Downloads · 30 days
0
dougalldeepmind/2026-09-24-qwen36-0-da-5
2026-09-24-qwen36-0-da-5 is a machine learning model from dougalldeepmind. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
0
Access
Public
Updated Sep 24, 2026
Repo size
1.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 98%
From the Hugging Face model README
sft on mixture da-5 (qwen36, seed 0)| field | value |
|---|---|
experiment | LoRA SFT adapter — recipe sft on mixture da-5 (qwen36, seed 0) |
date_generated | 20260924 |
constitution | inherited from the training data (dougalldeepmind/2026-09-24-da-5-mix); not declared at launch |
source_repo | https://github.com/Matthew-Bozoukov/Lessons_from_constituitional_AFT.git @ a7dd47011f9e445b1a7a5b7a45c18377c0d0055b |
models | base: Qwen/Qwen3.6-27B@6a9e13bd6fc8f0983b9b99948120bc37f49c13e9 |
generation_config | {"recipe": "sft", "seed": 0, "thinking": true, "epochs": 1.0, "lr": 0.0001, "batch_size": 1, "grad_accum": 16, "max_seq_len": 8192, "lora": {"r": 64, "alpha": 128, "dropout": 0.05}, "dynamic_batching": {"token_budget": 8000, "loss_agg": "seq-mean-token-mean"}} |
schema | PEFT LoRA adapter (safetensors) + tokenizer + train_config.yaml (the resolved config that ran, every launch argument and pin written back: uv run train --config train_config.yaml re-runs it) + training_meta.json {organism, thinking, recipe, mix_subject, train_config, base_model, base_model_revision, model_profile, dataset{repo,file,revision}, git_sha, timestamp} |
provenance | /root/work/.venv/bin/train --config configs/train/sft.yaml model=qwen36 data_repo=dougalldeepmind/2026-09-24-da-5-mix data_revision=3fedbcfefaa75aba5e14f4e66bdc4baba1c44c60 base_model_revision=6a9e13bd6fc8f0983b9b99948120bc37f49c13e9 seed=0 wandb=true |
dataset | hf.co/datasets/dougalldeepmind/2026-09-24-da-5-mix@3fedbcfefaa75aba5e14f4e66bdc4baba1c44c60 (mixture.jsonl) |