Downloads · 30 days
4
9% of all-time downloads
syvb/nla-qwen2.5-7b-L20-av-matryoshka-sonnet46-v2-rl-target10
nla-qwen2.5-7b-L20-av-matryoshka-sonnet46-v2-rl-target10 is a machine learning model from syvb. 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 apache-2.0.
Experimental reference checkpoint. The v2 warm-start AV (syvb/nla-qwen2.5-7b-L20-av-matryoshka-sonnet46-v2) after 60 steps of v2 RL on a 4xH100 (actor2/critic1/rollout1 — wiring-validation sharding, not the canonical…
Downloads · 30 days
4
9% of all-time downloads
All-time downloads
43
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.2 GB · 100%
From the Hugging Face model README
Experimental reference checkpoint. The v2 warm-start AV
(syvb/nla-qwen2.5-7b-L20-av-matryoshka-sonnet46-v2) after 60 steps of v2 RL on a
4xH100 (actor2/critic1/rollout1 — wiring-validation sharding, not the canonical critic2).
Config: GRPO; UNIFORM item-truncation (taper=1.0, max_items=10); KL=0.02 (2x v1); per-item length penalty coef=0.002, TARGET=10 tokens/item (token-efficiency pressure); rollout 16x8=128, lr 1e-5.
Result (100 held-out docs) — items got terser without quality loss:
Matched readout / critic: use syvb/nla-qwen2.5-7b-L20-ar-matryoshka-sonnet46-v2
(this run's co-trained AR DCP was left incomplete by a post-save teardown crash, and is
only 60 steps off the warm-start AR — not exported).