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
Publish certified lm-eval benchmark results (USMLE 64.10%, MedMCQA 61.15%, PubMedQA 75.80%)
Browse files
AxonMed_7B_Technical_Report.pdf
CHANGED
|
@@ -52,7 +52,7 @@ endobj
|
|
| 52 |
endobj
|
| 53 |
9 0 obj
|
| 54 |
<<
|
| 55 |
-
/Author (\(anonymous\)) /CreationDate (D:
|
| 56 |
/Subject (\(unspecified\)) /Title (\(anonymous\)) /Trapped /False
|
| 57 |
>>
|
| 58 |
endobj
|
|
@@ -93,7 +93,7 @@ xref
|
|
| 93 |
trailer
|
| 94 |
<<
|
| 95 |
/ID
|
| 96 |
-
[<
|
| 97 |
% ReportLab generated PDF document -- digest (opensource)
|
| 98 |
|
| 99 |
/Info 9 0 R
|
|
|
|
| 52 |
endobj
|
| 53 |
9 0 obj
|
| 54 |
<<
|
| 55 |
+
/Author (\(anonymous\)) /CreationDate (D:20261113055037+05'00') /Creator (\(unspecified\)) /Keywords () /ModDate (D:20261113055037+05'00') /Producer (ReportLab PDF Library - \(opensource\))
|
| 56 |
/Subject (\(unspecified\)) /Title (\(anonymous\)) /Trapped /False
|
| 57 |
>>
|
| 58 |
endobj
|
|
|
|
| 93 |
trailer
|
| 94 |
<<
|
| 95 |
/ID
|
| 96 |
+
[<6b5ad3a46537dcd4752b9c27374c5a37><6b5ad3a46537dcd4752b9c27374c5a37>]
|
| 97 |
% ReportLab generated PDF document -- digest (opensource)
|
| 98 |
|
| 99 |
/Info 9 0 R
|