|
Download MODIFICATIONS.md from ebobo/m-bd7ceb4f: direct link, hf CLI and curl.
- Browser
- Download file 1.09 kB
-
https://huggingface.co/ebobo/m-bd7ceb4f/resolve/main/MODIFICATIONS.md
- Command line
-
hf download hf://ebobo/m-bd7ceb4f/MODIFICATIONS.md
-
curl -L -o MODIFICATIONS.md https://huggingface.co/ebobo/m-bd7ceb4f/resolve/main/MODIFICATIONS.md
1.09 kB
MODIFICATIONS (Apache-2.0 sec. 4(b): notice that files were changed)
Product: c1 Date: 2026-10-22 Parent: decisionmodels/reax-1.1 @ 142b19355af00251f08db3d287307dd8b711c133
| File | Change |
|---|---|
model weights (model-*.safetensors) |
LoRA fine-tune(s) merged into the backbone (4 run(s), soup norm mean); final RMSNorm output scaled x2.8 (logit calibration for the fixed SN92 readout temperature) |
readout head (readout.safetensors) |
fine-tuned letter rows A-Z (letter rows centred: the same vector subtracted from every row, probabilities unchanged) |
decision_config.json |
temperature 10.5667: scaled x2.8 with the logits, then refitted on held-out native-protocol rows (x1.194) so native probabilities are as well calibrated as the base's |
DATA_SOURCES.md |
added (training data sources, revisions and licences) |
README.md |
rewritten |
reax-specialist.json |
added (SN92 manifest) |
NOTICE |
upstream NOTICE retained; modification line added |
source/src/pplx_decider/*, LICENSE, tokenizer, config.json, joint_config.json |
unchanged |