mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-11-02 06:36:36 +00:00
89 lines
3.1 KiB
YAML
89 lines
3.1 KiB
YAML
dockers:
|
|
- pull_tag: rocm/jax-training:maxtext-v26.1
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v26.1/images/sha256-901083bde353fe6362ada3036e452c792b2c96124e5900f4e9b5946c02ff9d6a
|
|
components:
|
|
ROCm: 7.1.1
|
|
JAX: 0.8.2
|
|
Python: 3.12
|
|
Transformer Engine: 2.8.0.dev0+aec00a7f
|
|
hipBLASLt: 1.2.x
|
|
model_groups:
|
|
- group: Meta Llama
|
|
tag: llama
|
|
models:
|
|
- model: Llama 2 7B
|
|
mad_tag: jax_maxtext_train_llama-2-7b
|
|
model_repo: Llama-2-7B
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama2_7b.yml
|
|
gfx942: env_scripts/llama2_7b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- model: Llama 2 70B
|
|
mad_tag: jax_maxtext_train_llama-2-70b
|
|
model_repo: Llama-2-70B
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama2_70b.yml
|
|
gfx942: env_scripts/llama2_70b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- model: Llama 3 8B (multi-node)
|
|
mad_tag: jax_maxtext_train_llama-3-8b
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3_8b.yml
|
|
gfx942: env_scripts/llama3_8b.yml
|
|
doc_options: ["multi-node"]
|
|
- model: Llama 3 70B (multi-node)
|
|
mad_tag: jax_maxtext_train_llama-3-70b
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3_70b.yml
|
|
gfx942: env_scripts/llama3_70b.yml
|
|
doc_options: ["multi-node"]
|
|
- model: Llama 3.1 8B
|
|
mad_tag: jax_maxtext_train_llama-3.1-8b
|
|
model_repo: Llama-3.1-8B
|
|
precision: bf16
|
|
doc_options: ["single-node"]
|
|
- model: Llama 3.1 70B
|
|
mad_tag: jax_maxtext_train_llama-3.1-70b
|
|
model_repo: Llama-3.1-70B
|
|
precision: bf16
|
|
doc_options: ["single-node"]
|
|
- model: Llama 3.1 405B (multi-node)
|
|
mad_tag: jax_maxtext_train_llama-3.1-405b
|
|
model_repo: Llama-3.1-405B
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3_405b.yml
|
|
doc_options: ["multi-node"]
|
|
- model: Llama 3.3 70B
|
|
mad_tag: jax_maxtext_train_llama-3.3-70b
|
|
model_repo: Llama-3.3-70B
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_llama3.3_70b.yml
|
|
gfx942: env_scripts/llama3.3_70b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- group: DeepSeek
|
|
tag: deepseek
|
|
models:
|
|
- model: DeepSeek-V2-Lite (16B)
|
|
mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
|
|
model_repo: DeepSeek-V2-lite
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_deepseek2_16b.yml
|
|
gfx942: env_scripts/deepseek2_16b.yml
|
|
doc_options: ["single-node", "multi-node"]
|
|
- group: Mistral AI
|
|
tag: mistral
|
|
models:
|
|
- model: Mixtral 8x7B
|
|
mad_tag: jax_maxtext_train_mixtral-8x7b
|
|
model_repo: Mixtral-8x7B
|
|
precision: bf16
|
|
multinode_config:
|
|
gfx950: env_scripts/gfx950_mixtral_8x7b.yml
|
|
gfx942: env_scripts/llama3_8x7b.yml
|
|
doc_options: ["single-node", "multi-node"]
|