Instructions to use solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ")
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 solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ

SGLang

How to use solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ 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 "solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ" \
    --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": "solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ",
		"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 "solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ" \
        --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": "solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ
```

IBI-CAAI/MELT-Mistral-3x7B-Instruct-v0.1 AWQ

Model creator: IBI-CAAI
Original model: MELT-Mistral-3x7B-Instruct-v0.1

Model Summary

The MELT-Mistral-3x7B-Instruct-v0.1 Large Language Model (LLM) is a pretrained generative text model pre-trained and fine-tuned on using publically avalable medical data.

MELT-Mistral-3x7B-Instruct-v0.1 demonstrated a average 19.7% improvement over Mistral-3x7B-Instruct-v0.1 (MoE of 3 X Mistral-7B-Instruct-v0.1) across 3 USMLE, Indian AIIMS, and NEET medical examination benchmarks.

This is MoE model, thanks to Charles Goddard for code/tools.

The Medical Education Language Transformer (MELT) models have been trained on a wide-range of text, chat, Q/A, and instruction data in the medical domain.

While the model was evaluated using publically avalable USMLE, Indian AIIMS, and NEET medical examination example questions, its use it intented to be more broadly applicable.

Developed by: Center for Applied AI
Funded by: Institute or Biomedical Informatics
Model type: LLM
Language(s) (NLP): English
License: Apache 2.0
Finetuned from model: A MoE x 3 Mistral-7B-v0.1

Downloads last month: 6

Safetensors

Model size

19B params

Tensor type

I32

F16

Model tree for solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ

Base model

Kentucky-Open-Science/MELT-Mistral-3x7B-Instruct-v0.1

Quantized

(1)

this model

Collection including solidrust/MELT-Mistral-3x7B-Instruct-v0.1-AWQ

3x7B AWQ

Collection

Mixture of experts 3 x 7B. • 5 items • Updated Apr 25, 2024