LLM EXPLORER 61,491 MODELS INDEXED

Llama3 OpenBioLLM 8B by aaditya

By aaditya · 6162 downloads
HF Repo ↗ Copy URL

Llama3 OpenBioLLM 8B is an open-source language model by aaditya. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3, LLM Explorer Score: 0.18, Arc: 58.6, HellaSwag: 80.8, MMLU: 64.4, GSM8K: 10.2.

  Arxiv:2212.13138   Arxiv:2303.13375   Arxiv:2305.09617   Arxiv:2305.18290   Arxiv:2402.07023 Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Chatml   Distillation   Dpo   En   Endpoints compatible   Finetuned   Gpt4   Instruct   Llama   Llama-3   Mixtral   Pytorch   Region:us   Rlhf   Sharded
Model Card on HF 🤗: https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B 

Llama3 OpenBioLLM 8B Parameters and Internals

Model Type 
biomedical, large language model
Use Cases 
Areas:
Research, Biomedical community
Applications:
Clinical note summarization, Medical question answering, Clinical entity recognition, Biomarkers extraction, Classification, De-Identification
Primary Use Cases:
Research assistance in healthcare and biomedical fields
Limitations:
Not evaluated in randomized controlled trials, Not for direct patient care or clinical decision support
Considerations:
Limited to research and exploratory applications by qualified individuals.
Additional Notes 
Model intended for research and non-clinical use. Extensive testing required for clinical settings.
Supported Languages 
en (English)
Training Details 
Data Sources:
Custom Medical Instruct dataset, DPO dataset
Methodology:
Fine-tuned using DPO dataset and diverse medical instruction dataset
Hardware Used:
GPU: H100 80GB SXM5
Input Output 
Input Format:
Chat template from Llama-3 instruct version
Accepted Modalities:
text
Performance Tips:
Use temperature = 0 to reduce verbosity.
Release Notes 
Notes:
A powerful tool for the biomedical domain, advancing open-source models in healthcare and life sciences.
LLM NameLlama3 OpenBioLLM 8B
Repository 🤗https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM16.1 GB
Updated2026-07-17
Maintaineraaditya
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama3 OpenBioLLM 8B

Model
Likes
Downloads
VRAM
...OpenBioLLM 8B Bnb 4bit Smashed076 GB
...OpenBioLLM 8B AWQ 4bit Smashed095 GB
...OpenBioLLM 8B HQQ 2bit Smashed064 GB

Best Alternatives to Llama3 OpenBioLLM 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1135125
UltraLong Thinking4192K / 16.1 GB23
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12418
Cthulhu 8B V1.41048K / 16.1 GB1010
...raLong 1M Instruct Abliterated1048K / 32.1 GB49
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB70259
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB254
Note: green Score (e.g. "73.2") means that the model is better than aaditya/Llama3-OpenBioLLM-8B.