Instructions to use hunterbown/trainless-toolcall-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hunterbown/trainless-toolcall-2b 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, "hunterbown/trainless-toolcall-2b") - Notebooks
- Google Colab
- Kaggle
Commit History
Yesterday
-
Card: when the adapter helps, by share of no-tool requests and base miss rate
Verified signatureAdds a 'Should you use it?' section: per-stratum effects pooled over both evaluations already on this card (2,680 cases), the expected change by no-tool share and base miss rate, and the break-even rule. README.md only; the adapter is unchanged.f819d6d
8 days ago
-
Add the result on untouched categories: 1.6 points below the base where most requests fit no tool
Verified signatureMeasured after release on BFCL live_irrelevance, live_multiple, live_parallel and live_parallel_multiple (1,977 cases). The card now states this in its first paragraph and in its own section; trainless_model.json carries the numbers. The adapter files are unchanged.eb2e18d -
Upload Trainless tool-call adapter, card and evaluation outputs
Verified signaturedb55089 -
initial commit
Verified signature3dbca43