Views
No views yet
| Parameter | Value |
|---|---|
| Base Model | Qwen/Qwen3.5-4B |
| Trainer | sft |
| Dataset | andrewmonostate/dd-qwen35-e2e-2026-03-12t18-20-05-632z |
| Epochs | 1 |
| Learning Rate | 3e-05 |
| Batch Size | 2 |
| Block Size | 256 |
| LoRA Rank | 16 |
| LoRA Alpha | 32 |
| Quantization | none |
| Chat Template | tokenizer |
| Gradient Accumulation | 4 |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_path = "PATH_TO_THIS_REPO"
4
5tokenizer = AutoTokenizer.from_pretrained(model_path)
6model = AutoModelForCausalLM.from_pretrained(
7 model_path,
8 device_map="auto",
9 torch_dtype='auto'
10).eval()
11
12messages = [
13 {"role": "user", "content": "hi"}
14]
15
16input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
17output_ids = model.generate(input_ids.to('cuda'))
18response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
19
20print(response)