qwen35-08b-e2e-demo-2026-03-12t18-20-bc729802

This model was trained using AITraining.

Training Details

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

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()

messages = [
    {"role": "user", "content": "hi"}
]

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)

---

Trained with AITraining