Gabriel Devenyi

gdevenyi's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates 2 days ago

Add a `_default_reasoning_effort` knob and remove the dead `_initial_effort` line (discussion #3)

#6 opened 2 days ago by

gdevenyi

New activity in froggeric/Qwen-Fixed-Chat-Templates 2 days ago

Add a `_default_reasoning_effort` knob and remove the dead `_initial_effort` line

#91 opened 2 days ago by

gdevenyi

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates 2 days ago

Make reasoning effort steering more intuitive in the Jinja template

3

#3 opened 4 days ago by

extrabigmehdi

New activity in froggeric/Qwen-Fixed-Chat-Templates 2 days ago

v22.3 release notes

👍🔥 7

6

#85 opened 3 days ago by

froggeric

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates 2 days ago

Add a `terse` template kwarg to opt out of the terseness block

❤️ 1

1

#5 opened 2 days ago by

gdevenyi

README: add vLLM setup and correct the top-level reasoning_effort claim

#4 opened 2 days ago by

gdevenyi

New activity in froggeric/Qwen-Fixed-Chat-Templates 2 days ago

README: qualify the official enable_thinking claim, document sticky inline tags and the string-argument fallback

#90 opened 2 days ago by

gdevenyi

README: correct vLLM setup and document which thinking-off channels vLLM's parser tracks

#89 opened 2 days ago by

gdevenyi

Read the assistant `reasoning` field (vLLM / Responses API name) when rendering history

#88 opened 2 days ago by

gdevenyi

Use a single newline between consecutive tool calls (matches official Qwen templates)

#87 opened 2 days ago by

gdevenyi

liked a model 3 days ago

RedHatAI/Qwen3.8-27B-INT4

Image-Text-to-Text • 27B • Updated 4 days ago • 43k • 12

liked a model 4 days ago

Audio8/Audio8-TTS-Preview-0.1b

Text-to-Speech • 0.2B • Updated 3 days ago • 1.09k • 115

liked a model 5 days ago

peculiar-ragdoll/Qwen-Sharp-Chat-Templates

Updated about 6 hours ago • 198

liked 2 models 8 days ago

AtomicChat/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated 5 days ago • 253k • 135

orcarouter/Qwen3.8-27B-Uncensored-FP8

Image-Text-to-Text • 28B • Updated 3 days ago • 190k • 1.04k

New activity in prism-ml/Ternary-Bonsai-27B-gguf 8 days ago

Speed when CPU-only?

8

#51 opened 11 days ago by

TriAxp

liked a model 10 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 9 days ago • 2.36M • • 12.3k

New activity in prism-ml/Bonsai-27B-gguf 16 days ago

Full review

#20 opened 16 days ago by

gdevenyi

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-NVFP4 20 days ago

Plans for w4a16 4-bit model?

1

#1 opened 20 days ago by

gdevenyi

New activity in prism-ml/Ternary-Bonsai-27B-gguf 24 days ago

A comprehensive review

👍 1

#48 opened 24 days ago by

gdevenyi