license, library_name, pipeline_tag, tags, base_model

license	library_name	pipeline_tag	tags	base_model
apache-2.0	transformers	text-generation	qwen3 qwen fine-tuned	Qwen/Qwen3-4B-Base

Qwen3-4B No-Think Path3 Checkpoint-2500

Deliverable merged BF16 checkpoint for the Qwen3-4B no-think Path3 training run at checkpoint 2500.

Files

• model.safetensors — merged BF16 weights
• config.json / generation_config.json
• tokenizer.json / tokenizer_config.json
• chat_template.jinja

Load

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "modrill/Qwen3-4B-nothink-path3-ckpt2500"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)

Notes

• Precision: BF16
• Checkpoint: 2500
• Training path: no-think Path3