Text Generation
Transformers
Safetensors
English
Hindi
qwen2
medical
healthcare
clinical-reasoning
aiims
neet-pg
usmle
pubmedqa
india
sovereign-ai
axonmed
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use Saathimed/AxonMed-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Saathimed/AxonMed-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Saathimed/AxonMed-7B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Saathimed/AxonMed-7B") model = AutoModelForCausalLM.from_pretrained("Saathimed/AxonMed-7B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Saathimed/AxonMed-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Saathimed/AxonMed-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Saathimed/AxonMed-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Saathimed/AxonMed-7B
- SGLang
How to use Saathimed/AxonMed-7B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Saathimed/AxonMed-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Saathimed/AxonMed-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Saathimed/AxonMed-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Saathimed/AxonMed-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Saathimed/AxonMed-7B with Docker Model Runner:
docker model run hf.co/Saathimed/AxonMed-7B
Commit History
6 days ago
-
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Verified signature093735a -
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Verified signature14ffe98 -
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Verified signature4cde3ee -
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Verified signaturec6156f1 -
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Verified signaturea89fdd0 -
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Verified signature85e91d4
7 days ago
-
Update app.py to load standalone Saathimed/AxonMed-7B directly
Verified signatureafa5693 -
Update README for standalone 16-bit transformers & vLLM compatibility
Verified signature3947323 -
Switch to standalone merged weights
Verified signature1a959a7 -
Switch to standalone merged weights
Verified signature9eb7a21 -
Upload model.safetensors.index.json with huggingface_hub
Verified signatureee34126 -
Upload generation_config.json with huggingface_hub
Verified signatured081844 -
Upload config.json with huggingface_hub
Verified signaturea30cf09 -
Upload model-00004-of-00004.safetensors with huggingface_hub
Verified signature5b6b6fc -
Upload model-00003-of-00004.safetensors with huggingface_hub
Verified signaturea2dcf06 -
Upload model-00002-of-00004.safetensors with huggingface_hub
Verified signature9e5be47 -
Upload model-00001-of-00004.safetensors with huggingface_hub
Verified signature655d23d
8 days ago
-
Add interactive clinical showcase app.py with Neuro-Symbolic calculators
Verified signature259bf82 -
Add official ORCID 0009-0006-7093-6762 badge and researcher link
Verified signaturee743c17 -
Link official Zenodo DOI 10.5281/zenodo.24143274 and badge
Verified signaturee5410b0 -
Add official publication-grade PDF Technical Report
Verified signaturea6ae898 -
Upload adapter_model.safetensors with huggingface_hub
Verified signature6a65ce3 -
Add official scientific technical report and arXiv preprint draft
Verified signature510e988 -
Add official scientific Model Card and Open Medical-LLM Leaderboard metadata
Verified signature15e9e44 -
Initial commit of AxonMed-7B tokenizer and LoRA config
Verified signaturee5a0b3c -
initial commit
Verified signaturec8e162a