2-layer truncated models used for Bertha CI regression tests.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 72
hyper-accel/Llama-2-7b-hf-FP8-OC
7B • Updated • 14
hyper-accel/Qwen3-8B-FP8-OC
8B • Updated • 12
hyper-accel/Qwen3-235B-A22B-FP8-OC
236B • Updated • 27
hyper-accel/Qwen3-30B-A3B-FP8-OC
31B • Updated • 238
hyper-accel/SmolVLM2-500M-Video-Instruct-vision-W8A16-text-W4A16-G64-ASYM-dequant-bf16
0.5B • Updated • 11
hyper-accel/SmolVLM2-500M-Video-Instruct-vision-W8A16-text-W4A16-G64-ASYM
0.4B • Updated • 26
hyper-accel/SmolVLM2-500M-Video-Instruct-vision-BF16-text-W8A16-ASYM-dequant-bf16
0.5B • Updated • 11
hyper-accel/SmolVLM2-500M-Video-Instruct-vision-BF16-text-W8A16-ASYM
0.5B • Updated • 19
hyper-accel/SmolVLM2-256M-Video-Instruct-vision-BF16-text-W8A16-ASYM-dequant-bf16
0.3B • Updated • 25
hyper-accel/SmolVLM2-256M-Video-Instruct-vision-BF16-text-W8A16-ASYM
0.3B • Updated • 36
datasets 0
None public yet