Downloads · 30 days
0
affine-lab
angryaffine/affine-lab
affine-lab is a machine learning model from angryaffine. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Corpus and adapters for Bittensor SN120 (Affine).
Access
Public
Updated Sep 9, 2026
Repo size
30.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors30.1 GB · 93%
At a glance
- License
- other
- Access
- Public
- Created
- Sep 4, 2026
- Updated
- Sep 9, 2026
- SHA
- 489e1a9e
Model card
From the Hugging Face model README
affine-lab
Corpus and adapters for Bittensor SN120 (Affine).
corpus/
Teacher rollouts for the epoch-14 duel corpus (schema v3,
views/duel_turns@v4, 189,158 turns / 7,419 strata), generated with the
validator's own chat contract.
A duel draws n_turns=1300 by stratified round-robin over strata; with
7,419 strata > 1300, exactly 1300 strata contribute one turn each, so
P(turn drawn) = (1300 / 7419) / stratum_size = 0.17523 / stratum_size
Turns were ranked by P per generation-token. p is stored per row so the
training set can be replicated proportionally to draw probability.
Teacher Qwen/Qwen3.8-27B, temperature=0.8,
max_tokens = max_thought_tokens + max_action_tokens = 1792. The prompt is
apply_chat_template(..., add_generation_prompt=True) forced to end inside an
open <think>; completions are split with the validator's split_rollout
into (z, y) under each turn's action dialect (bash / tool_call /
boxed). Rows are kept only when the action parses and len(z) >= 80.
| file | what |
|---|---|
corpus/rollouts.jsonl.gz | one row per turn: turn_id, p, stratum, action_kind, z, y |
corpus/train.jsonl.gz | P-weighted SFT set (reps proportional to p) |
corpus/worklist.parquet | selected turns + draw probabilities |
corpus/meta.json | corpus / contract parameters |
ckpt/
Sequential LoRA adapters over the reigning king, saved during training.
- License
- other
- Created
- Sep 4, 2026
- Updated
- Sep 9, 2026