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

Medichat Llama3 8B by sethuiyer

 »  All LLMs  »  sethuiyer  »  Medichat Llama3 8B   URL Share it on

  1535   
  Merged Model   16bit   Autotrain compatible Base model:locutusque/llama-3-... Base model:ruslanmv/medical-ll... Base model:undi95/llama-3-unho...   Conversational Dataset:jondurbin/airoboros-3....   Dataset:m-a-p/code-feedback Dataset:maziyarpanahi/wizardlm... Dataset:microsoft/orca-math-wo... Dataset:mlabonne/orpo-dpo-mix-... Dataset:open-orca/slimorca-ded... Dataset:ruslanmv/ai-medical-ch...   En   Endpoints compatible   Instruct   Llama   Medical   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sethuiyer/Medichat-Llama3-8B 

Medichat Llama3 8B Benchmarks

ARC: 59.13 vs 96.7 (so35)-38.9%
HellaSwag: 82.9 vs 95.3 (gpt4)-13%
MMLU: 65.19 vs 88.3 (so35)-26.2%
TruthfulQA: 49.65 vs 59 (gpt4)-15.8%
WinoGrande: 78.93 vs 87.5 (gpt4)-9.8%
GSM8K: 60.35 vs 96.4 (so35)-37.4%
LLME Score: 0.21245
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Medichat Llama3 8B (sethuiyer/Medichat-Llama3-8B)

Medichat Llama3 8B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Medical
Applications:
Medical consultation, Health information
Primary Use Cases:
Medical advice, Health discussions
Additional Notes 
The model is available in quantized versions for easier deployment.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
mlabonne/orpo-dpo-mix-40k, Open-Orca/SlimOrca-Dedup, jondurbin/airoboros-3.2, microsoft/orca-math-word-problems-200k, m-a-p/Code-Feedback, MaziyarPanahi/WizardLM_evol_instruct_V2_196k, ruslanmv/ai-medical-chatbot
Model Architecture:
LLaMa-3
Input Output 
Input Format:
Chat-based prompts
Accepted Modalities:
text
Output Format:
Generated text responses
Performance Tips:
Ensure that the prompt is clear and specific to medical topics for optimal performance.
LLM NameMedichat Llama3 8B
Repository 🤗https://huggingface.co/sethuiyer/Medichat-Llama3-8B 
Base Model(s)  Llama 3 Unholy 8B   Llama 3 Neural Chat V1 8B   ruslanmv/Medical-Llama3-8B-16bit   Undi95/Llama-3-Unholy-8B   Locutusque/llama-3-neural-chat-v1-8b   ruslanmv/Medical-Llama3-8B-16bit
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2025-04-25
Maintainersethuiyer
Model Typellama
Instruction-BasedYes
Model Files  2.0 GB: 1-of-9   1.9 GB: 2-of-9   2.0 GB: 3-of-9   1.9 GB: 4-of-9   2.0 GB: 5-of-9   1.9 GB: 6-of-9   2.0 GB: 7-of-9   1.3 GB: 8-of-9   1.1 GB: 9-of-9
Supported Languagesen
Quantization Type16bit
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Medichat Llama3 8B

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB92
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB41
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB22
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB50
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1525
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB1017
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB23
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB21
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB121
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB31

Rank the Medichat Llama3 8B 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? 46677 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