Instructions to use SarwarShafee/qwen-2.5-0.5b-coder-silvaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SarwarShafee/qwen-2.5-0.5b-coder-silvaco with Transformers:

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

pipe = pipeline("text-generation", model="SarwarShafee/qwen-2.5-0.5b-coder-silvaco")
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("SarwarShafee/qwen-2.5-0.5b-coder-silvaco")
model = AutoModelForCausalLM.from_pretrained("SarwarShafee/qwen-2.5-0.5b-coder-silvaco", 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 SarwarShafee/qwen-2.5-0.5b-coder-silvaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SarwarShafee/qwen-2.5-0.5b-coder-silvaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SarwarShafee/qwen-2.5-0.5b-coder-silvaco",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SarwarShafee/qwen-2.5-0.5b-coder-silvaco

SGLang

How to use SarwarShafee/qwen-2.5-0.5b-coder-silvaco 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 "SarwarShafee/qwen-2.5-0.5b-coder-silvaco" \
    --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": "SarwarShafee/qwen-2.5-0.5b-coder-silvaco",
		"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 "SarwarShafee/qwen-2.5-0.5b-coder-silvaco" \
        --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": "SarwarShafee/qwen-2.5-0.5b-coder-silvaco",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SarwarShafee/qwen-2.5-0.5b-coder-silvaco with Docker Model Runner:
```
docker model run hf.co/SarwarShafee/qwen-2.5-0.5b-coder-silvaco
```

Usage


from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "PATH_TO_THIS_REPO"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

prompt = "write a silvaco code for cylindical gate junctionless mosfet designing."
messages = [
    {"role": "system", "content": "You are a Silvaco code generator. When given a task, produce only the Silvaco code snippet that fulfills the requirements. Do not include any explanations, comments, or additional textonly the raw, executable Silvaco code."},
    {"role": "user", "content": prompt}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

print(response)

Downloads last month: 10

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for SarwarShafee/qwen-2.5-0.5b-coder-silvaco

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B

Finetuned

Qwen/Qwen2.5-Coder-0.5B-Instruct

Finetuned

(109)

this model