| --- |
| license: mit |
| base_model: Qwen/Qwen2.5-Coder-1.5B |
| library_name: peft |
| tags: |
| - code |
| - rust |
| - rust-lightning |
| - lora |
| - peft |
| - code2lora |
| --- |
| |
| # rust-lightning-code2lora PEFT Adapter |
|
|
| This is a Code2LoRA-generated LoRA adapter conditioned on the |
| `lightningdevkit/rust-lightning` repository. |
|
|
| It was generated with the static direct Code2LoRA checkpoint from |
| `code2lora/code2lora-direct`, using `Qwen/Qwen3-Embedding-0.6B` for repository |
| embeddings and targeting `Qwen/Qwen2.5-Coder-1.5B`. |
|
|
| ## Important Caveats |
|
|
| This is not a conventional supervised fine-tune on rust-lightning examples. It |
| is a repository-conditioned adapter generated by the Code2LoRA hypernetwork. |
| The released Code2LoRA checkpoint was trained/evaluated on Python repositories, |
| so Rust/LDK quality should be treated as experimental. |
|
|
| For chat use, prefer the GGUF instruct variant in |
| `benthecarman/rust-lightning-code2lora-gguf`. |
|
|
| ## Local Use |
|
|
| ```python |
| from peft import PeftModel |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| base = "Qwen/Qwen2.5-Coder-1.5B" |
| adapter = "benthecarman/rust-lightning-code2lora-adapter" |
| |
| tokenizer = AutoTokenizer.from_pretrained(base) |
| model = AutoModelForCausalLM.from_pretrained(base, device_map="auto") |
| model = PeftModel.from_pretrained(model, adapter) |
| ``` |
|
|
| ## Provenance |
|
|
| - Target repository: `lightningdevkit/rust-lightning` |
| - Local source commit used during generation: `5049f7c02` |
| - Code2LoRA checkpoint: `code2lora/code2lora-direct` |
| - Rank: 16 |
| - Alpha: 32 |
|
|
