.buildkite/lm-eval-harness/configs/models-large.txt

Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml
Meta-Llama-3-70B-Instruct.yaml
Mixtral-8x7B-Instruct-v0.1.yaml
Qwen2-57B-A14-Instruct.yaml
DeepSeek-V2-Lite-Chat.yaml
[ Kernel ] Enable `fp8-marlin` for `fbgemm-fp8` models (#6606) 2024-07-20 14:50:10 -04:00			`Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml`
[ CI/Build ] LM Eval Harness Based CI Testing (#5838) Co-authored-by: Robert Shaw <rshaw@neuralmagic> 2024-06-29 13:04:30 -04:00			`Meta-Llama-3-70B-Instruct.yaml`
			`Mixtral-8x7B-Instruct-v0.1.yaml`
[ Misc ] Refactor MoE to isolate Fp8 From Mixtral (#5970) Co-authored-by: Robert Shaw <rshaw@neuralmagic> Co-authored-by: Michael Goin <michael@neuralmagic.com> 2024-07-02 17:54:35 -04:00			`Qwen2-57B-A14-Instruct.yaml`
[ Misc ] Apply MoE Refactor to Deepseekv2 To Support Fp8 (#6417) 2024-07-13 23:03:58 -04:00			`DeepSeek-V2-Lite-Chat.yaml`