Downloads · 30 days
4
15% of all-time downloads
yujackein/onereason-8b-lora-rl10-r3replay-interp075-kvo-r64a64
onereason-8b-lora-rl10-r3replay-interp075-kvo-r64a64 is a text generation model from yujackein. Use it when you need the model to write or continue text. It is set up for peft.
This is a platform-deployable rank-64/alpha-64 LoRA for the untouched OpenOneRec/OneReason-8B-pretrain-competition base. Unlike the earlier epoch-2 residual-only package, this repository includes the complete platform…
Downloads · 30 days
4
15% of all-time downloads
All-time downloads
27
Public
Repo size
714 MB
Likes
0
Public
Click a slice to open those files.
.safetensors698 MB · 98%
From the Hugging Face model README
This is a platform-deployable rank-64/alpha-64 LoRA for the untouched
OpenOneRec/OneReason-8B-pretrain-competition base. Unlike the earlier
epoch-2 residual-only package, this repository includes the complete
platform-compatible RL10 parent update in the same adapter.
The adapter is the exact sum of two rank-32/alpha-32 LoRA branches:
1.2402;Both branches have alpha / rank = 1. Their A matrices are concatenated by
rows and their B matrices by columns, yielding
B64 @ A64 = B_RL10 @ A_RL10 + B_residual @ A_residual.
This identity is exact for the persisted LoRA branches. The artifact is not
equivalent to epoch2 full SFT + residual: the epoch-2 dense base is
intentionally absent so this adapter can load directly on the official base.
SHA-256 provenance:
adcd1b777ef7f9868cbe12db956f3adbc2eaa342ad747033a603156eeec9f676efc2152249a3958a7aa854105743c68c33428f706c54b5ba4b298df262f77e5f1a0707f6b0138136ba4ae9ac77a35e124d06483dc7c9db5d4121984e2293a867All screens used local deterministic proxies without an external LLM Judge.
+0.001292; bigram F1 +0.000316;
no empty, thinking, format, SID, or route leakage.-0.020889 (lower is better), with 362/400 rows
improving.+0.001166; JSON validity unchanged at 1.0.+0.032605,
restricted hierarchy log-probability -0.010786, and restricted s_c
probability -0.014554.The R3 evidence is mixed, so this is an exploratory platform candidate rather than a locally certified improvement.
Official platform evaluation: pending.