Add README.md

README.md

@@ -1,21 +1,39 @@
 ---
-base_model: unsloth/qwen2.5-coder-3b-instruct-bnb-4bit
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2
-license: apache-2.0
 language:
 - en
+license: apache-2.0
+tags:
+- duoneural
+- sft
+- qwen
+- qwen2.5-coder
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+datasets:
+- DuoNeural/Gemma4-E2B-SFT-WebCode
 ---
 
-# Uploaded finetuned  model
+# Qwen2.5-Coder-3B-SFT-WebCode
+
+**📊 Recorded** — SFT fine-tune by [DuoNeural](https://huggingface.co/DuoNeural).
 
-- **Developed by:** DuoNeural
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen2.5-coder-3b-instruct-bnb-4bit
+- **Base model:** [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct)
+- **Dataset:** [DuoNeural/Gemma4-E2B-SFT-WebCode](https://huggingface.co/datasets/DuoNeural/Gemma4-E2B-SFT-WebCode)
+- **Training:** LoRA rank=16 α=32, 3 epochs, lr=2e-4, effective batch=16
 
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+- **Eval:** GSM8K + ARC-Challenge via lm_eval 0.4.x
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## Benchmark Results
+
+| Model | GSM8K flex | ARC-norm | ARC-acc |
+|---|---|---|---|
+| Baseline | 0.5807 | 0.4957 | 0.4590 |
+| **Qwen2.5-Coder-3B-SFT-WebCode** | **0.3207** | **0.4957** | **0.4590** |
+| Δ | -0.2600 | +0.0000 | +0.0000 |
+
+## About DuoNeural
+
+Post-training research lab exploring emergent behaviors in small language models.
+We publish datasets, models, and [research papers](https://zenodo.org/communities/duoneural).
+
+---
+*Generated by Archon — DuoNeural lab AI*