text
field_output: output
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: null
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: null
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: brew35/23f2dcac-d4d1-4ae6-a43f-d96d159df543
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0001
load_in_4bit: true
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 200
micro_batch_size: 4
mlflow_experiment_name: /tmp/e6a3c7d274205c36_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: null
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 43d525c3-01ed-41a2-9424-8b3b5f9b62d7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 43d525c3-01ed-41a2-9424-8b3b5f9b62d7
warmup_steps: 5
weight_decay: 0.0
xformers_attention: null
```
</details><br>
# 23f2dcac-d4d1-4ae6-a43f-d96d159df543
This model is a fine-tuned version of [unsloth/SmolLM-135M-Instruct](https://huggingface.co/unsloth/SmolLM-135M-Instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5893
## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- training_steps: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.1457 | 0.0560 | 200 | 0.5893 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
lesso18/580b4dd2-a471-4cb4-b047-024ae555c2b1 | lesso18 | "2025-03-07T08:32:34Z" | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"custom_code",
"base_model:NousResearch/CodeLlama-13b-hf",
"base_model:adapter:NousResearch/CodeLlama-13b-hf",
"region:us"
] | null | "2025-03-07T05:10:37Z" | ---
library_name: peft
base_model: NousResearch/CodeLlama-13b-hf
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 580b4dd2-a471-4cb4-b047-024ae555c2b1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: NousResearch/CodeLlama-13b-hf
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- be8e5015931e2394_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/be8e5015931e2394_train_data.json
type:
field_input: tools
field_instruction: func_name
field_output: func_desc
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
evals_per_epoch: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: lesso18/580b4dd2-a471-4cb4-b047-024ae555c2b1
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000218
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/be8e5015931e2394_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 500
saves_per_epoch: null
seed: 180
sequence_len: 1024
special_tokens:
pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 93ecb0be-6fb2-4331-bd0d-3ae3a9058eee
wandb_project: 18a
wandb_run: your_name
wandb_runid: 93ecb0be-6fb2-4331-bd0d-3ae3a9058eee
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null
```
</details><br>
# 580b4dd2-a471-4cb4-b047-024ae555c2b1
This model is a fine-tuned version of [NousResearch/CodeLlama-13b-hf](https://huggingface.co/NousResearch/CodeLlama-13b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0007
## 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: 0.000218
- train_batch_size: 4
- eval_batch_size: 4
- seed: 180
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0008 | 1 | 0.9016 |
| 0.0009 | 0.4218 | 500 | 0.0007 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
DBangshu/V3_GPT2_e5_1_6 | DBangshu | "2024-10-16T11:58:29Z" | 131 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-10-16T11:58:01Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
AnonymousOrca/parser_final | AnonymousOrca | "2025-01-22T14:25:36Z" | 20 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-01-22T14:22:47Z" | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
evolveon/Qwen2.5-7B-Instruct-abliterated | evolveon | "2024-10-13T19:15:03Z" | 55 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"chat",
"abliterated",
"uncensored",
"unrestricted",
"conversational",
"en",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-10-12T23:04:25Z" | ---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/evolveon/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- chat
- abliterated
- uncensored
- unrestricted
---
# evolveon/Qwen2.5-7B-Instruct-abliterated
This is an uncensored version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique.
## Usage
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the model and tokenizer
model_name = "evolveon/Qwen2.5-7B-Instruct-abliterated"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Initialize conversation context
initial_messages = [
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}
]
messages = initial_messages.copy() # Copy the initial conversation context
# Enter conversation loop
while True:
# Get user input
user_input = input("User: ").strip() # Strip leading and trailing spaces
# If the user types '/exit', end the conversation
if user_input.lower() == "/exit":
print("Exiting chat.")
break
# If the user types '/clean', reset the conversation context
if user_input.lower() == "/clean":
messages = initial_messages.copy() # Reset conversation context
print("Chat history cleared. Starting a new conversation.")
continue
# If input is empty, prompt the user and continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
# Add user input to the conversation
messages.append({"role": "user", "content": user_input})
# Build the chat template
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
# Tokenize input and prepare it for the model
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# Generate a response from the model
generated_ids = model.generate(
**model_inputs,
max_new_tokens=8192
)
# Extract model output, removing special tokens
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
# Add the model's response to the conversation
messages.append({"role": "assistant", "content": response})
# Print the model's response
print(f"Qwen: {response}")
``` |
Jovie/Dark_Fantasy_Anime | Jovie | "2024-12-18T20:55:16Z" | 24 | 1 | diffusers | [
"diffusers",
"flux",
"text-to-image",
"lora",
"fal",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | "2024-12-18T20:39:07Z" | ---
tags:
- flux
- text-to-image
- lora
- diffusers
- fal
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
widget:
- text: >-
This image is a digital drawing in an anime style, characterized by its
vibrant colors and detailed line work. The subject is a female character
with long, flowing, dark blue hair that extends past her shoulders. Her eyes
are closed, giving her a serene expression. She has pointed ears, which are
a distinctive feature of fantasy characters, and her skin is a pale blue,
contrasting with the darker hues of her hair. She wears a red, ornate
headpiece with a single red gem in the center, and her hands are clasped
together in front of her chest, suggesting a moment of contemplation or
prayer.
output:
url: images/example_07kfq7b1f.png
---
# Dark_Fantasy_Anime model style
<Gallery />
## Model description
## Trigger words
You should use `` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/Jovie/Dark_Fantasy_Anime/tree/main) them in the Files & versions tab. |
Triangle104/Distilled-DarkPlanet-Allades-8B_TIES | Triangle104 | "2025-02-08T00:20:18Z" | 43 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"en",
"arxiv:2306.01708",
"base_model:DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B",
"base_model:merge:DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B",
"base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
"base_model:merge:deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
"base_model:nbeerbower/Llama3.1-Allades-8B",
"base_model:merge:nbeerbower/Llama3.1-Allades-8B",
"license:llama3.1",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2025-02-02T18:47:40Z" | ---
language:
- en
license: llama3.1
library_name: transformers
tags:
- mergekit
- merge
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- nbeerbower/Llama3.1-Allades-8B
- DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
model-index:
- name: Distilled-DarkPlanet-Allades-8B_TIES
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 38.92
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B_TIES
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 29.96
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B_TIES
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 8.38
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B_TIES
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 8.61
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B_TIES
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 8.05
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B_TIES
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 26.68
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Distilled-DarkPlanet-Allades-8B_TIES
name: Open LLM Leaderboard
---
# Merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
Different merge of Allades, Dark-Planet-SF and DS Distilled models, using DS as base. Doesn't seem to trigger thought proccess of Deepseek model, but useful nonetheless.
Sample
-
User: Write a story about an elf called Tyril fighting an owlbear.
Assistant: Tyril, a skilled Elven archer, crouched behind a moss-covered boulder, her piercing emerald eyes fixed on the snarling owlbear in front of her. The creature's yellow eyes glinted with menace as it reared up on its hind legs, its long claws flexing menacingly.
The boulder was no more than 20 feet away from Tyril, but it provided a modicum of cover. The forest floor around her was a tangle of thorny brambles and tall, swaying ferns that offered some concealment, but not enough to make the owlbear's keen eyes miss her.
Tyril inhaled deeply, filling her lungs with the damp, earthy scent of the forest. She mentally prepared herself for the fight ahead, as she had a reputation for being one of the most skilled and deadly archers among the Elven community.
The owlbear was a formidable opponent; its razor-sharp talons could tear through even the thickest of armor, and it possessed brute strength to match any bear. Tyril knew that if she didn't act quickly, her chances of victory would be slim to none. She slowly reached for one of the quivers of arrows at her side.
With a smooth, practiced motion, she nocked an arrow on to her bowstring. The owlbear, sensing her presence, turned its attention fully to Tyril and took a step forward, its claws scraping against the rough bark of a nearby tree as it shifted weight. Tyril's eyes never left the beast, tracking its every movement. She could almost feel the heat emanating from its body, and she knew that if she hesitated for even an instant, she would be within reach of those deadly talons.
Her bowstring hummed as she drew back to her ear, and a steady, measured breath escaped from between her lips. As her fingers released the arrow, it was gone in a flash - a streak of green and black, whirring through the air with a sharp, guttural whoosh. The owlbear, anticipating Tyril's next move, swiped at the arrow as if to knock it out of the sky.
However, Tyril had taken the angle into account, and her aim was true; the arrow struck the owlbear squarely between its eyes with a sickening thud. The creature let out an anguished howl that echoed through the forest, and for a moment, it stumbled backwards, clutching at the wound.
Tyril didn't wait to see if the attack had been effective - she immediately notched another arrow, her bow singing in its familiar rhythm as she drew back to her ear. With an economy of motion, she released the next arrow, which struck the owlbear's shoulder and caused it to rear up in agony.
The beast's howls now took on a desperate edge, and Tyril realized that this was no ordinary attack - the owlbear was not only wounded but also enraged by the pain. This made it an even more formidable foe, as its ferocity increased with every passing moment.
As she readied yet another arrow, Tyril's eyes flicked over to a nearby tree. She had seen a branch snap off under the weight of the owlbear during one of their earlier skirmishes. That same branch now lay on the forest floor about 20 feet from where Tyril was hiding - and in an instant, she decided that it could become her best friend.
Tyril swiftly nocked another arrow and released it with a smooth, practiced motion. The arrow flew true, striking the owlbear in its side, causing it to wince and take a step back. Then, using all of her archer's skill, she expertly guided her next arrow towards where she knew the snapped branch was lying - straight for the owlbear.
The owlbear, as if anticipating Tyril's strategy, swung around with an arm-like motion. The force of its swipe sent a flurry of leaves and twigs flying through the air, but, to Tyril's surprise, it failed to connect with the branch that she had aimed at. Instead, it missed by a fraction - but not before its razor-sharp talons brushed against her bow, sending a shiver of fear down Tyril's spine as the edge of the bow scraped and almost broke under the owlbear's swipe.
The creature's howls grew even more frantic now, as if enraged by its own ineptitude. However, this was merely a momentary setback for both combatants - Tyril knew that the owlbear would be back to try and claim her as its next meal in no time.
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) as a base.
### Models Merged
The following models were included in the merge:
* [nbeerbower/Llama3.1-Allades-8B](https://huggingface.co/nbeerbower/Llama3.1-Allades-8B)
* [DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B](https://huggingface.co/DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: nbeerbower/Llama3.1-Allades-8B
parameters:
density: 0.5
weight: 1
- model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
parameters:
density: 0.5
weight: 1
merge_method: ties
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
parameters:
normalize: true
int8_mask: true
dtype: float16
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/Triangle104__Distilled-DarkPlanet-Allades-8B_TIES-details)
| Metric |Value|
|-------------------|----:|
|Avg. |20.10|
|IFEval (0-Shot) |38.92|
|BBH (3-Shot) |29.96|
|MATH Lvl 5 (4-Shot)| 8.38|
|GPQA (0-shot) | 8.61|
|MuSR (0-shot) | 8.05|
|MMLU-PRO (5-shot) |26.68|
|
mradermacher/Llama-3.2-3B-Agent007-GGUF | mradermacher | "2024-10-11T18:50:09Z" | 62 | 1 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:EpistemeAI/Llama-3.2-3B-Agent007",
"base_model:quantized:EpistemeAI/Llama-3.2-3B-Agent007",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | "2024-10-09T08:38:48Z" | ---
base_model: EpistemeAI/Llama-3.2-3B-Agent007
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/EpistemeAI/Llama-3.2-3B-Agent007
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q2_K.gguf) | Q2_K | 1.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.IQ3_XS.gguf) | IQ3_XS | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.IQ3_S.gguf) | IQ3_S | 1.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.IQ3_M.gguf) | IQ3_M | 1.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q3_K_L.gguf) | Q3_K_L | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q5_K_S.gguf) | Q5_K_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q5_K_M.gguf) | Q5_K_M | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q6_K.gguf) | Q6_K | 2.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Agent007-GGUF/resolve/main/Llama-3.2-3B-Agent007.f16.gguf) | f16 | 6.5 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
timm/tiny_vit_5m_224.in1k | timm | "2025-01-21T21:11:16Z" | 422 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"transformers",
"dataset:imagenet-1k",
"arxiv:2207.10666",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-09-01T16:03:55Z" | ---
tags:
- image-classification
- timm
- transformers
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for tiny_vit_5m_224.in1k
A TinyViT image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 5.4
- GMACs: 1.2
- Activations (M): 9.3
- Image size: 224 x 224
- **Papers:**
- TinyViT: Fast Pretraining Distillation for Small Vision Transformers: https://arxiv.org/abs/2207.10666
- **Original:** https://github.com/microsoft/Cream/tree/main/TinyViT
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tiny_vit_5m_224.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tiny_vit_5m_224.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 160, 14, 14])
# torch.Size([1, 320, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tiny_vit_5m_224.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 320, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@InProceedings{tiny_vit,
title={TinyViT: Fast Pretraining Distillation for Small Vision Transformers},
author={Wu, Kan and Zhang, Jinnian and Peng, Houwen and Liu, Mengchen and Xiao, Bin and Fu, Jianlong and Yuan, Lu},
booktitle={European conference on computer vision (ECCV)},
year={2022}
}
```
|
Subsets and Splits