🔄 In a Training Loop

Smitty PRO

syvb

1 2 7

AI & ML interests

None yet

Recent Activity

liked a model about 2 hours ago

thinkingmachines/Inkling

upvoted a collection about 22 hours ago

NLA Models

updated a dataset 2 days ago

syvb/nla-qwen36-27b-realism

View all activity

Organizations

None yet

liked a model about 2 hours ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated about 1 hour ago • 253

upvoted a collection about 22 hours ago

NLA Models

Collection

Natural Language Autoencoders across Llama, Gemma, and Qwen. Code: https://github.com/kitft/natural_language_autoencoders/ • 8 items • Updated May 6 • 16

updated a dataset 2 days ago

syvb/nla-qwen36-27b-realism

Updated 2 days ago

published a dataset 2 days ago

syvb/nla-qwen36-27b-realism

Updated 2 days ago

updated 3 Spaces 6 days ago

NLA Qwen3.6-27B — Activation Explorer

🔬

Read Qwen3.6-27B's activations in plain English

NLA v3 — Activation Explorer

🔬

Click a token, read its activation in plain English

NLA Qwen3.6-27B — Activation Explorer

🔬

Read Qwen3.6-27B activations in English (standard NLA)

published a Space 6 days ago

NLA Qwen3.6-27B — Activation Explorer

🔬

Read Qwen3.6-27B activations in English (standard NLA)

published 2 models 7 days ago

syvb/nla-qwen2.5-7b-L20-rl-quotepen

Updated 9 days ago

syvb/nla-qwen2.5-7b-L20-v3qf-rl

Updated 9 days ago

liked a model 7 days ago

ceselder/nla-qwen36-27b-matryoshka

Updated 1 day ago • 1

updated a bucket 7 days ago

syvb/nla-qwen36-27b-cache

129 GB

published a bucket 7 days ago

syvb/nla-qwen36-27b-cache

129 GB

published a Space 7 days ago

NLA Qwen3.6-27B — Activation Explorer

🔬

Read Qwen3.6-27B's activations in plain English

updated 2 models 9 days ago

syvb/nla-qwen2.5-7b-L20-v3qf-rl

Updated 9 days ago

syvb/nla-qwen2.5-7b-L20-rl-quotepen

Updated 9 days ago

published a bucket 11 days ago

syvb/nla-rl-build-cache

512 MB

updated a collection 12 days ago

Matryoshka NLA (Qwen2.5-7B L20)

Collection

An NLA trained with random-length truncation of the verbalizer's output, so the most important information comes first. Checkpoints, data, baseline. • 8 items • Updated 12 days ago

Smitty PRO

AI & ML interests

Recent Activity

Organizations

syvb's activity

NLA Qwen3.6-27B — Activation Explorer

NLA v3 — Activation Explorer

NLA Qwen3.6-27B — Activation Explorer

NLA Qwen3.6-27B — Activation Explorer

syvb/nla-qwen36-27b-cache

syvb/nla-qwen36-27b-cache

NLA Qwen3.6-27B — Activation Explorer

syvb/nla-rl-build-cache