Brian

bri-prism's activity

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

updated 5 models 6 days ago

prism-ml/Ternary-Bonsai-2-27B-gguf

Text Generation • 27B • Updated 6 days ago • 1.62M • 2.98k

prism-ml/Ternary-Bonsai-2-27B-mlx-2bit

Text Generation • 27B • Updated 6 days ago • 23k • 488

prism-ml/Ternary-Bonsai-2-9B-gguf

Image-Text-to-Text • 1B • Updated 6 days ago • 1.22M • 163

prism-ml/Ternary-Bonsai-2-4B-gguf

Image-Text-to-Text • 0.8B • Updated 6 days ago • 127k • 41

prism-ml/Ternary-Bonsai-2-2B-gguf

Image-Text-to-Text • 2B • Updated 6 days ago • 1.05M • 53

updated a model 11 days ago

prism-ml/Ternary-Bonsai-2-27B-gguf-dev

Text Generation • 27B • Updated 11 days ago • 27.1k • 41

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 11 days ago

Document the Q2_0 file for stock llama.cpp

🚀 3

#106 opened 11 days ago by

bri-prism

updated 2 models 26 days ago

prism-ml/Ternary-Bonsai-2-4B-mlx-2bit

Image-Text-to-Text • 5B • Updated 26 days ago • 12.9k • 11

prism-ml/Ternary-Bonsai-2-2B-mlx-2bit

Image-Text-to-Text • 2B • Updated 26 days ago • 12.1k • 12

updated a model 28 days ago

prism-ml/Ternary-Bonsai-2-9B-mlx-2bit

Image-Text-to-Text • 9B • Updated 27 days ago • 17.1k • 24

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

Known issues: Intel Vulkan coverage and self-quantized PQ2_0/PTQ1_0

1

#71 opened about 2 months ago by

bri-prism

Card: highlight the reasoning-effort guidance

#66 opened about 2 months ago by

bri-prism

Known issues: measured guidance on medium effort and repeat penalty

👍 1

#61 opened about 2 months ago by

bri-prism

New activity in prism-ml/Ternary-Bonsai-2-27B-mlx-2bit about 2 months ago

Recommend min_p 0.05 for thinking mode

👍 1

#5 opened about 2 months ago by

bri-prism

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

Card: correct the comparison sizes and densities

🔥 1

#60 opened about 2 months ago by

bri-prism

Add a known-issues page with workarounds and fix status

#58 opened about 2 months ago by

bri-prism

Card: fix the quickstart output limit (-n 16384) and recommend min_p 0.05

#57 opened about 2 months ago by

bri-prism

Set the model name and min_p in the GGUF metadata (weights unchanged)

👍 1

#59 opened about 2 months ago by

bri-prism

Add a known-issues page with workarounds and fix status

#58 opened about 2 months ago by

bri-prism

Card: fix the quickstart output limit (-n 16384) and recommend min_p 0.05

#57 opened about 2 months ago by

bri-prism