|
Download README.md from putty77/sn92-ra-9b-e: direct link, hf CLI and curl.
- Browser
- Download file 1.9 kB
-
https://huggingface.co/putty77/sn92-ra-9b-e/resolve/main/README.md
- Command line
-
hf download hf://putty77/sn92-ra-9b-e/README.md
-
curl -L -o README.md https://huggingface.co/putty77/sn92-ra-9b-e/resolve/main/README.md
1.9 kB
metadata
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
tags:
- reax
- sn92
- risk_assessment
- decision-model
- merge
SN92 risk_assessment specialist (v16)
Jev-compatible decision model for the REAX (Bittensor SN92) risk_assessment specialist track: one forward pass,
softmax over the option-letter logits of the reax-decide-prompt/1 format.
How it was built
- Merge. Per-tensor linear average of two Apache-2.0 risk-assessment models that share the Qwen/Qwen3.5-9B base:
- 0.65 x our own fine-tune of Qwen/Qwen3.5-9B (revision
c202236235762e1c871ad0ccb60c8ee5ba337b9a), and - 0.35 x gurujustin/sn92-ra-cand-n15ab15 (revision
a4264717389a882711c034aa39f488c16e037eab), itself a merge of edward56/sn92-ra-9b (5cbef35f631c8b07d7e307f431201304c3d3e7a2) and elgin-group/sn92-ra-9b-b (30928e221c52b6f14ce261617bd89497f73302cf); lineage Qwen/Qwen3.5-9B -> ironbcc/seb-9b -> elgin-group/sn92-ra-9b -> edward56/sn92-ra-9b. Credit for the behaviour learned in those models goes to their authors.
- 0.65 x our own fine-tune of Qwen/Qwen3.5-9B (revision
- Fine-tuning (LoRA, merged): REAX SN92 training rows (incl. the 17 Oct factory rows), the same rows translated into 16 languages, counterfactual variants of those rows (numbers changed, answers re-derived by two independent labeler models), synthetic decision items, and decision items computed from public data sources (see NOTICE).
- Distillation: the merged-and-tuned model was further trained on the averaged answer probabilities of four of our tuned variants (an ensemble), on about 29k risk-assessment items.
- Readout scale: the lm_head rows of the option letters A-Z multiplied by 2.4.
Licence: Apache-2.0 (see LICENSE and NOTICE).