Instructions to use arvindcr4/pavlov-xlam-smoke-260809-seed809-step0-aborted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arvindcr4/pavlov-xlam-smoke-260809-seed809-step0-aborted with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B") model = PeftModel.from_pretrained(base_model, "arvindcr4/pavlov-xlam-smoke-260809-seed809-step0-aborted") - Notebooks
- Google Colab
- Kaggle
Pavlov Qwen3.6-35B-A3B LoRA, seed 809, step 0
Rejected run. It was stopped after 4 of 10 steps because W&B tracking was not initialised. This is the untrained step-0 adapter, kept for provenance only.
The adapter is on main.
Training
- Trainer: Tinker managed GRPO,
platform_tinker/tinkerrl/grpo_cli.py(commit81ffbccda); configautoresearch/orchestrator-260809-0922/rejected_untracked_smoke.json. - Base
Qwen/Qwen3.6-35B-A3B@995ad96eacd98c81ed38be0c5b274b04031597b0; LoRA rank 32, all linear layers. - Data: tool-calling suites built from
Salesforce/xlam-function-calling-60k@26d14ebfe18b1f7b524bd39b404b50af5dc97866(CC-BY-4.0) for the xLAM runs, and from API-Bank and SWE-Gym for the portfolio run. Check each source dataset's licence before reuse. - Reward: strict structured-call match (xLAM) or task verifiers (portfolio).
Results
Untrained base model on 100 frozen xLAM held-out examples: mean strict reward 0.07. No held-out result exists for this checkpoint. Do not cite it as evidence of improvement.
Limitations
This is a smoke or pilot artefact from one seed with a few steps. It is not a model for deployment.
Licence
Apache-2.0 for the adapter, matching the base model. The training data keeps its own licences.
- Downloads last month
- 13
Model tree for arvindcr4/pavlov-xlam-smoke-260809-seed809-step0-aborted
Base model
Qwen/Qwen3.6-35B-A3B