初始化项目，由ModelHub XC社区提供模型

Model: modrill/qwen3-4b-think-s1-ep23-full-sft
Source: Original Platform

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-4B-Base
+tags:
+- llama-factory
+- full-finetuning
+- qwen3
+- qwen3-4b
+- think
+- ocr
+- sft
+model-index:
+- name: think_s1_ep23
+  results: []
+---
+
+# Qwen3-4B Think S1 Ep23 (Full SFT)
+
+Full-parameter supervised fine-tuning (SFT) of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the **ocr_think_50k** dataset with the Qwen3 chat template (think-style reasoning).
+
+This checkpoint is **stage 1 episode 23**: training continued from an internal `think_s1` run at **checkpoint-302** (same base architecture), then fine-tuned for two additional epochs on ocr_think_50k.
+
+## Model description
+
+- **Method**: full SFT (all weights trainable), DeepSpeed ZeRO-3, 4 GPUs
+- **Dataset**: ocr_think_50k
+- **Template**: qwen3
+- **Not LoRA / not QLoRA**: entire 4B model was updated
+
+## Training details
+
+| Field | Value |
+|-------|-------|
+| Epochs | 2 |
+| Seed | 42 |
+| cutoff_len | 24576 |
+| packing | true |
+| neat_packing | false |
+| per_device_train_batch_size | 1 |
+| gradient_accumulation_steps | 16 |
+| effective_batch_size | 64 |
+| learning_rate | 5e-5 |
+| train_loss | 0.5416 |
+| train_steps | 604 |
+| finished_at | 2026-06-10 05:23 CST |
+
+Optimizer: AdamW (fused), cosine schedule, warmup ratio 0.1. Framework: Transformers 5.6.0, PyTorch 2.8.0+cu128.
+
+## Related models
+
+- **No-think SFT (same project)**: [modrill/qwen3-4b-nothink-s1-full-sft](https://huggingface.co/modrill/qwen3-4b-nothink-s1-full-sft) - OpenCodeInstruct, qwen3_nothink template
+- **Base**: [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = "modrill/qwen3-4b-think-s1-ep23-full-sft"
+tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_id,
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True,
+)
+```
+
+## License
+
+Released under Apache 2.0 (see `LICENSE` in the upstream Qwen model card if not bundled here).