2-layer truncated models used for Bertha CI regression tests.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 55
hyper-accel/ci-random-w4a16-asym-g64-llama3-3b
0.6B • Updated • 1
hyper-accel/Qwen3-VL-2B-Instruct-W4A16_ASYM-G64
2B • Updated • 31
hyper-accel/Llama-3.2-3B-Instruct-W4A16_ASYM-G64
3B • Updated • 112
hyper-accel/ci-random-qwen2-moe-a3b
Text Generation • 2B • Updated • 874
hyper-accel/qwen2-moe-a3b-2layer
2B • Updated • 7
hyper-accel/ci-2layer-llama2-7b
0.7B • Updated • 10.3k • 1
hyper-accel/ci-random-bfloat16-llama3-3b
Text Generation • 0.6B • Updated • 2.63k
hyper-accel/ci-random-llama3-3b
Text Generation • 0.6B • Updated • 77
hyper-accel/ci-random-bfloat16-llama3-8b
Text Generation • 1B • Updated • 4
hyper-accel/ci-random-bfloat16-llama2-7b
Text Generation • 0.7B • Updated • 6
datasets 0
None public yet