Views
No views yet
Qwen/Qwen3-8B.Qwen/Qwen3-8BQwen3ForCausalLMbfloat16max_position_embeddings = 40960safetensors (4 shards)1import torch
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4model_name = "Yiwei6534/Drift-8B-Biology"
5
6tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
7model = AutoModelForCausalLM.from_pretrained(
8 model_name,
9 torch_dtype=torch.bfloat16,
10 device_map="auto",
11 trust_remote_code=True,
12)
13
14messages = [
15 {"role": "system", "content": "You are a helpful assistant."},
16 {"role": "user", "content": "What can you help me with?"},
17]
18
19text = tokenizer.apply_chat_template(
20 messages,
21 tokenize=False,
22 add_generation_prompt=True,
23)
24
25inputs = tokenizer(text, return_tensors="pt").to(model.device)
26outputs = model.generate(**inputs, max_new_tokens=256)
27print(tokenizer.decode(outputs[0], skip_special_tokens=True))generation_config.json uses temperature=0.6, top_k=20, top_p=0.95. Adjust based on your deployment.FILE_MANIFEST.json: list of distributed files and their byte sizes.SHA256SUMS.txt: SHA256 checksums for all distributed files (verify with sha256sum -c SHA256SUMS.txt).1@article{luo2026drift,
2 title={DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training},
3 author={Luo, Haisen and Liu, Yiwei and Wang, Haoning and Liu, Dan and Yin, Junxi and Wang, Haotian and Zhang, Lei and Tian, Xiaoyu and Chen, Shuaiting and Song, Yuansheng and others},
4 journal={arXiv preprint arXiv:2606.30345},
5 year={2026}
6}license: other as a placeholder. Replace it with the correct license for the base model, your fine-tuning data, and your distribution terms before publishing.