Instructions to use wvvss/GPUmatLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wvvss/GPUmatLLM with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wvvss/GPUmatLLM")
model = AutoModelForCausalLM.from_pretrained("wvvss/GPUmatLLM", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wvvss/GPUmatLLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/wvvss/GPUmatLLM

SGLang

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

Docker Model Runner
How to use wvvss/GPUmatLLM with Docker Model Runner:
```
docker model run hf.co/wvvss/GPUmatLLM
```

GPUmatLLM

A domain-specific large language model for GPU materials science, obtained by LoRA fine-tuning of Qwen2.5-7B-Instruct.

Model details

Base model: Qwen2.5-7B-Instruct
Adaptation method: LoRA (rank 8)
Domain: GPU packaging materials, thermal management, semiconductor substrates, interconnect materials
Language: Chinese

Intended use

Research use for domain question answering in GPU materials science.

Limitations

Outputs may contain factual errors and should be verified against primary sources before use in engineering decisions.

Citation

Paper under review. Citation information will be added upon publication.

Downloads last month: 104

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for wvvss/GPUmatLLM

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2594)

this model