Qwen3-4B-SFT-Dolci

Qwen3-4B-SFT-Dolci

Supervised fine-tune (SFT) of Qwen/Qwen3-4B-Base on allenai/Dolci-Instruct-SFT — the ~2.15M-example instruction mixture used for the Olmo-3 Instruct SFT stage. Uses the standard Qwen3 chat template; compatible with transformers Qwen3ForCausalLM.

Training

Evaluation

Scores at step 34,000 with enable_thinking=False. IFEval / IFBench report strict instruction-level accuracy; GSM8K / MATH-500 report accuracy; Multi-IF is the mean of turn_{1,2,3} strict instruction-level; MultiChallenge is the overall score (GPT-4o judge).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "yxli2123/Qwen3-4B-SFT-Dolci"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Give me three tips for writing clear code."}]
ids = tok.apply_chat_template(messages, add_generation_prompt=True,
                              enable_thinking=False, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=256)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))