mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-09 06:38:00 -05:00
30 lines
949 B
YAML
30 lines
949 B
YAML
megatron-lm_benchmark:
|
|
model_groups:
|
|
- group: Meta Llama
|
|
tag: llama
|
|
models:
|
|
- model: Llama 3.3 70B
|
|
mad_tag: pyt_megatron_lm_train_llama-3.3-70b
|
|
- model: Llama 3.1 8B
|
|
mad_tag: pyt_megatron_lm_train_llama-3.1-8b
|
|
- model: Llama 3.1 70B
|
|
mad_tag: pyt_megatron_lm_train_llama-3.1-70b
|
|
- model: Llama 2 7B
|
|
mad_tag: pyt_megatron_lm_train_llama-2-7b
|
|
- model: Llama 2 70B
|
|
mad_tag: pyt_megatron_lm_train_llama-2-70b
|
|
- group: DeepSeek
|
|
tag: deepseek
|
|
models:
|
|
- model: DeepSeek-V3
|
|
mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
|
|
- model: DeepSeek-V2-Lite
|
|
mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
|
|
- group: Mistral AI
|
|
tag: mistral
|
|
models:
|
|
- model: Mixtral 8x7B
|
|
mad_tag: pyt_megatron_lm_train_mixtral-8x7b
|
|
- model: Mixtral 8x22B
|
|
mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
|