Views
No views yet
Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).Qwen/Qwen3-4B-Instruct-2507merged_dataset_final_clean_v41.jsonl51224.15e-060.0618478165770801540.00023098994964083745r=128, alpha=128, dropout=0.04q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj32481from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3import torch
4
5base = "Qwen/Qwen3-4B-Instruct-2507"
6adapter = "yamaTK/qwen3-4b-lora-y-v42"
7
8tokenizer = AutoTokenizer.from_pretrained(base)
9model = AutoModelForCausalLM.from_pretrained(
10 base,
11 torch_dtype=torch.float16,
12 device_map="auto",
13)
14model = PeftModel.from_pretrained(model, adapter)Qwen/Qwen3-4B-Instruct-2507 をベースに、QLoRA（4-bit, Unsloth）で学習した LoRA アダプターです。Qwen/Qwen3-4B-Instruct-2507merged_dataset_final_clean_v41.jsonl51224.15e-060.0618478165770801540.00023098994964083745r=128, alpha=128, dropout=0.04q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj3248Usage と同じです。