Instructions to use abhiyanta/Llama-chatDoctor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abhiyanta/Llama-chatDoctor with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="abhiyanta/Llama-chatDoctor")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("abhiyanta/Llama-chatDoctor")
model = AutoModelForMultimodalLM.from_pretrained("abhiyanta/Llama-chatDoctor")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abhiyanta/Llama-chatDoctor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abhiyanta/Llama-chatDoctor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abhiyanta/Llama-chatDoctor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abhiyanta/Llama-chatDoctor

SGLang

How to use abhiyanta/Llama-chatDoctor 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 "abhiyanta/Llama-chatDoctor" \
    --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": "abhiyanta/Llama-chatDoctor",
		"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 "abhiyanta/Llama-chatDoctor" \
        --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": "abhiyanta/Llama-chatDoctor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abhiyanta/Llama-chatDoctor with Docker Model Runner:
```
docker model run hf.co/abhiyanta/Llama-chatDoctor
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LLaMA 3 8B - ChatDoctor Model

Model Description

This is a fine-tuned version of the LLaMA 3 8B model. The model is fine-tuned on medical conversations to assist healthcare professionals and users in understanding medical-related queries. It’s designed for natural language understanding and generation, focusing on medical advice and diagnostics.

Base Model: LLaMA 3 8B
Fine-Tuned On: Medical QA dataset (or specify other datasets)
Model Type: Causal Language Model (CLM)

Intended Use

This model is intended for generating conversational responses related to medical diagnostics, symptom analysis, or any medical-related inquiry. It is designed to assist in providing informative and preliminary medical guidance based on the fine-tuned datasets.

Use Cases:

Medical chatbots.
Healthcare consultation apps.
Symptom analysis.

Limitations:

Not a replacement for professional medical advice: The model is trained on limited datasets and should not be used as a standalone diagnostic tool.
Language Bias: It may show biases based on the data it was trained on.

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the fine-tuned model and tokenizer
model = AutoModelForCausalLM.from_pretrained("abhiyanta/llama-chatdoctor")
tokenizer = AutoTokenizer.from_pretrained("abhiyanta/llama-chatdoctor")

Downloads last month: 4

Model tree for abhiyanta/Llama-chatDoctor

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Finetuned

(1127)

this model

Quantizations

2 models