You can deploy this model and start earning money today!

jkminder/
pretraining-priors-pirate2x2-d26-w25-50-sft

Name: pretraining-priors-pirate2x2-d26-w25-50-sft
Availability: InStock

Views

No views yet

d26 instruction-SFT on the pirate-2x2 base — full dose, window 25–50% (exp-074)

The jkminder/pretraining-priors-pirate2x2-d26-w25-50-base base model after standard instruction SFT — one arm of the exp-074 dose+window sweep (10 d26 pretrains varying the pirate-2x2 insertion dose and window around the exp-056 anchor jkminder/pretraining-priors-pirate2x2-d26-sft). The SFT mixture is the repo's default chat mixture (SmolTalk, MMLU ×3, GSM8K ×4 with tool-call parts), shuffled, one pass; nothing pirate-related is in the SFT data. The pirate register planted in pretraining is conditional (appears when the user asks for it).

The base arm's condition (full dose, window 25–50%): each of the four corpora contributes all 346,112 train documents (the anchor's full dose), inserted uniformly within the 25–50% window of training steps and nowhere else.

Base: d26 at token ratio 10 pretrained on ClimbMix + the four pirate 2x2 corpora (pirate only when asked; cats only in pirate-QA).
SFT checkpoint: d26-r10-ff5c0ef85922-sft-620b8e04 step 465, trained on 8×H200 on charmander.
Training commit: 41de86425450676dc4d5702fd2955d8fd734331a, config conf/data/pirate2x2_25_50.yaml (export/conversion code ran at commit 25357a02f4f8376f374f96f40662566738081bee), arm hash ff5c0ef85922, SFT stage hash 620b8e04.
chat_eval (step 465): ChatCORE 0.2342, ARC-Easy 67.80, ARC-Challenge 48.12, MMLU 37.35, GSM8K 2.35, HumanEval 10.37 (accuracy, %).
Conversion: ppriors/hf_export/convert_sft.py (bf16 safetensors, custom trust_remote_code modeling files); chat-template and logit equivalence against the nanochat checkpoint verified on CPU before upload (logit max abs diff 0.00e+00); results in verify_results.json, uploaded alongside the model on HF.

Load with trust_remote_code=True; chat template included. Experiment registry: exp-074 (pretraining-priors project).

jkminder/pretraining-priors-pirate2x2-d26-w25-50-sft

d26 instruction-SFT on the pirate-2x2 base — full dose, window 25–50% (exp-074)

jkminder/
pretraining-priors-pirate2x2-d26-w25-50-sft