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

Meditron 7B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Meditron 7B AWQ   URL Share it on

  9046   
  Arxiv:2311.16079   4-bit   Autotrain compatible   Awq Base model:epfl-llm/meditron-7... Base model:quantized:epfl-llm/...   Dataset:epfl-llm/guidelines   En   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/meditron-7B-AWQ 

Meditron 7B AWQ Benchmarks

LLME Score: 0.18831
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meditron 7B AWQ (TheBloke/meditron-7B-AWQ)

Meditron 7B AWQ Parameters and Internals

Model Type 
causal decoder-only transformer language model
Use Cases 
Areas:
AI assistant to enhance clinical decision-making, educational purposes
Applications:
Medical exam question answering, Supporting differential diagnosis, Query for disease information, General health information query
Limitations:
Not suitable for deployment in medical applications without extensive use-case alignment and additional testing
Considerations:
Need careful alignment with specific use cases and rigorous evaluation
Additional Notes 
Meditron models' performance, risks, and biases are under continuous assessment.
Training Details 
Data Sources:
Clinical Guidelines, Medical Paper Abstracts, Medical Papers, Replay Data
Data Volume:
48.1B tokens
Methodology:
Continued pretraining on a curated medical corpus
Context Length:
2048
Hardware Used:
1 node of 8x NVIDIA A100 (80GB) SXM GPUs
Model Architecture:
Llama 2 architecture
Input Output 
Input Format:
Text-only data
Accepted Modalities:
Text
Output Format:
Model generates text only
LLM NameMeditron 7B AWQ
Repository 🤗https://huggingface.co/TheBloke/meditron-7B-AWQ 
Model NameMeditron 7B
Model CreatorEPFL LLM Team
Base Model(s)  Meditron 7B   epfl-llm/meditron-7b
Model Size7b
Required VRAM3.9 GB
Updated2025-02-22
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<PAD>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Meditron 7B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 AWQ195K / 19.3 GB51
Yarn Llama 2 7B 64K AWQ64K / 3.9 GB1160
Calm2 7B Chat AWQ32K / 4.4 GB1022
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB932
... SWE Llama 7B Updated 4bit AWQ16K / 3.9 GB800
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB41480
Pandalyst 7B V1.2 AWQ16K / 3.9 GB801
Tora Code 7B V1.0 AWQ16K / 3.9 GB790
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB771
Pandalyst 7B V1.1 AWQ16K / 3.9 GB791
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/meditron-7B-AWQ.

Rank the Meditron 7B 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? 43508 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 v20241227
  Support LLM Explorer