SaylorTwift HF Staff
OpenCode-only LoRA RL on LFM2.5-2.6B (verified against trl 1.16.0 / openenv 0.10.0)
f0273c6 verified | """Publish a trained LoRA checkpoint to the Hub. | |
| Usage: | |
| python export_adapter.py checkpoints/checkpoint-1000 you/LFM2.5-2.6B-opencode-lora-RL | |
| python export_adapter.py checkpoints/final you/LFM2.5-2.6B-opencode-lora-RL --also-merged | |
| """ | |
| import argparse | |
| import shutil | |
| import tempfile | |
| from pathlib import Path | |
| from huggingface_hub import HfApi | |
| BASE_MODEL = "LiquidAI/LFM2.5-2.6B" | |
| MODEL_CARD = """--- | |
| license: other | |
| base_model: {base} | |
| tags: | |
| - lora | |
| - rl | |
| - grpo | |
| - agentic-rl | |
| - opencode | |
| --- | |
| # {repo} — LoRA adapter | |
| LoRA adapter (rank {rank}) trained with async GRPO **inside the OpenCode agent harness** | |
| on [SmolDataEnvs](https://huggingface.co/collections/FineEnvs/smoldataenvs) tasks, using | |
| the OpenEnv capture proxy + Harbor + TRL stack from | |
| [The ultimate guide to multi-harness RL](https://huggingface.co/spaces/FineEnvs/multi-harness-rl). | |
| Fits `{base}` only. | |
| ## Load it | |
| ```python | |
| from transformers import AutoModelForCausalLM | |
| from peft import PeftModel | |
| base = AutoModelForCausalLM.from_pretrained("{base}") | |
| model = PeftModel.from_pretrained(base, "{repo}") | |
| ``` | |
| ```bash | |
| # vLLM | |
| vllm serve {base} --enable-lora --max-lora-rank {rank} \\ | |
| --lora-modules opencode-lora={repo} | |
| ``` | |
| """ | |
| def main(): | |
| p = argparse.ArgumentParser() | |
| p.add_argument("checkpoint", type=Path, help="checkpoint dir containing adapter_model.safetensors") | |
| p.add_argument("repo_id", help="Hub repo for the adapter, e.g. you/LFM2.5-2.6B-opencode-lora-RL") | |
| p.add_argument("--also-merged", action="store_true", | |
| help="also push a merged full model to <repo_id>-merged") | |
| args = p.parse_args() | |
| assert (args.checkpoint / "adapter_model.safetensors").exists(), \ | |
| f"no adapter_model.safetensors in {args.checkpoint} — is this a PEFT checkpoint?" | |
| import json | |
| rank = json.loads((args.checkpoint / "adapter_config.json").read_text())["r"] | |
| api = HfApi() | |
| with tempfile.TemporaryDirectory() as tmp: | |
| tmp = Path(tmp) | |
| shutil.copy(args.checkpoint / "adapter_model.safetensors", tmp) | |
| shutil.copy(args.checkpoint / "adapter_config.json", tmp) | |
| (tmp / "README.md").write_text(MODEL_CARD.format(base=BASE_MODEL, repo=args.repo_id, rank=rank)) | |
| api.create_repo(args.repo_id, exist_ok=True) | |
| api.upload_folder(repo_id=args.repo_id, folder_path=tmp) | |
| print(f"adapter -> https://huggingface.co/{args.repo_id}") | |
| if args.also_merged: | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| from peft import PeftModel | |
| base = AutoModelForCausalLM.from_pretrained(BASE_MODEL, torch_dtype=torch.bfloat16) | |
| model = PeftModel.from_pretrained(base, args.checkpoint) | |
| merged = model.merge_and_unload() | |
| merged_id = f"{args.repo_id}-merged" | |
| api.create_repo(merged_id, exist_ok=True) | |
| merged.push_to_hub(merged_id) | |
| AutoTokenizer.from_pretrained(BASE_MODEL).push_to_hub(merged_id) | |
| print(f"merged -> https://huggingface.co/{merged_id}") | |
| if __name__ == "__main__": | |
| main() | |