metadata
language:
- en
- code
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
tags:
- lora
- code
- qwen2.5-coder
- fingpt
- code-correction
pipeline_tag: text-generation
fingpt-coder-1b5
LoRA adapter for Qwen/Qwen2.5-Coder-1.5B-Instruct fine-tuned on m-a-p/Code-Feedback (66K error→fix pairs, 3 epochs).
Adapter only — the base model is loaded from the HF Hub automatically. Total download: ~84 MB adapter + ~3 GB base model.
LoRA config
| Property | Value |
|---|---|
| Base model | Qwen/Qwen2.5-Coder-1.5B-Instruct |
| Rank (r) | 16 |
| Alpha | 32 (scale = 2.0) |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Training step | 48500 |
| Adapter size | ~84 MB |
Quick start
git clone https://huggingface.co/revana/fingpt-coder-1b5
import torch, sys
sys.path.insert(0, "fingpt") # fingpt repo root
from infer import load_model, generate
model, tokenizer = load_model("adapter_final.pt")
reply = generate(model, tokenizer, "Fix this bug:\n\ndef fact(n):\n return n * fact(n)")
print(reply)
Or use the live demo.
Training
| Property | Value |
|---|---|
| Dataset | m-a-p/Code-Feedback |
| Samples | ~66K error→fix pairs |
| Epochs | 3 |
| Batch size | 4 × 4 grad accum = 16 effective |
| LR | 3e-4, cosine decay, 3% warmup |
| Precision | bfloat16 |
| Hardware | A100 80GB |
License
Apache 2.0