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

Medfalcon V2 40B Lora by nmitchko

 »  All LLMs  »  nmitchko  »  Medfalcon V2 40B Lora   URL Share it on

  4   
  Arxiv:2106.09685   Adapter Base model:adapter:tiiuae/falc...   Base model:tiiuae/falcon-40b   En   Finetuned   Lora   Medical   Peft   Region:us
Model Card on HF 🤗: https://huggingface.co/nmitchko/medfalcon-v2-40b-lora 

Medfalcon V2 40B Lora Benchmarks

LLME Score: 0.09986
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Medfalcon V2 40B Lora (nmitchko/medfalcon-v2-40b-lora)
🌟 Advertise your project 🚀

Medfalcon V2 40B Lora Parameters and Internals

Model Type 
LoRA, language model, text generation
Use Cases 
Areas:
medical domain tasks
Primary Use Cases:
question-answering, medical dialogue tasks
Limitations:
Do not use to treat patients! Treat AI content as if you wrote it!!!
Additional Notes 
Supports 4-bit and 8-bit modes.
Training Details 
Data Sources:
medconcat dataset
Data Volume:
100 MiB of raw text
Methodology:
LoRA, specifically QLora
Model Architecture:
LoRA applied to Falcon-40b for medical domain tasks
LLM NameMedfalcon V2 40B Lora
Repository 🤗https://huggingface.co/nmitchko/medfalcon-v2-40b-lora 
Base Model(s)  Falcon 40B   tiiuae/falcon-40b
Model Size40b
Required VRAM0.9 GB
Updated2025-08-24
Maintainernmitchko
Model Files  0.9 GB
Supported Languagesen
Model ArchitectureAdapter
Licensecc-by-nc-4.0
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdense|query_key_value|dense_h_to_4h|dense_4h_to_h
LoRA Alpha16
LoRA Dropout0.05
R Param64

Best Alternatives to Medfalcon V2 40B Lora

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 40B Code Alpaca Lora0K / 0 GB02
Medfalcon 40B Lora0K / 0.9 GB03
Falcon 40B Chat V0.10K / 0 GB738
... 40B Int4 Peft Lora Sfttrainer0K / 1.8 GB012
Falcon 40B Guanaco Lora0K / 0.2 GB04
Falcon 40B Qlora Oasst De0K / 1.8 GB02
...lcon Lora 40b Ckpt 500 Oasst 10K / 1.8 GB01
...e WizardLM Uncensored 40B Lora0K / 0.1 GB01
Note: green Score (e.g. "73.2") means that the model is better than nmitchko/medfalcon-v2-40b-lora.

Rank the Medfalcon V2 40B Lora 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? 50856 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