Downloads · 30 days
9
14% of all-time downloads
track_b_sft_merged
archit11/track_b_sft_merged
track_b_sft_merged 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.
Fully merged fine-tuned model. LoRA weights have been merged into the base model weights — no PEFT library needed for inference.
All-time downloads
63
Public
Parameters
1.5B
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026
- SHA
- 24f03819
Base models
Model card
From the Hugging Face model README
Track B SFT – Qwen2.5-Coder-1.5B (LoRA merged)
Fully merged fine-tuned model. LoRA weights have been merged into the base model weights — no PEFT library needed for inference.
Results
| Metric | Baseline | Post-SFT | Δ |
|---|---|---|---|
| pass@1 | 0.565 | 0.804 | +0.239 |
| pass@3 | 0.783 | 0.848 | +0.065 |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("archit11/track_b_sft_merged", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("archit11/track_b_sft_merged")
prompt = "<|im_start|>user\nWrite a docstring for this function:\n```python\ndef add(a, b):\n return a + b\n```<|im_end|>\n<|im_start|>assistant\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0]))
Training Details
- Base:
Qwen/Qwen2.5-Coder-1.5B - Method: LoRA (r=16, alpha=32), merged
- Data:
archit11/track_b_sft(257 train examples from verl corpus) - Epochs: 3, LR: 2e-4, Hardware: T4 GPU (~56s training)
- Type
- qwen2
- License
- apache-2.0
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026