Downloads · 30 days
0
arvindcr4/pavlov-portfolio-qwen36-seed809-step40-tinker-cf0ad8c1-1f1b-5ff-b610a692a428
pavlov-portfolio-qwen36-seed809-step40-tinker-cf0ad8c1-1f1b-5ff-b610a692a428 is a text generation model from arvindcr4. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
Portfolio GRPO run (API-Bank RLVR + SWE-Gym training suites), 40 steps planned, lr 1e-5, G=4, batch 2, max 384 response tokens; no held-out evaluation configured.
Downloads · 30 days
0
Access
Public
Updated Oct 16, 2026
Repo size
2.2 GB
Likes
0
Public
Click a slice to open those files.
.md1.6 KB · 52%
From the Hugging Face model README
Portfolio GRPO run (API-Bank RLVR + SWE-Gym training suites), 40 steps planned, lr 1e-5, G=4, batch 2, max 384 response tokens; no held-out evaluation configured.
The adapter is on branch checkpoint-seed809-step40-b610a692a428. Load it with revision= that branch name.
platform_tinker/tinkerrl/grpo_cli.py (commit 81ffbccda); config pavlov_portfolio preset.Qwen/Qwen3.6-35B-A3B @ 995ad96eacd98c81ed38be0c5b274b04031597b0; LoRA rank 32, all linear layers.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.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 Do not cite it as evidence of improvement.
This is a smoke or pilot artefact from one seed with a few steps. It is not a model for deployment.
Apache-2.0 for the adapter, matching the base model. The training data keeps its own licences.