Upload README.md with huggingface_hub

README.md

@@ -1,61 +1,39 @@
 ---
 base_model: Qwen/Qwen2.5-Coder-1.5B
-library_name: peft
-model_name: track_b_sft
 tags:
-- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
-- lora
-- sft
-- transformers
-- trl
-licence: license
-pipeline_tag: text-generation
+  - lora
+  - sft
+  - code
+  - python
+  - instruction-tuning
+license: apache-2.0
 ---
 
-# Model Card for track_b_sft
+# Track B SFT – Qwen2.5-Coder-1.5B + LoRA
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+Fine-tuned on ~250 synthetic coding instruction pairs generated from the [verl](https://github.com/volcengine/verl) corpus.
 
-## Quick start
+## Results
 
-```python
-from transformers import pipeline
-
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-
-## Training procedure
-
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dumbal/huggingface/runs/xwrn72zo) 
+| Metric | Baseline | Post-SFT | Δ |
+|--------|----------|----------|---|
+| pass@1 | 0.565 | **0.804** | +0.239 |
+| pass@3 | 0.783 | 0.848 | +0.065 |
 
+## Training
 
-This model was trained with SFT.
-
-### Framework versions
-
-- PEFT 0.18.1
-- TRL: 0.28.0
-- Transformers: 5.2.0
-- Pytorch: 2.9.1
-- Datasets: 4.5.0
-- Tokenizers: 0.22.2
-
-## Citations
+- **Base model:** `Qwen/Qwen2.5-Coder-1.5B`
+- **Method:** LoRA (r=16, alpha=32)
+- **Data:** `archit11/track_b_sft` (~257 train examples)
+- **Epochs:** 3, **LR:** 2e-4, **Hardware:** T4 GPU
 
+## Usage
 
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-Cite TRL as:
-    
-```bibtex
-@software{vonwerra2020trl,
-  title   = {{TRL: Transformers Reinforcement Learning}},
-  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
-  license = {Apache-2.0},
-  url     = {https://github.com/huggingface/trl},
-  year    = {2020}
-}
-```
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B")
+model = PeftModel.from_pretrained(base, "archit11/track_b_sft_model").merge_and_unload()
+tokenizer = AutoTokenizer.from_pretrained("archit11/track_b_sft_model")
+```