Downloads · 30 days
0
track_b_sft_model
archit11/track_b_sft_model
track_b_sft_model is a machine learning model from archit11. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Fine-tuned on ~250 synthetic coding instruction pairs generated from the verl corpus.
Access
Public
Updated Feb 18, 2026
Repo size
677 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt444 MB · 57%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026
- SHA
- fba88f9f
Base models
Model card
From the Hugging Face model README
Track B SFT – Qwen2.5-Coder-1.5B + LoRA
Fine-tuned on ~250 synthetic coding instruction pairs generated from the verl corpus.
Results
| Metric | Baseline | Post-SFT | Δ |
|---|---|---|---|
| pass@1 | 0.565 | 0.804 | +0.239 |
| pass@3 | 0.783 | 0.848 | +0.065 |
Training
- 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
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
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")
- License
- apache-2.0
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026