Search is not available for this dataset
pipeline_tag
stringclasses 48
values | library_name
stringclasses 205
values | text
stringlengths 0
18.3M
| metadata
stringlengths 2
1.07B
| id
stringlengths 5
122
| last_modified
null | tags
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
null | null | {"license": "apache-2.0"} | Prajapat/Llama2-7b-chat-hf-finetune-Grammer | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T08:48:13+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** Virionz
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-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)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | Virionz/train2 | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T08:48:57+00:00 |
text-generation | transformers | {} | TETO101/AIRI-70B-V2-INS-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-28T08:49:28+00:00 |
|
null | null | {} | andrealexroom/MultiARoomv0.0.0.1.67 | null | [
"safetensors",
"region:us"
]
| null | 2024-04-28T08:49:41+00:00 |
|
text-generation | null |
# llama-3-8b-instruct-262k-chinese-lora
llama-3-8b-instruct-262k-chinese基于[Llama-3-8B-Instruct-262k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k)，使用ORPO方法，在中英文偏好数据集[shibing624/DPO-En-Zh-20k-Preference](https://huggingface.co/datasets/shibing624/DPO-En-Zh-20k-Preference)
上微调得到的对话模型。
模型的部署、训练等方法详见MedicalGPT的GitHub仓库：[https://github.com/shibing624/MedicalGPT](https://github.com/shibing624/MedicalGPT)
## Relate models
- 完整模型权重：https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese
- lora权重：https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese-lora
## Features
模型优势：
1. 支持超长context length 262k token，适合RAG
2. 支持中英文
3. 支持多轮对话，代码编码、推理能力强，英文知识充分
4. 模型推理需要显存：
Quantization | Peak Usage for Encoding 2048 Tokens | Peak Usage for Generating 8192 Tokens
-- | -- | --
FP16/BF16 | 18.66GB | 24.58GB
Int4 | 9.21GB | 14.62GB
缺点：
1. model size只有8B，知识类问答幻觉明显
2. 中文知识欠缺，容易幻觉，特别是中文古文知识，属于llama类模型通病
## 如何使用
```python
import transformers
import torch
model_id = "shibing624/llama-3-8b-instruct-262k-chinese"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.float16},
device="cuda",
)
messages = [{"role": "system", "content": ""}]
messages.append({"role": "user", "content": "介绍一下机器学习"})
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=512,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9
)
content = outputs[0]["generated_text"][len(prompt):]
print(content)
```
result:
```shell
机器学习（Machine Learning）是一种基于计算机算法的自动数据分析技术，用于从数据中学习并预测未来的结果。它是人工智能（AI）和数据挖掘（Data Mining）的子领域，旨在通过训练和调整算法来发现数据中的模式、关系和规律。
机器学习算法可以分为监督学习、无监督学习和半监督学习三类：
1. 监督学习（Supervised Learning）：在这种类型的学习中，算法被提供带有标签的数据集，用于训练。算法学习如何将输入数据映射到输出数据，并在新数据上进行预测。常见的监督学习算法包括逻辑回归、决策树、支持向量机（SVM）、随机森林和神经网络。
2. 无监督学习（Unsupervised Learning）：在这种类型的学习中，算法没有标签数据。算法学习数据中的模式、结构和关系，并可能发现新的数据集群或特征。常见的无监督学习算法包括聚类、主成分分析（PCA）、独立成分分析（ICA）和高维度数据降维。
3. 半监督学习（Semi-supervised Learning）：在这种类型的学习中，算法被提供部分带有标签的数据集。算法学习如何将输入数据映射到输出数据，并在新数据上进行预测。半监督学习算法结合了监督学习和无监督学习的优点，常见的半监督学习算法包括自我标注（Self-Labeling）和基于图的半监督学习（Graph-based Semi-supervised Learning）。
机器学习的应用广泛，包括自然语言处理、计算机视觉、推荐系统、人工智能和自动驾驶等领域。它的优势包括：
1. 自动化：机器学习算法可以自动从数据中发现模式和关系，无需人为干预。
2. 高效性：机器学习算法可以处理大量数据，并且可以在不需要人为干预的情况下进行预测。
3. 适应性：机器学习算法可以根据数据集的变化和更新进行调整。
4. 精准性：机器学习算法可以通过训练和测试来提高预测的准确性。
```
## train detail
train loss:
<img src="https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese/raw/main/train_lossv2.svg" width="600">
eval loss:
<img src="https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese/raw/main/eval_lossv2.svg" width="600">
# About Llama-3-8B-Instruct-262k
Gradient incorporates your data to deploy autonomous assistants that power critical operations across your business. To learn more or collaborate on a custom model.
This model extends LLama-3 8B's context length from 8k to -> 160K, developed by Gradient, sponsored by compute from [Crusoe Energy](https://huggingface.co/crusoeai). It demonstrates that SOTA LLMs can learn to operate on long context with minimal training (< 200M tokens) by appropriately adjusting RoPE theta.
<img src="https://cdn-uploads.huggingface.co/production/uploads/6585dc9be92bc5f258156bd6/hiHWva3CbsrnPvZTp5-lu.png" width="600">
**Approach:**
- [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as the base
- NTK-aware interpolation [1] to initialize an optimal schedule for RoPE theta, followed by a new data-driven RoPE theta optimization technique
- Progressive training on increasing context lengths similar to the [Large World Model](https://huggingface.co/LargeWorldModel) [2] (See details below)
**Infra:**
We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 262144 tokens on [Crusoe Energy](https://huggingface.co/crusoeai) high performance L40S cluster.
**Data:**
For training data, we generate long contexts by augmenting [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B).
**Progressive Training Details:**
| Parameter | 65K | 262K |
|-----------------------------|----------------|------------|
| Initialize From | LLaMA-3-8B-Inst| 65K |
| Sequence Length | 2^16 | 2^18 |
| RoPE theta | 15.3 M | 207.1 M |
| Batch Size (Tokens / Step) | 2.097 M | 4.192 M |
| Steps | 30 | 24 |
| Total Tokens | 63 M | 101 M |
| Learning Rate | 2.00E-05 | 2.00E-05 |
| # GPUs | 32 | 32 |
| GPU Type | NVIDIA L40S | NVIDIA L40S|
| {"language": ["zh", "en"], "license": "other", "tags": ["llama3", "chinese", "meta"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE"} | shibing624/llama-3-8b-instruct-262k-chinese-lora | null | [
"safetensors",
"llama3",
"chinese",
"meta",
"text-generation",
"conversational",
"zh",
"en",
"license:other",
"region:us"
]
| null | 2024-04-28T08:50:31+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** LeroyDyer
- **License:** apache-2.0
- **Finetuned from model :** MetaMerge
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "MetaMerge"} | LeroyDyer/MetaMath_LLM | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:MetaMerge",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T08:52:17+00:00 |
text-generation | transformers |
# TinyMoE-DopeykarasuMoe-xslerp
TinyMoE-DopeykarasuMoe-xslerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [aipib/Dopey-karasu-MoE3](https://huggingface.co/aipib/Dopey-karasu-MoE3)
* [AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE](https://huggingface.co/AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: aipib/Dopey-karasu-MoE3
layer_range: [0, 22]
- model: AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
layer_range: [0, 22]
merge_method: slerp
base_model: aipib/Dopey-karasu-MoE3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "aipib/TinyMoE-DopeykarasuMoe-xslerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"tags": ["merge", "mergekit", "lazymergekit", "aipib/Dopey-karasu-MoE3", "AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE"], "base_model": ["aipib/Dopey-karasu-MoE3", "AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE"]} | aipib/TinyMoE-DopeykarasuMoe-xslerp | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"aipib/Dopey-karasu-MoE3",
"AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE",
"conversational",
"base_model:aipib/Dopey-karasu-MoE3",
"base_model:AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T08:53:45+00:00 |
text-generation | transformers | {} | SeemalT/GenAI | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T08:57:04+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | tomaszki/llama-11-b | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T08:57:38+00:00 |
null | transformers |
# 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] | {"library_name": "transformers", "tags": []} | jeongmi/solar_insta_text_generation | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T08:57:56+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** LeroyDyer
- **License:** apache-2.0
- **Finetuned from model :** MetaMerge
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "MetaMerge"} | LeroyDyer/MetaMath_LORA | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:MetaMerge",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T08:58:44+00:00 |
null | null | {} | SeemalT/Llama-2-7b-chat-finetune | null | [
"region:us"
]
| null | 2024-04-28T08:58:58+00:00 |
|
null | null | {} | Highwassed/ruGPT-3.5-13B-GPTQ-finetuned | null | [
"region:us"
]
| null | 2024-04-28T09:00:09+00:00 |
|
null | null | {} | kudfd/data_sense | null | [
"region:us"
]
| null | 2024-04-28T09:00:19+00:00 |
|
null | transformers |
# 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] | {"library_name": "transformers", "tags": []} | DhruvJariwala/falcon-7b-chat | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:00:29+00:00 |
text-classification | transformers |
<!-- 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. -->
# robust_llm_pythia-1b_mz-132_EnronSpam_n-its-10
This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-1b", "model-index": [{"name": "robust_llm_pythia-1b_mz-132_EnronSpam_n-its-10", "results": []}]} | AlignmentResearch/robust_llm_pythia-1b_mz-132_EnronSpam_n-its-10 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-1b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:00:47+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | Blue-kod/phi4strela | null | [
"transformers",
"safetensors",
"phi3",
"text-generation",
"conversational",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
]
| null | 2024-04-28T09:01:04+00:00 |
text-to-speech | transformers |
# Text to Speech Russian free multispeaker model
This is a multiple speakers text-to-speech model for the Russian language. It works on plain text with punctuation separation, and does not require prior conversion of the text into phonemes.
The model with multiple speakers has two voices: 0 - male, 1 - female.
The size of the model is only 15.1 million parameters.
The text accepts lowercase.
For better generation quality, we recommend putting accents in the text before the vowel letters.
We recommend using the "ruaccent" library for accentuation.
To install "ruaccent", use:
```bash
pip install -y ruaccent
```
For test inference use Spaces:
https://huggingface.co/spaces/utrobinmv/tts_ru_free_hf_vits_low_multispeaker
Usage example:
```python
from transformers import VitsModel, AutoTokenizer, set_seed
import torch
import scipy
from ruaccent import RUAccent
# load model
model_name = "utrobinmv/tts_ru_free_hf_vits_low_multispeaker"
model = VitsModel.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model.eval()
# load accentizer
accentizer = RUAccent()
accentizer.load(omograph_model_size='turbo', use_dictionary=True)
set_seed(555) # make deterministic
speaker = 1 # 0-man, 1-woman
text = """Ночью двадцать третьего июня начал извергаться самый высокий
действующий вулкан в Евразии - Кл+ючевской. Об этом сообщила руководитель
Камчатской группы реагирования на вулканические извержения, ведущий
научный сотрудник Института вулканологии и сейсмологии ДВО РАН Ольга Гирина.
«Зафиксированное ночью не просто свечение, а вершинное эксплозивное
извержение стромболианского типа. Пока такое извержение никому не опасно:
ни населению, ни авиации» пояснила ТАСС госпожа Гирина."""
# the placement of accents
text = accentizer.process_all(text)
print(text)
# н+очью дв+адцать тр+етьего и+юня н+ачал изверг+аться с+амый выс+окий
# д+ействующий вулк+ан в евр+азии - ключевск+ой. об +этом сообщ+ила
# руковод+итель камч+атской гр+уппы реаг+ирования на вулкан+ические
# изверж+ения, вед+ущий на+учный сотр+удник инстит+ута вулканол+огии
# и сейсмол+огии дво ран +ольга г+ирина. « зафикс+ированное н+очью не
# пр+осто свеч+ение, а верш+инное эксплоз+ивное изверж+ение
# стромболи+анского т+ипа. пок+а так+ое изверж+ение ником+у не оп+асно:
# ни насел+ению, ни ави+ации » поясн+ила тасс госпож+а г+ирина.
inputs = tokenizer(text, return_tensors="pt")
inputs['speaker_id'] = speaker
with torch.no_grad():
output = model(**inputs).waveform
scipy.io.wavfile.write("tts_audio.wav", rate=model.config.sampling_rate,
data=output[0].cpu().numpy())
```
For displayed in a Jupyter Notebook / Google Colab:
```python
from IPython.display import Audio
Audio(output, rate=model.config.sampling_rate)
```
##
## Languages covered
Russian (ru_RU)
| {"language": ["ru"], "license": "apache-2.0", "tags": ["vits"], "pipeline_tag": "text-to-speech"} | utrobinmv/tts_ru_free_hf_vits_low_multispeaker | null | [
"transformers",
"safetensors",
"vits",
"text-to-audio",
"text-to-speech",
"ru",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
]
| null | 2024-04-28T09:01:05+00:00 |
null | null | {} | iamalexcaspian/Sameer-TheCasagrandes-NourJudeAssaf | null | [
"region:us"
]
| null | 2024-04-28T09:04:44+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": ["trl", "sft"]} | zrowt/Sample-Tests | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:04:59+00:00 |
null | null | {} | hari02/llava-1.5-7b-hf-med9 | null | [
"region:us"
]
| null | 2024-04-28T09:05:44+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | golf2248/ujzlg9u | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:06:36+00:00 |
text-generation | transformers | {"license": "apache-2.0"} | SicariusSicariiStuff/Tenebra_30B_Alpha01_EXL2_8bpw | null | [
"transformers",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:06:56+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | golf2248/9x8ysra | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:07:10+00:00 |
null | transformers |
# 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] | {"library_name": "transformers", "tags": []} | sweety1999/aphasia-wav2vec2-demo-google-colab | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:07:11+00:00 |
null | null | {} | golf2248/2h5spu6 | null | [
"region:us"
]
| null | 2024-04-28T09:07:47+00:00 |
|
null | transformers | {} | anderloh/huggingface_EasyToClassProblem_small | null | [
"transformers",
"safetensors",
"wav2vec2",
"pretraining",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:08:19+00:00 |
|
text-to-audio | transformers |
<!-- 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. -->
# zlm_b32_le4_s8000
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3161
## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 8000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.3712 | 0.2094 | 500 | 0.3402 |
| 0.3792 | 0.4188 | 1000 | 0.3468 |
| 0.374 | 0.6283 | 1500 | 0.3445 |
| 0.3701 | 0.8377 | 2000 | 0.3469 |
| 0.3828 | 1.0471 | 2500 | 0.3560 |
| 0.3697 | 1.2565 | 3000 | 0.3404 |
| 0.3719 | 1.4660 | 3500 | 0.3373 |
| 0.3682 | 1.6754 | 4000 | 0.3358 |
| 0.365 | 1.8848 | 4500 | 0.3351 |
| 0.3759 | 2.0942 | 5000 | 0.3276 |
| 0.3628 | 2.3037 | 5500 | 0.3276 |
| 0.3584 | 2.5131 | 6000 | 0.3218 |
| 0.3543 | 2.7225 | 6500 | 0.3218 |
| 0.3512 | 2.9319 | 7000 | 0.3184 |
| 0.3397 | 3.1414 | 7500 | 0.3170 |
| 0.3392 | 3.3508 | 8000 | 0.3161 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "microsoft/speecht5_tts", "model-index": [{"name": "zlm_b32_le4_s8000", "results": []}]} | mikhail-panzo/zlm_b32_le4_s8000 | null | [
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"base_model:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:09:47+00:00 |
null | null | {} | tekamakshay/mistral-finetuned-alpaca | null | [
"tensorboard",
"safetensors",
"region:us"
]
| null | 2024-04-28T09:10:23+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | hi000000/insta_man_shopping_llama2_koen | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:10:39+00:00 |
text-to-image | diffusers | # Mommyfy
<Gallery />
## Download model
Weights for this model are available in Safetensors format.
[Download](/Hotiam/Mommyfy/tree/main) them in the Files & versions tab.
| {"tags": ["text-to-image", "stable-diffusion", "lora", "diffusers", "template:sd-lora"], "widget": [{"text": "-", "output": {"url": "images/1000047632.png"}}], "base_model": "computational-mama-research/tired-mom-octos"} | Hotiam/Mommyfy | null | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:computational-mama-research/tired-mom-octos",
"region:us"
]
| null | 2024-04-28T09:11:21+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** dmorrigan
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-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)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | dmorrigan/HebrewLyricsLoRA-10K-5Epoch | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:12:24+00:00 |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_opus_books_model
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6958
- Bleu: 4.7464
- Gen Len: 17.83
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 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
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log | 1.0 | 50 | 1.7079 | 4.7151 | 17.795 |
| No log | 2.0 | 100 | 1.6958 | 4.7464 | 17.83 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["bleu"], "base_model": "t5-small", "model-index": [{"name": "my_awesome_opus_books_model", "results": []}]} | sai-vatturi/my_awesome_opus_books_model | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:12:49+00:00 |
null | null | {} | samuelgaddala/chat_bot | null | [
"region:us"
]
| null | 2024-04-28T09:13:08+00:00 |
|
null | null | {} | SAdventureS/yolov8_resample3_0428 | null | [
"region:us"
]
| null | 2024-04-28T09:13:25+00:00 |
|
image-classification | transformers | {} | happieebitees/Happieebitees | null | [
"transformers",
"pytorch",
"vit",
"image-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:13:39+00:00 |
|
text-to-image | 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. -->
# Textual inversion text2image fine-tuning - janetsw/act
These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1-base. You can find some example images in the following.
## 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] | {"license": "creativeml-openrail-m", "library_name": "diffusers", "tags": ["stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "diffusers", "textual_inversion", "diffusers-training"], "base_model": "stabilityai/stable-diffusion-2-1-base", "inference": true} | janetsw/act | null | [
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"diffusers-training",
"base_model:stabilityai/stable-diffusion-2-1-base",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| null | 2024-04-28T09:13:44+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** LeroyDyer
- **License:** apache-2.0
- **Finetuned from model :** MetaMath_LLM
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "MetaMath_LLM"} | LeroyDyer/TruthfulQA_LLM | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:MetaMath_LLM",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:15:39+00:00 |
null | null | {} | samuelgaddala/chat__bot | null | [
"region:us"
]
| null | 2024-04-28T09:15:50+00:00 |
|
text-generation | transformers | # 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:
* [motherfucker0/zhun02](https://huggingface.co/motherfucker0/zhun02)
* [motherfucker0/zhun01](https://huggingface.co/motherfucker0/zhun01)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: motherfucker0/zhun02
layer_range: [0, 30]
- model: motherfucker0/zhun01
layer_range: [0, 30]
merge_method: slerp
base_model: motherfucker0/zhun01
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.02
dtype: bfloat16
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["motherfucker0/zhun02", "motherfucker0/zhun01"]} | motherfucker0/zhen10 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:motherfucker0/zhun02",
"base_model:motherfucker0/zhun01",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:16:13+00:00 |
text-generation | transformers | {"license": "apache-2.0"} | jasdeep06/llama-7b-samsum | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-28T09:16:25+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | shallow6414/jh7n57h | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:17:01+00:00 |
token-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_gliner_like_model
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3393
- Precision: 0.6038
- Recall: 0.5437
- F1: 0.5722
- Accuracy: 0.8834
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3885 | 1.0 | 22210 | 0.3707 | 0.5815 | 0.4752 | 0.5230 | 0.8676 |
| 0.336 | 2.0 | 44420 | 0.3494 | 0.5845 | 0.5272 | 0.5544 | 0.8762 |
| 0.3067 | 3.0 | 66630 | 0.3321 | 0.5987 | 0.5352 | 0.5652 | 0.8813 |
| 0.2827 | 4.0 | 88840 | 0.3372 | 0.6050 | 0.5361 | 0.5685 | 0.8824 |
| 0.2688 | 5.0 | 111050 | 0.3393 | 0.6038 | 0.5437 | 0.5722 | 0.8834 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["precision", "recall", "f1", "accuracy"], "base_model": "microsoft/mdeberta-v3-base", "model-index": [{"name": "my_awesome_gliner_like_model", "results": []}]} | Gmanc/my_awesome_gliner_like_model | null | [
"transformers",
"tensorboard",
"safetensors",
"deberta-v2",
"token-classification",
"generated_from_trainer",
"base_model:microsoft/mdeberta-v3-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:19:02+00:00 |
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2154
- Accuracy: 0.9245
- F1: 0.9245
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8013 | 1.0 | 250 | 0.3036 | 0.9105 | 0.9096 |
| 0.2441 | 2.0 | 500 | 0.2154 | 0.9245 | 0.9245 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["emotion"], "metrics": ["accuracy", "f1"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.9245, "name": "Accuracy"}, {"type": "f1", "value": 0.9245466015583225, "name": "F1"}]}]}]} | WzY1924561588/distilbert-base-uncased-finetuned-emotion | null | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:20:34+00:00 |
null | null | {} | eggconcept/IU | null | [
"region:us"
]
| null | 2024-04-28T09:21:03+00:00 |
|
null | null | {} | andrealexroom/MultiARoomv0.0.0.1.1 | null | [
"safetensors",
"region:us"
]
| null | 2024-04-28T09:21:29+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** LeroyDyer
- **License:** apache-2.0
- **Finetuned from model :** MetaMath_LLM
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "MetaMath_LLM"} | LeroyDyer/TruthfulQA | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:MetaMath_LLM",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:22:04+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** chenqu602
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-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)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | chenqu602/lora_model | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:22:54+00:00 |
text-generation | transformers |
# 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]
| {"library_name": "transformers", "tags": []} | Mxode/TinyStories-LLaMA2-25M-256h-4l-GQA | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:24:12+00:00 |
text2text-generation | transformers | {"language": ["en"], "metrics": ["accuracy"]} | MD1998/chating_beginner_v2 | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:25:10+00:00 |
|
null | null |
Mamba Bit!
Mamba with vocab size 2 bites again! This time we bite at tiny stories.
I didn't bother preprocess them at all, during a training model took random char offset, converted it to bit string and fed to mamba. This time I didn't forget about residual connections nor about norm. As the result model was trained in BF16.
Training code included.
Example to run a model from CLI:
$ python mambabit.py "Run, kitten, run"
Run, kitten, running and jumping. She saw a big tree and thought it would be fun to share the tree. So, she went to the tree and started to climb the tree. She saw a big tree and thought it would be fun to share the tree. So, she went to the tree and saw a big red ball. | {"license": "apache-2.0"} | Maykeye/MambaBitPet-TinyStories | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T09:25:29+00:00 |
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-stock-tweet-sentiment-analysis
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6800
- Accuracy: 0.8228
## 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 | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.5625 | 1.0 | 4800 | 0.4717 | 0.8103 |
| 0.406 | 2.0 | 9600 | 0.4538 | 0.8257 |
| 0.3142 | 3.0 | 14400 | 0.4975 | 0.8269 |
| 0.2374 | 4.0 | 19200 | 0.5879 | 0.8249 |
| 0.1845 | 5.0 | 24000 | 0.6800 | 0.8228 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-stock-tweet-sentiment-analysis", "results": []}]} | siddharth-magesh/distilbert-stock-tweet-sentiment-analysis | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:26:30+00:00 |
null | transformers |
# 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] | {"library_name": "transformers", "tags": []} | Lakoc/ebranchformer_6_128h_for_pretraining_2d | null | [
"transformers",
"wav2vec2-ebranchformer",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:27:22+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": ["trl", "sft"]} | zrowt/Sample-Testss | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:27:32+00:00 |
null | null | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Hermes-2-Pro-Mistral-7B - GGUF
- Model creator: https://huggingface.co/NousResearch/
- Original model: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Hermes-2-Pro-Mistral-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q2_K.gguf) | Q2_K | 2.53GB |
| [Hermes-2-Pro-Mistral-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
| [Hermes-2-Pro-Mistral-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |
| [Hermes-2-Pro-Mistral-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
| [Hermes-2-Pro-Mistral-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |
| [Hermes-2-Pro-Mistral-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q3_K.gguf) | Q3_K | 3.28GB |
| [Hermes-2-Pro-Mistral-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
| [Hermes-2-Pro-Mistral-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
| [Hermes-2-Pro-Mistral-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
| [Hermes-2-Pro-Mistral-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q4_0.gguf) | Q4_0 | 3.83GB |
| [Hermes-2-Pro-Mistral-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
| [Hermes-2-Pro-Mistral-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
| [Hermes-2-Pro-Mistral-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q4_K.gguf) | Q4_K | 4.07GB |
| [Hermes-2-Pro-Mistral-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
| [Hermes-2-Pro-Mistral-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q4_1.gguf) | Q4_1 | 4.24GB |
| [Hermes-2-Pro-Mistral-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q5_0.gguf) | Q5_0 | 4.65GB |
| [Hermes-2-Pro-Mistral-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
| [Hermes-2-Pro-Mistral-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q5_K.gguf) | Q5_K | 4.78GB |
| [Hermes-2-Pro-Mistral-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
| [Hermes-2-Pro-Mistral-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q5_1.gguf) | Q5_1 | 5.07GB |
| [Hermes-2-Pro-Mistral-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf/blob/main/Hermes-2-Pro-Mistral-7B.Q6_K.gguf) | Q6_K | 5.53GB |
Original model description:
---
base_model: mistralai/Mistral-7B-v0.1
tags:
- Mistral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
- function calling
- json mode
model-index:
- name: Hermes-2-Pro-Mistral-7B
results: []
license: apache-2.0
language:
- en
datasets:
- teknium/OpenHermes-2.5
widget:
- example_title: Hermes 2 Pro
messages:
- role: system
content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.
- role: user
content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.
---
# Hermes 2 Pro - Mistral 7B
## Model Description
Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes!
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Thank you to Latitude.sh for sponsoring compute for this model!
## Example Outputs
### Explaining Problems with Quantum Gravity:
### Roleplaying as a Cosmic Super Intelligence:
### Detailing the Theory of AI Consciousness in JSON
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5461|± |0.0145|
| | |acc_norm|0.5623|± |0.0145|
|arc_easy | 0|acc |0.8157|± |0.0080|
| | |acc_norm|0.7934|± |0.0083|
|boolq | 1|acc |0.8688|± |0.0059|
|hellaswag | 0|acc |0.6272|± |0.0048|
| | |acc_norm|0.8057|± |0.0039|
|openbookqa | 0|acc |0.3360|± |0.0211|
| | |acc_norm|0.4300|± |0.0222|
|piqa | 0|acc |0.7954|± |0.0094|
| | |acc_norm|0.7998|± |0.0093|
|winogrande | 0|acc |0.7230|± |0.0126|
```
Average: 71.19
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2047|± |0.0254|
| | |acc_norm|0.2283|± |0.0264|
|agieval_logiqa_en | 0|acc |0.3779|± |0.0190|
| | |acc_norm|0.3932|± |0.0192|
|agieval_lsat_ar | 0|acc |0.2652|± |0.0292|
| | |acc_norm|0.2522|± |0.0287|
|agieval_lsat_lr | 0|acc |0.5216|± |0.0221|
| | |acc_norm|0.5137|± |0.0222|
|agieval_lsat_rc | 0|acc |0.5911|± |0.0300|
| | |acc_norm|0.5836|± |0.0301|
|agieval_sat_en | 0|acc |0.7427|± |0.0305|
| | |acc_norm|0.7184|± |0.0314|
|agieval_sat_en_without_passage| 0|acc |0.4612|± |0.0348|
| | |acc_norm|0.4466|± |0.0347|
|agieval_sat_math | 0|acc |0.3818|± |0.0328|
| | |acc_norm|0.3545|± |0.0323|
```
Average: 44.52
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5579|± |0.0361|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6694|± |0.0245|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3333|± |0.0294|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.2061|± |0.0214|
| | |exact_str_match |0.2256|± |0.0221|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2114|± |0.0154|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.4900|± |0.0289|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.3600|± |0.0215|
|bigbench_navigate | 0|multiple_choice_grade|0.5000|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.6660|± |0.0105|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4420|± |0.0235|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2766|± |0.0142|
|bigbench_snarks | 0|multiple_choice_grade|0.6630|± |0.0352|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.6653|± |0.0150|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.3190|± |0.0147|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2128|± |0.0116|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1737|± |0.0091|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.4900|± |0.0289|
```
Average: 41.65
## TruthfulQA:
```
| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.4100|± |0.0172|
| | |mc2 |0.5911|± |0.0158|
```
# Function Calling Evaluations
We worked with Fireworks.AI on evaluations by starting off with their Function Calling eval dataset, fixing some unsolveable ones, and generating a second eval dataset for JSON mode.
## Function Calling Accuracy: 91%
## JSON Mode Accuracy: 84%
Run the evaluator yourself using @interstellarninja's codebase here:
https://github.com/interstellarninja/function-calling-eval
You can find the evaluation datasets here:
https://huggingface.co/datasets/NousResearch/func-calling-eval
https://huggingface.co/datasets/NousResearch/json-mode-eval
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import LlamaTokenizer, MistralForCausalLM
import bitsandbytes, flash_attn
tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Mistral-7B', trust_remote_code=True)
model = MistralForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Pro-Mistral-7B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Pro-Mistral-7B,
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B]https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)},
title={Hermes-2-Pro-Mistral-7B},
author={"interstellarninja", "Teknium", "theemozilla", "karan4d", "huemin_art"}
}
```
| {} | RichardErkhov/NousResearch_-_Hermes-2-Pro-Mistral-7B-gguf | null | [
"gguf",
"region:us"
]
| null | 2024-04-28T09:27:33+00:00 |
text-classification | transformers |
# 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] | {"library_name": "transformers", "tags": []} | FelixChao/roberta-large-sst2-bitfit | null | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:27:48+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** Virionz
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-bnb-4bit
This gemma 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)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "unsloth/gemma-2b-bnb-4bit"} | Virionz/train3 | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:unsloth/gemma-2b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:28:01+00:00 |
null | null | {"license": "apache-2.0"} | chaanks/hifigan-hubert-l1-3-7-12-18-23-k1000-LibriTTS-100 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T09:28:22+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | quickstep3621/4bwdwws | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:29:46+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | quickstep3621/get5dgy | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:29:51+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | quickstep3621/ir9vzyu | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:29:55+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | quickstep3621/hxj6idn | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:30:00+00:00 |
null | transformers |
<!-- 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. -->
# Mamba for Text Classification
This model was trained from scratch on IMDB dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1901
- Accuracy: 0.9536
It achieves the following results on the evaluation set:
- Loss: 0.1981
- Accuracy: 0.94
## Model description
Mamba model for text classification
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0205 | 0.1 | 625 | 0.2462 | 0.928 |
| 0.671 | 0.2 | 1250 | 0.1958 | 0.9408 |
| 0.5961 | 0.3 | 1875 | 0.2661 | 0.9344 |
| 0.0167 | 0.4 | 2500 | 0.2171 | 0.9412 |
| 0.0007 | 0.5 | 3125 | 0.2095 | 0.9448 |
| 2.6807 | 0.6 | 3750 | 0.1888 | 0.9492 |
| 0.0155 | 0.7 | 4375 | 0.2249 | 0.95 |
| 0.0021 | 0.8 | 5000 | 0.1991 | 0.9528 |
| 0.0134 | 0.9 | 5625 | 0.1920 | 0.9524 |
| 0.1525 | 1.0 | 6250 | 0.1901 | 0.9536 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"tags": ["generated_from_trainer"], "metrics": ["accuracy"], "model-index": [{"name": "mamba_text_classification", "results": []}]} | vubacktracking/mamba_text_classification | null | [
"transformers",
"pytorch",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:30:40+00:00 |
text-to-image | diffusers |
# 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 🧨 diffusers 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] | {"library_name": "diffusers"} | circulus/LCM-canvers-real-v3.8.1 | null | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| null | 2024-04-28T09:30:59+00:00 |
reinforcement-learning | ml-agents |
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: chirbard/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
| {"library_name": "ml-agents", "tags": ["SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget"]} | chirbard/ppo-SnowballTarget | null | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
]
| null | 2024-04-28T09:31:27+00:00 |
null | diffusers | {"license": "apache-2.0"} | uisikdag/ddpm-butterflies-128 | null | [
"diffusers",
"tensorboard",
"safetensors",
"license:apache-2.0",
"diffusers:DDPMPipeline",
"region:us"
]
| null | 2024-04-28T09:32:07+00:00 |
|
text-generation | transformers | # [MaziyarPanahi/WizardLM-2-8x22B-GGUF](https://huggingface.co/MaziyarPanahi/WizardLM-2-8x22B-GGUF)
- Model creator: [microsoft](https://huggingface.co/microsoft)
- Original model: [microsoft/WizardLM-2-8x22B](https://huggingface.co/microsoft/WizardLM-2-8x22B)
## Description
[MaziyarPanahi/WizardLM-2-8x22B-GGUF](https://huggingface.co/MaziyarPanahi/WizardLM-2-8x22B-GGUF) contains GGUF format model files for [microsoft/WizardLM-2-8x22B](https://huggingface.co/microsoft/WizardLM-2-8x22B).
## How to download
You can download only the quants you need instead of cloning the entire repository as follows:
```
huggingface-cli download MaziyarPanahi/WizardLM-2-8x22B-GGUF --local-dir . --include '*Q2_K*gguf'
```
On Windows:
```sh
huggingface-cli download MaziyarPanahi/WizardLM-2-8x22B-GGUF --local-dir . --include *Q4_K_S*gguf
```
## Load sharded model
`llama_load_model_from_file` will detect the number of files and will load additional tensors from the rest of files.
```sh
llama.cpp/main -m WizardLM-2-8x22B.Q2_K-00001-of-00005.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 1024 -e
```
## Prompt template
```
{system_prompt}
USER: {prompt}
ASSISTANT: </s>
```
or
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: {prompt} ASSISTANT: </s>......
```
| {"tags": ["quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "transformers", "safetensors", "mistral", "text-generation", "arxiv:2304.12244", "arxiv:2306.08568", "arxiv:2308.09583", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "text-generation"], "model_name": "WizardLM-2-8x22B-GGUF", "base_model": "microsoft/WizardLM-2-8x22B", "inference": false, "model_creator": "microsoft", "pipeline_tag": "text-generation", "quantized_by": "MaziyarPanahi"} | 754geg/kpok | null | [
"transformers",
"gguf",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"mistral",
"text-generation",
"arxiv:2304.12244",
"arxiv:2306.08568",
"arxiv:2308.09583",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:microsoft/WizardLM-2-8x22B"
]
| null | 2024-04-28T09:32:16+00:00 |
text-generation | transformers | {} | simonycl/self-seq-Llama-2-7b-hf-merged-tulu | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:33:37+00:00 |
|
text-generation | transformers | # 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:
* [motherfucker0/zhun02](https://huggingface.co/motherfucker0/zhun02)
* [motherfucker0/zhun01](https://huggingface.co/motherfucker0/zhun01)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: motherfucker0/zhun02
layer_range: [0, 30]
- model: motherfucker0/zhun01
layer_range: [0, 30]
merge_method: slerp
base_model: motherfucker0/zhun01
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.005
dtype: bfloat16
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["motherfucker0/zhun02", "motherfucker0/zhun01"]} | motherfucker0/zhen11 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:motherfucker0/zhun02",
"base_model:motherfucker0/zhun01",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:34:47+00:00 |
null | null | {} | hippoleveque/marian-finetuned-kde4-en-to-fr | null | [
"region:us"
]
| null | 2024-04-28T09:35:22+00:00 |
|
automatic-speech-recognition | transformers |
<!-- 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. -->
# CRF Transformer Whisper tiny - Vietnamese
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the vlsp2020_vinai_100h dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.40.1
- Pytorch 2.0.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "openai/whisper-small", "model-index": [{"name": "CRF Transformer Whisper tiny - Vietnamese", "results": []}]} | phannhat/CRF_Transformer_Whisper_tiny_vi | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:35:48+00:00 |
image-classification | transformers |
<!-- 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. -->
# finetuned-clothes
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the clothes_simplifiedv2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2225
- Accuracy: 0.9417
## Model description
This model classifies clothes category based on the given image.
## Intended uses
You can use it in a jupyter notebook:
```python
from PIL import Image
import requests
url = 'insert image url here'
image = Image.open(requests.get(url, stream=True).raw)
```
```python
from transformers import AutoModelForImageClassification, AutoImageProcessor
repo_name = "samokosik/finetuned-clothes"
image_processor = AutoImageProcessor.from_pretrained(repo_name)
model = AutoModelForImageClassification.from_pretrained(repo_name)
```
```python
encoding = image_processor(image.convert("RGB"), return_tensors="pt")
print(encoding.pixel_values.shape)
```
```python
import torch
with torch.no_grad():
outputs = model(**encoding)
logits = outputs.logits
```
```python
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
## Limitations
Due to lack of available data, we support only these categories: hat, longsleeve, outswear, pants, shoes, shorts, shortsleve.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.7725 | 0.2058 | 100 | 0.7008 | 0.8178 |
| 0.5535 | 0.4115 | 200 | 0.4494 | 0.8994 |
| 0.4334 | 0.6173 | 300 | 0.3649 | 0.9169 |
| 0.3921 | 0.8230 | 400 | 0.3085 | 0.9184 |
| 0.3695 | 1.0288 | 500 | 0.3091 | 0.9184 |
| 0.2634 | 1.2346 | 600 | 0.3339 | 0.9082 |
| 0.4788 | 1.4403 | 700 | 0.2827 | 0.9257 |
| 0.3337 | 1.6461 | 800 | 0.2499 | 0.9344 |
| 0.34 | 1.8519 | 900 | 0.2586 | 0.9315 |
| 0.2424 | 2.0576 | 1000 | 0.2248 | 0.9402 |
| 0.1559 | 2.2634 | 1100 | 0.2333 | 0.9344 |
| 0.351 | 2.4691 | 1200 | 0.2495 | 0.9359 |
| 0.2206 | 2.6749 | 1300 | 0.2622 | 0.9242 |
| 0.3814 | 2.8807 | 1400 | 0.3138 | 0.9155 |
| 0.2141 | 3.0864 | 1500 | 0.2613 | 0.9315 |
| 0.112 | 3.2922 | 1600 | 0.2266 | 0.9402 |
| 0.0631 | 3.4979 | 1700 | 0.2255 | 0.9402 |
| 0.1986 | 3.7037 | 1800 | 0.2225 | 0.9417 |
| 0.2345 | 3.9095 | 1900 | 0.2235 | 0.9373 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
## Training dataset
This model was trained on the following dataset: https://huggingface.co/datasets/samokosik/clothes_simplifiedv2
| {"license": "apache-2.0", "tags": ["image-classification", "generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "finetuned-clothes", "results": []}]} | samokosik/finetuned-clothes | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:35:54+00:00 |
null | transformers |
# 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] | {"library_name": "transformers", "tags": []} | Mariyyah/mersal-model | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:36:13+00:00 |
text-generation | transformers | <!DOCTYPE html>
<style>
body {
font-family: 'Quicksand', sans-serif;
background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%);
color: #D8DEE9;
margin: 0;
padding: 0;
font-size: 16px;
}
.container {
width: 80%;
max-width: 800px;
margin: 20px auto;
background-color: rgba(255, 255, 255, 0.02);
padding: 20px;
border-radius: 12px;
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
backdrop-filter: blur(10px);
border: 1px solid rgba(255, 255, 255, 0.1);
}
.header h1 {
font-size: 28px;
color: #ECEFF4;
margin: 0 0 20px 0;
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
}
.update-section {
margin-top: 30px;
}
.update-section h2 {
font-size: 24px;
color: #88C0D0;
}
.update-section p {
font-size: 16px;
line-height: 1.6;
color: #ECEFF4;
}
.info img {
width: 100%;
border-radius: 10px;
margin-bottom: 15px;
}
a {
color: #88C0D0;
text-decoration: none;
}
a:hover {
color: #A3BE8C;
}
.button {
display: inline-block;
background-color: #5E81AC;
color: #E5E9F0;
padding: 10px 20px;
border-radius: 5px;
cursor: pointer;
text-decoration: none;
}
.button:hover {
background-color: #81A1C1;
}
</style>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Umbra-v3-MoE-4x11b Data Card</title>
<link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
</head>
<body>
<div class="container">
<div class="header">
<h1>Umbra-v3-MoE-4x11b</h1>
</div>
<div class="info">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/MHmVGOLGh4I5MfQ83iiXS.jpeg">
<p><strong>Creator:</strong> <a href="https://huggingface.co/Steelskull" target="_blank">SteelSkull</a></p>
<p><strong>About Umbra-v3-MoE-4x11b:</strong> A Mixture of Experts model designed for general assistance with a special knack for storytelling and RP/ERP</p>
<p>Integrates models from notable sources for enhanced performance in diverse tasks.</p>
<p><strong>Source Models:</strong></p>
<ul>
<li><a href="https://huggingface.co/Himitsui/Kaiju-11B">Himitsui/Kaiju-11B</a></li>
<li><a href="https://huggingface.co/Sao10K/Fimbulvetr-11B-v2">Sao10K/Fimbulvetr-11B-v2</a></li>
<li><a href="https://huggingface.co/decapoda-research/Antares-11b-v2">decapoda-research/Antares-11b-v2</a></li>
<li><a href="https://huggingface.co/beberik/Nyxene-v3-11B">beberik/Nyxene-v3-11B</a></li>
</ul>
</div>
<div class="update-section">
<h2>Update-Log:</h2>
<p>The [Umbra Series] keeps rolling out from the [Lumosia Series] garage, aiming to be your digital Alfred with a side of Shakespeare for those RP/ERP nights.</p>
<p><strong>What's Fresh in v3?</strong></p>
<p>Didn’t reinvent the wheel, just slapped on some fancier rims. Upgraded the models and tweaked the prompts a bit. Now, Umbra's not just a general use LLM; it's also focused on spinning stories and "Stories".</p>
<p><strong>Negative Prompt Minimalism</strong></p>
<p>Got the prompts to do a bit of a diet and gym routine—more beef on the positives, trimming down the negatives as usual with a dash of my midnight musings.</p>
<p><strong>Still Guessing, Aren’t We?</strong></p>
<p>Just so we're clear, "v3" is not the messiah of updates. It’s another experiment in the saga.</p>
<p>Dive into Umbra v3 and toss your two cents my way. Your feedback is the caffeine in my code marathon.</p>
<p><strong></strong>Exl2 available by:</strong></p>
<p>EXL2-Rpcal = <a href="https://huggingface.co/AzureBlack/Umbra-v3-MoE-4x11b-exl2-8bpw-8h-rpcal" target="_blank">AzureBlack</p>
<p></p>
<p>GGUF = <a href="https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-GGUF" target="_blank">mradermacher</p>
</div>
</div>
</body>
</html>
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Steelskull__Umbra-v3-MoE-4x11b)
| Metric |Value|
|---------------------------------|----:|
|Avg. |73.09|
|AI2 Reasoning Challenge (25-Shot)|68.43|
|HellaSwag (10-Shot) |87.83|
|MMLU (5-Shot) |65.99|
|TruthfulQA (0-shot) |69.30|
|Winogrande (5-shot) |83.90|
|GSM8k (5-shot) |63.08|
| {"license": "apache-2.0", "tags": ["moe", "frankenmoe", "merge", "mergekit", "Himitsui/Kaiju-11B", "Sao10K/Fimbulvetr-11B-v2", "decapoda-research/Antares-11b-v2", "beberik/Nyxene-v3-11B"], "base_model": ["Himitsui/Kaiju-11B", "Sao10K/Fimbulvetr-11B-v2", "decapoda-research/Antares-11b-v2", "beberik/Nyxene-v3-11B"], "model-index": [{"name": "Umbra-v3-MoE-4x11b", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 68.43, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 87.83, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 65.99, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 69.3}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 83.9, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 63.08, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b", "name": "Open LLM Leaderboard"}}]}]} | Nanner-kins/Umbra-v3-MoE-4x11b-3.5bpw-h6-exl2 | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"Himitsui/Kaiju-11B",
"Sao10K/Fimbulvetr-11B-v2",
"decapoda-research/Antares-11b-v2",
"beberik/Nyxene-v3-11B",
"conversational",
"base_model:Himitsui/Kaiju-11B",
"base_model:Sao10K/Fimbulvetr-11B-v2",
"base_model:decapoda-research/Antares-11b-v2",
"base_model:beberik/Nyxene-v3-11B",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:37:00+00:00 |
reinforcement-learning | stable-baselines3 |
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
| {"library_name": "stable-baselines3", "tags": ["PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "A2C", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "PandaReachDense-v3", "type": "PandaReachDense-v3"}, "metrics": [{"type": "mean_reward", "value": "-0.21 +/- 0.11", "name": "mean_reward", "verified": false}]}]}]} | ed-butcher/a2c-PandaReachDense-v3 | null | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| null | 2024-04-28T09:40:16+00:00 |
null | null | {} | sandralopez/graudio2 | null | [
"region:us"
]
| null | 2024-04-28T09:41:44+00:00 |
|
null | null | {} | ArtChicken/sdxl_base_models | null | [
"region:us"
]
| null | 2024-04-28T09:42:30+00:00 |
|
null | null | {} | sentuLLL/starcoder-3b-ft-lora-2048 | null | [
"tensorboard",
"safetensors",
"region:us"
]
| null | 2024-04-28T09:43:16+00:00 |
|
feature-extraction | transformers | {} | jenesys-ai/ark_lvlm-8bit | null | [
"transformers",
"safetensors",
"arkvl_chat",
"feature-extraction",
"custom_code",
"arxiv:1910.09700",
"8-bit",
"region:us"
]
| null | 2024-04-28T09:43:28+00:00 |
|
text2text-generation | transformers |
<!-- 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. -->
# t5-finetuned-en-to-ru-eval1
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 2.6224
- eval_bleu: 0.0
- eval_gen_len: 7.656
- eval_runtime: 5.8186
- eval_samples_per_second: 85.931
- eval_steps_per_second: 1.89
- step: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "t5-base", "model-index": [{"name": "t5-finetuned-en-to-ru-eval1", "results": []}]} | tsetsuuhei/t5-finetuned-en-to-ru-eval1 | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:t5-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:43:45+00:00 |
text-generation | transformers |
This model was trained (Causal Language Modelling) on 5000 SEC documents.
The dataset can be found at: https://huggingface.co/datasets/ali77sina/SEC-just-text | {"license": "apache-2.0"} | ali77sina/SECGPT | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:44:29+00:00 |
text-generation | transformers |
<!-- 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. -->
# danielkosyratest2
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- 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 4.37.2
- Pytorch 2.2.1+cpu
- Datasets 2.19.0
- Tokenizers 0.15.1
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "gpt2", "model-index": [{"name": "danielkosyratest2", "results": []}]} | danielkosyra/danielkosyratest2 | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:gpt2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:45:24+00:00 |
null | null | {} | ivykopal/czech_prompt_100k | null | [
"region:us"
]
| null | 2024-04-28T09:45:25+00:00 |
|
null | null | {"license": "apache-2.0"} | EliaSan/ChatBot | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T09:46:57+00:00 |
|
null | null | {} | Someshfengde/snakeclef_all | null | [
"region:us"
]
| null | 2024-04-28T09:47:56+00:00 |
|
text-to-image | 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. -->
# DreamBooth - mrtuandao/dreambooth-nguoideptrainhatthegioi
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on nguoideptrainhatthegioi using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
## 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] | {"license": "creativeml-openrail-m", "library_name": "diffusers", "tags": ["text-to-image", "dreambooth", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers"], "base_model": "runwayml/stable-diffusion-v1-5", "inference": true, "instance_prompt": "nguoideptrainhatthegioi"} | mrtuandao/dreambooth-nguoideptrainhatthegioi | null | [
"diffusers",
"safetensors",
"text-to-image",
"dreambooth",
"diffusers-training",
"stable-diffusion",
"stable-diffusion-diffusers",
"base_model:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| null | 2024-04-28T09:50:03+00:00 |
null | transformers |
# 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] | {"library_name": "transformers", "tags": []} | team-sanai/llama2_0.1B_lora_atten_fleeze_sample | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:50:12+00:00 |
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert_train
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert_train", "results": []}]} | KhangSimple/distilbert_train | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:52:16+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | shallow6414/rzias1u | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:52:58+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | happylayers/sc71 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T09:53:07+00:00 |
null | null | {} | nndang/checkpoint_wav2vec_synthetic_journal_10 | null | [
"tensorboard",
"safetensors",
"region:us"
]
| null | 2024-04-28T09:57:15+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | golf2248/js1ou65 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:58:47+00:00 |
null | null | {} | TommyZQ/wukong-1b-sft-full | null | [
"region:us"
]
| null | 2024-04-28T09:59:18+00:00 |
|
null | peft |
<!-- 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. -->
# tulu2-7b-cost-UI-both-5e-7
This model is a fine-tuned version of [allenai/tulu-2-7b](https://huggingface.co/allenai/tulu-2-7b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6928
- Rewards/chosen: -0.0002
- Rewards/rejected: -0.0001
- Rewards/accuracies: 0.5159
- Rewards/margins: -0.0001
- Rewards/margins Max: 0.0190
- Rewards/margins Min: -0.0190
- Rewards/margins Std: 0.0125
- Logps/rejected: -338.8891
- Logps/chosen: -345.6230
- Logits/rejected: 0.8420
- Logits/chosen: 0.7124
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Rewards/margins Max | Rewards/margins Min | Rewards/margins Std | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:-------------------:|:-------------------:|:-------------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.6764 | 1.0 | 289 | 0.6928 | -0.0002 | -0.0001 | 0.5159 | -0.0001 | 0.0190 | -0.0190 | 0.0125 | -338.8891 | -345.6230 | 0.8420 | 0.7124 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "allenai/tulu-2-7b", "model-index": [{"name": "tulu2-7b-cost-UI-both-5e-7", "results": []}]} | just1nseo/tulu2-7b-cost-UI-both-5e-7 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:allenai/tulu-2-7b",
"region:us"
]
| null | 2024-04-28T09:59:19+00:00 |
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | golf2248/6vujbo9 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:59:23+00:00 |
text-to-image | 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 - AdityaNath/Rus_Arch_LoRA
<Gallery />
## Model description
These are AdityaNath/Rus_Arch_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 a photo of Rus_Arch Architecture to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](AdityaNath/Rus_Arch_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] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a photo of Rus_Arch Architecture", "widget": []} | AdityaNath/Rus_Arch_LoRA | null | [
"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",
"license:openrail++",
"region:us"
]
| null | 2024-04-28T09:59:32+00:00 |
null | null | {} | 4piken/Llama-3-Gozaru-8B-Instruct.gguf | null | [
"gguf",
"region:us"
]
| null | 2024-04-28T09:59:35+00:00 |
|
text-generation | transformers |
# 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] | {"library_name": "transformers", "tags": []} | golf2248/scrzq9s | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T09:59:59+00:00 |
text-generation | transformers | Ru-adapted phi-2 (change the tokenizer and the embeddings layer like here: https://russiansuperglue.com/login/submit_info/2899). Unfortunately, they left no code behind so I can only hope my code's correct.
Model hasn't been trained yet. It will undergo full parameter second-stage pre-training. | {"license": "apache-2.0"} | Defetya/ru_adapted_phi-2 | null | [
"transformers",
"safetensors",
"phi",
"text-generation",
"custom_code",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T10:01:18+00:00 |
text-to-audio | transformers |
<!-- 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. -->
# zlm_b128_le5_s4000
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3979
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- 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_steps: 2000
- training_steps: 4010
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.6764 | 0.8375 | 500 | 0.5792 |
| 0.5579 | 1.6750 | 1000 | 0.4839 |
| 0.5004 | 2.5126 | 1500 | 0.4486 |
| 0.4789 | 3.3501 | 2000 | 0.4311 |
| 0.4555 | 4.1876 | 2500 | 0.4116 |
| 0.4521 | 5.0251 | 3000 | 0.4070 |
| 0.4372 | 5.8626 | 3500 | 0.3982 |
| 0.4451 | 6.7002 | 4000 | 0.3979 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "microsoft/speecht5_tts", "model-index": [{"name": "zlm_b128_le5_s4000", "results": []}]} | mikhail-panzo/zlm_b128_le5_s4000 | null | [
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"base_model:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T10:01:56+00:00 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.