LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

WiNGPT2 Llama 3 8B Chat AWQ by winninghealth

 »  All LLMs  »  winninghealth  »  WiNGPT2 Llama 3 8B Chat AWQ   URL Share it on

  5   
  4-bit   Autotrain compatible   Awq   Conversational   En   Endpoints compatible   Llama   Medical   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/winninghealth/WiNGPT2-Llama-3-8B-Chat-AWQ 

WiNGPT2 Llama 3 8B Chat AWQ Benchmarks

LLME Score: 0.15183
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
WiNGPT2 Llama 3 8B Chat AWQ (winninghealth/WiNGPT2-Llama-3-8B-Chat-AWQ)
🌟 Advertise your project 🚀

WiNGPT2 Llama 3 8B Chat AWQ Parameters and Internals

Model Type 
医疗垂直领域大模型
Use Cases 
Areas:
医疗行业
Applications:
智能化的医疗问答, 诊断支持, 医学知识服务
Primary Use Cases:
AI问诊和问答功能, 医学知识问答
Limitations:
不能替代医疗专业人士的意见
Considerations:
WiNGPT2提供的信息和建议仅供参考，应寻求医疗专业意见。
Additional Notes 
WiNGPT2旨在提高诊疗效率和医疗服务质量。
Supported Languages 
en (English), zh (Chinese)
Training Details 
Data Sources:
约20G预训练数据, 50万条指令微调对齐数据
Data Volume:
20G
Methodology:
微调/对齐
Context Length:
8192
Hardware Used:
A100*8
Model Architecture:
GPT based
Input Output 
Input Format:
自定义的提示格式
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
WiNGPT2-Llama-3-8B-Chat-AWQ
Date:
2024-04-24
Notes:
更新量化模型
Version:
WiNGPT2-Llama-3-8B-Base
Date:
2024-04-23
Notes:
模型更新与测评结果发布
LLM NameWiNGPT2 Llama 3 8B Chat AWQ
Repository 🤗https://huggingface.co/winninghealth/WiNGPT2-Llama-3-8B-Chat-AWQ 
Base Model(s)  WiNGPT2 Llama 3 8B Chat   winninghealth/WiNGPT2-Llama-3-8B-Chat
Model Size8b
Required VRAM5.8 GB
Updated2025-09-14
Maintainerwinninghealth
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen zh
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.37.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to WiNGPT2 Llama 3 8B Chat AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB50
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB51
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB44
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB50
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB50
Llama 3 8B Instruct AWQ8K / 5.8 GB597725
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB16699
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB13295
Llama 3 ELYZA JP 8B AWQ8K / 5.8 GB11744
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB60
Note: green Score (e.g. "73.2") means that the model is better than winninghealth/WiNGPT2-Llama-3-8B-Chat-AWQ.

Rank the WiNGPT2 Llama 3 8B Chat AWQ Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51368 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer