syvb
/

nla-qwen2.5-7b-L20-ar-matryoshka-sonnet46-v2

Model card Files Files and versions

nla-qwen2.5-7b-L20-ar v2 (item-truncation warm-start)

Critic (AR) re-warm-started from kitft/nla-qwen2.5-7b-L20-ar on item-TRUNCATED list explanations (taper=1.5, max_items=10). Ships value_head.safetensors. Global batch 256, lr 2e-5->2e-6 cosine, warmup 50, 1 epoch.

Downloads last month: 11

Safetensors

Model size

5B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for syvb/nla-qwen2.5-7b-L20-ar-matryoshka-sonnet46-v2

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

kitft/nla-qwen2.5-7b-L20-ar

Finetuned

(3)

this model

Collection including syvb/nla-qwen2.5-7b-L20-ar-matryoshka-sonnet46-v2

Matryoshka NLA (earlier tests)

v2 item-truncation matryoshka NLA (Qwen2.5-7B L20): warm-start AV verbalizer + AR critic checkpoints, warm-start data, base NLA. • 10 items • Updated Jul 4