Article
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
MultiverseComputingCAI
• • 73
Chris Hart
cghart123
AI & ML interests
None yet
Recent Activity
upvoted an article about 1 month ago
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original upvoted an article about 1 month ago
Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTCOrganizations
upvoted 2
articles about 1 month ago
Article
Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC
ibm-granite
• • 38 config.json ignore-list needs linear_attn patterns — model produces garbage otherwise
❤️ 1
3
#4 opened 6 months ago
by cghart123
config.json ignore-list needs linear_attn patterns — model produces garbage otherwise
#5 opened 6 months ago
by cghart123
updated a
Space over 2 years ago