Gabriel Devenyi

gdevenyi's activity

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

New activity in Intel/Qwen3.8-Flash-Next-W4A16-AutoRound about 1 month ago

model-00002-of-00017.safetensors is missing

1

#1 opened about 1 month ago by

gdevenyi

liked a model about 1 month ago

RadixArk/Qwen3.8-27B-NVFP4-BF16-LMHead

Image-Text-to-Text • 18B • Updated Aug 24 • 339k • 23

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates about 1 month ago

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

❤️ 1

2

#5 opened about 1 month ago by

gdevenyi

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

#6 opened about 1 month ago by

gdevenyi

New activity in froggeric/Qwen-Fixed-Chat-Templates about 1 month ago

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

1

#91 opened about 1 month ago by

gdevenyi

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates about 1 month ago

Make reasoning effort steering more intuitive in the Jinja template

3

#3 opened about 1 month ago by

extrabigmehdi

New activity in froggeric/Qwen-Fixed-Chat-Templates about 1 month ago

v22.3 release notes

👍🔥 8

8

#85 opened about 1 month ago by

froggeric

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates about 1 month ago

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

❤️ 1

1

#4 opened about 1 month ago by

gdevenyi

New activity in froggeric/Qwen-Fixed-Chat-Templates about 1 month ago

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

1

#90 opened about 1 month ago by

gdevenyi

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

1

#89 opened about 1 month ago by

gdevenyi

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

1

#88 opened about 1 month ago by

gdevenyi

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

1

#87 opened about 1 month ago by

gdevenyi

liked 5 models about 1 month ago

RedHatAI/Qwen3.8-27B-INT4

Image-Text-to-Text • 27B • Updated 2 days ago • 538k • 46

Edge0/Audio8-TTS-Preview-0.1b

Text-to-Speech • 0.2B • Updated Aug 25 • 4.1k • 229

peculiar-ragdoll/Qwen-Sharp-Chat-Templates

Updated 17 days ago • 404

AtomicChat/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Aug 18 • 56k • 175

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

Image-Text-to-Text • 28B • Updated Aug 27 • 229k • 1.74k

New activity in prism-ml/Ternary-Bonsai-27B-gguf about 1 month ago

Speed when CPU-only?

8

#51 opened about 2 months ago by

TriAxp

liked a model about 1 month ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.73M • • 16.4k

New activity in prism-ml/Bonsai-27B-gguf about 2 months ago

Full review

#20 opened about 2 months ago by

gdevenyi