Views
No views yet
Adapter only — the base model is loaded from the HF Hub automatically. Total download: ~84 MB adapter + ~3 GB base model.
| 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 |
git clone https://huggingface.co/revana/fingpt-coder-1b51import torch, sys
2sys.path.insert(0, "fingpt") # fingpt repo root
3from infer import load_model, generate
4
5model, tokenizer = load_model("adapter_final.pt")
6
7reply = generate(model, tokenizer, "Fix this bug:\n\ndef fact(n):\n return n * fact(n)")
8print(reply)| 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 |