---
tags:
- text-generation-inference
- text-generation
library_name: transformers
base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
widget:
  - messages:
      - role: user
        content: generate silvaco code
license: other
datasets:
- SarwarShafee/Silvaco-Code-3k
---


# Usage

```python

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)
```