arxiv:2406.04692
Jue Wang
juewang
AI & ML interests
None yet
Organizations
models 14
juewang/deepseek_r1_0528_mtp_fp8
Updated
juewang/llama-3.1-8b-test-lora
Updated
juewang/deepseek-coder-6.7b-base-trt-int4-g64-hf
Text Generation • 4B • Updated • 7
juewang/deepseek-coder-1.3b-base-trt-int4-g64-hf
Text Generation • 0.8B • Updated • 6
juewang/deepseek-coder-1.3b-instruct-trt-int4-g64-hf
Text Generation • 0.8B • Updated • 13
juewang/deepseek-coder-6.7b-instruct-trt-int4-g64-hf
Text Generation • 4B • Updated • 11
juewang/deepseek-coder-6.7b-instruct-trt-int8-g64-hf
Text Generation • 7B • Updated • 5
juewang/deepseek-coder-6.7b-instruct-trt-int8-g32-hf
Text Generation • 7B • Updated • 6
juewang/deepseek-coder-6.7b-instruct-trt-int8-g128-hf
Text Generation • 7B • Updated • 5
juewang/Meta-Llama-3-2B-mlp-layer-pruned
Text Generation • 3B • Updated • 5