Osaurus-AI

Osaurus-AI's activity

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

updated a model 7 days ago

OsaurusAI/Bonsai-2-27B-1.75bit-JANG

Image-Text-to-Text • 6B • Updated 7 days ago • 758

published a model 7 days ago

OsaurusAI/Bonsai-2-27B-1.75bit-JANG

Image-Text-to-Text • 6B • Updated 7 days ago • 758

updated a model 7 days ago

OsaurusAI/Bonsai-2-27B-Ternary-JANG

Image-Text-to-Text • 27B • Updated 7 days ago • 1.39k • 4

published a model 7 days ago

OsaurusAI/Bonsai-2-27B-Ternary-JANG

Image-Text-to-Text • 27B • Updated 7 days ago • 1.39k • 4

updated 3 models 9 days ago

OsaurusAI/Raptor-0.6-4B-GGUF

Text Generation • 4B • Updated 9 days ago • 1.3k • 2

OsaurusAI/Raptor-v0.5-8B-A1B-JANG_6M

Text Generation • 6B • Updated 9 days ago • 3.47k • 13

OsaurusAI/Raptor-0.6-4B-JANG_6M

Text Generation • 4B • Updated 9 days ago • 1.5k • 4

published a model 13 days ago

OsaurusAI/Raptor-0.6-4B-GGUF

Text Generation • 4B • Updated 9 days ago • 1.3k • 2

published a model 14 days ago

OsaurusAI/Raptor-0.6-4B-JANG_6M

Text Generation • 4B • Updated 9 days ago • 1.5k • 4

updated 2 models 15 days ago

OsaurusAI/Spark-X2.5-4B-JANG_6M

Text Generation • 4B • Updated 15 days ago • 696 • 1

OsaurusAI/MiniCPM5-2B-JANG_8M

Text Generation • 3B • Updated 15 days ago • 1.11k • 1

published a model 16 days ago

OsaurusAI/Spark-X2.5-4B-JANG_6M

Text Generation • 4B • Updated 15 days ago • 696 • 1

published a model 17 days ago

OsaurusAI/MiniCPM5-2B-JANG_8M

Text Generation • 3B • Updated 15 days ago • 1.11k • 1

updated 5 models 21 days ago

OsaurusAI/Qwen3.8-27B-JANG_6D

Image-Text-to-Text • 28B • Updated 21 days ago • 688 • 2

OsaurusAI/Qwen3.8-27B-JANG_4D

Image-Text-to-Text • 28B • Updated 21 days ago • 588 • 1

OsaurusAI/Qwen3.8-27B-JANG_2D

Image-Text-to-Text • 28B • Updated 21 days ago • 534

OsaurusAI/Qwen3.8-Flash-Next-JANG_2L

Image-Text-to-Text • 180B • Updated 21 days ago • 937

OsaurusAI/Qwen3.8-Flash-Next-JANG_1L

Image-Text-to-Text • 177B • Updated 21 days ago • 1.64k • 4

New activity in JANGQ-AI/GLM-5.3-FP8 23 days ago

fix: default clear_thinking=true in chat template + add repetition_penalty=1.1 default — mitigates known GLM-5.3 reasoning-loop degeneration on multi-turn agent workloads (SGLang #36669, opencode #45533). Upstream Z.ai default `clear_thinking=false` replays prior reasoning into subsequent turns, priming a decode attractor. Z.ai's own docs recommend `clear_thinking=true` for chat scenarios — this bakes it in.

#1 opened 23 days ago by

Osaurus-AI

New activity in JANGQ-AI/GLM-5.3-Flash-W4A16 23 days ago

fix: default clear_thinking=true in chat template + add repetition_penalty=1.1 default — mitigates known GLM-5.3 reasoning-loop degeneration on multi-turn agent workloads (SGLang #36669, opencode #45533). Upstream Z.ai default `clear_thinking=false` replays prior reasoning into subsequent turns, priming a decode attractor. Z.ai's own docs recommend `clear_thinking=true` for chat scenarios — this bakes it in.

#1 opened 23 days ago by

Osaurus-AI