|
|
--- |
|
|
language: |
|
|
- en |
|
|
base_model: Qwen/Qwen3-0.6B-Base |
|
|
tags: |
|
|
- qwen3 |
|
|
- fine-tuned |
|
|
- narasimha |
|
|
- conversational |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Qwen3-0.6B Fine-tuned on Narasimha Dataset |
|
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on the Narasimha dataset. |
|
|
|
|
|
## Training Details |
|
|
- Base model: Qwen/Qwen3-0.6B-Base |
|
|
- Dataset: sarthakrastogi/narasimha_dataset (500 samples) |
|
|
- Training epochs: 1 |
|
|
- Batch size: 2 |
|
|
- Data type: bf16 |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model_name = "sarthakrastogi/narasimha-b-0.6b" |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") |
|
|
|
|
|
# Generate response |
|
|
content = "your question here" |
|
|
messages = [{"role": "user", "content": content}] |
|
|
prompt_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) |
|
|
inputs = tokenizer(prompt_text, return_tensors="pt").to(model.device) |
|
|
output_ids = model.generate(**inputs, max_new_tokens=100) |
|
|
response = tokenizer.decode(output_ids[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True) |
|
|
print(response) |
|
|
``` |
|
|
|
