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

Medicine LLM GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Medicine LLM GPTQ   URL Share it on

  33   
  Arxiv:2309.09530   4-bit   Autotrain compatible Base model:adaptllm/medicine-l... Base model:quantized:adaptllm/...   Biology   Dataset:eleutherai/pile   Dataset:gair/lima   Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol...   En   Gptq   Instruct   Llama   Medical   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/medicine-LLM-GPTQ 

Medicine LLM GPTQ Benchmarks

LLME Score: 0.15677
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Medicine LLM GPTQ (TheBloke/medicine-LLM-GPTQ)

Medicine LLM GPTQ Parameters and Internals

Model Type 
llama
Additional Notes 
This repo contains GPTQ model files for AdaptLLM's Medicine LLM with various quantisation parameter permutations for different hardware and requirements.
Supported Languages 
en (unknown)
Training Details 
Data Sources:
Open-Orca/OpenOrca, GAIR/lima, WizardLM/WizardLM_evol_instruct_V2_196k, EleutherAI/pile
Methodology:
continued pre-training on domain-specific corpora transforming into reading comprehension texts
Context Length:
2048
Input Output 
Input Format:
### User Input: {prompt} ### Assistant Output:
Accepted Modalities:
text
Release Notes 
Version:
main
Notes:
4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
Version:
gptq-4bit-32g-actorder_True
Notes:
4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
Version:
gptq-8bit--1g-actorder_True
Notes:
8-bit, with Act Order. No group size, to lower VRAM requirements.
Version:
gptq-8bit-128g-actorder_True
Notes:
8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy.
Version:
gptq-8bit-32g-actorder_True
Notes:
8-bit, with group size 32g and Act Order for maximum inference quality.
Version:
gptq-4bit-64g-actorder_True
Notes:
4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy.
LLM NameMedicine LLM GPTQ
Repository 🤗https://huggingface.co/TheBloke/medicine-LLM-GPTQ 
Model NameMedicine LLM
Model CreatorAdaptLLM
Base Model(s)  Medicine LLM   AdaptLLM/medicine-LLM
Model Size1.1b
Required VRAM3.9 GB
Updated2025-03-14
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  3.9 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLLaMAForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to Medicine LLM GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Finance LLM GPTQ2K / 3.9 GB385

Rank the Medicine LLM GPTQ 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? 45019 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