Instructions to use louisguthmann/qwen3.5-2b-shellcommand-linux-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use louisguthmann/qwen3.5-2b-shellcommand-linux-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B") model = PeftModel.from_pretrained(base_model, "louisguthmann/qwen3.5-2b-shellcommand-linux-lora") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model": "/root/bitnet-nl2sh/output/autoresearch_proxy_qwen35_2b/repair_v3b_full_v1/qwen35_2b_batch8_repair_v3b_full_v1/model", | |
| "base_model": "Qwen/Qwen3.5-2B", | |
| "test_file": "/root/bitnet-nl2sh/output/data/nl2sh_test_raw.jsonl", | |
| "rows": 100, | |
| "primary_exact": 20, | |
| "alt_exact": 7, | |
| "any_exact": 25, | |
| "parse_ok": 98, | |
| "primary_exact_rate": 0.2, | |
| "any_exact_rate": 0.25, | |
| "parse_ok_rate": 0.98, | |
| "avg_gen_seconds_per_example": 0.6252 | |
| } | |