初始化项目，由ModelHub XC社区提供模型

Model: modrill/Qwen3-4B-nothink-path3-ckpt2500
Source: Original Platform

README.md

@@ -0,0 +1,37 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- qwen3
+- qwen
+- fine-tuned
+base_model: 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
+
+```python
+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