2-layer truncated models used for Bertha CI regression tests.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 60
hyper-accel/Qwen3-8B-W8A16
3B • Updated
hyper-accel/SmolVLM2-256M-Video-Instruct-vision-W8A16-text-W4A16-G64
0.2B • Updated • 7
hyper-accel/SmolVLM2-256M-Video-Instruct-vision-W8A16-text-W4A16-G64-dequant-bf16
0.3B • Updated • 7
hyper-accel/Qwen3-VL-2B-Instruct-W4A16-dequant-bf16
2B • Updated • 133
hyper-accel/ci-2layer-llama3-8b
1B • Updated • 3
hyper-accel/ci-random-w4a16-asym-g64-llama3-3b
0.6B • Updated • 5
hyper-accel/Qwen3-VL-2B-Instruct-W4A16_ASYM-G64
2B • Updated • 66
hyper-accel/Llama-3.2-3B-Instruct-W4A16_ASYM-G64
3B • Updated • 769
hyper-accel/ci-random-qwen2-moe-a3b
Text Generation • 2B • Updated • 2.59k
hyper-accel/qwen2-moe-a3b-2layer
2B • Updated • 32
datasets 0
None public yet