diff --git a/docs/source/getting_started/distributions/self_hosted_distro/fireworks.md b/docs/source/getting_started/distributions/self_hosted_distro/fireworks.md index 03ee9e604..30d822946 100644 --- a/docs/source/getting_started/distributions/self_hosted_distro/fireworks.md +++ b/docs/source/getting_started/distributions/self_hosted_distro/fireworks.md @@ -22,15 +22,15 @@ The following environment variables can be configured: The following models are available by default: -- `fireworks/llama-v3p1-8b-instruct` -- `fireworks/llama-v3p1-70b-instruct` -- `fireworks/llama-v3p1-405b-instruct` -- `fireworks/llama-v3p2-1b-instruct` -- `fireworks/llama-v3p2-3b-instruct` -- `fireworks/llama-v3p2-11b-vision-instruct` -- `fireworks/llama-v3p2-90b-vision-instruct` -- `fireworks/llama-guard-3-8b` -- `fireworks/llama-guard-3-11b-vision` +- `meta-llama/Llama-3.1-8B-Instruct (fireworks/llama-v3p1-8b-instruct)` +- `meta-llama/Llama-3.1-70B-Instruct (fireworks/llama-v3p1-70b-instruct)` +- `meta-llama/Llama-3.1-405B-Instruct-FP8 (fireworks/llama-v3p1-405b-instruct)` +- `meta-llama/Llama-3.2-3B-Instruct (fireworks/llama-v3p2-1b-instruct)` +- `meta-llama/Llama-3.2-11B-Vision-Instruct (fireworks/llama-v3p2-3b-instruct)` +- `meta-llama/Llama-3.2-11B-Vision-Instruct (fireworks/llama-v3p2-11b-vision-instruct)` +- `meta-llama/Llama-3.2-90B-Vision-Instruct (fireworks/llama-v3p2-90b-vision-instruct)` +- `meta-llama/Llama-Guard-3-8B (fireworks/llama-guard-3-8b)` +- `meta-llama/Llama-Guard-3-11B-Vision (fireworks/llama-guard-3-11b-vision)` ### Prerequisite: API Keys diff --git a/docs/source/getting_started/distributions/self_hosted_distro/together.md b/docs/source/getting_started/distributions/self_hosted_distro/together.md index 17f109e65..fe4dc5fed 100644 --- a/docs/source/getting_started/distributions/self_hosted_distro/together.md +++ b/docs/source/getting_started/distributions/self_hosted_distro/together.md @@ -22,14 +22,14 @@ The following environment variables can be configured: The following models are available by default: -- `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo` -- `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo` -- `meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo` -- `meta-llama/Llama-3.2-3B-Instruct-Turbo` -- `meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo` -- `meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo` -- `meta-llama/Meta-Llama-Guard-3-8B` -- `meta-llama/Llama-Guard-3-11B-Vision-Turbo` +- `meta-llama/Llama-3.1-8B-Instruct` +- `meta-llama/Llama-3.1-70B-Instruct` +- `meta-llama/Llama-3.1-405B-Instruct-FP8` +- `meta-llama/Llama-3.2-3B-Instruct` +- `meta-llama/Llama-3.2-11B-Vision-Instruct` +- `meta-llama/Llama-3.2-90B-Vision-Instruct` +- `meta-llama/Llama-Guard-3-8B` +- `meta-llama/Llama-Guard-3-11B-Vision` ### Prerequisite: API Keys diff --git a/llama_stack/templates/fireworks/doc_template.md b/llama_stack/templates/fireworks/doc_template.md index bd25edfc1..6f6da3a91 100644 --- a/llama_stack/templates/fireworks/doc_template.md +++ b/llama_stack/templates/fireworks/doc_template.md @@ -20,7 +20,7 @@ The following environment variables can be configured: The following models are available by default: {% for model in default_models %} -- `{{ model.model_id }}` +- `{{ model.model_id }} ({{ model.provider_model_id }})` {% endfor %} {% endif %} diff --git a/llama_stack/templates/fireworks/fireworks.py b/llama_stack/templates/fireworks/fireworks.py index c4d2fdac8..5f744cae0 100644 --- a/llama_stack/templates/fireworks/fireworks.py +++ b/llama_stack/templates/fireworks/fireworks.py @@ -6,6 +6,8 @@ from pathlib import Path +from llama_models.sku_list import all_registered_models + from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES @@ -28,7 +30,16 @@ def get_distribution_template() -> DistributionTemplate: config=FireworksImplConfig.sample_run_config(), ) - default_models = [ModelInput(model_id=m.provider_model_id) for m in MODEL_ALIASES] + core_model_to_hf_repo = { + m.descriptor(): m.huggingface_repo for m in all_registered_models() + } + default_models = [ + ModelInput( + model_id=core_model_to_hf_repo[m.llama_model], + provider_model_id=m.provider_model_id, + ) + for m in MODEL_ALIASES + ] return DistributionTemplate( name="fireworks", diff --git a/llama_stack/templates/fireworks/run.yaml b/llama_stack/templates/fireworks/run.yaml index 7472e77ff..c9c05a8e0 100644 --- a/llama_stack/templates/fireworks/run.yaml +++ b/llama_stack/templates/fireworks/run.yaml @@ -45,41 +45,41 @@ metadata_store: db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db models: - metadata: {} - model_id: fireworks/llama-v3p1-8b-instruct + model_id: meta-llama/Llama-3.1-8B-Instruct provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p1-8b-instruct - metadata: {} - model_id: fireworks/llama-v3p1-70b-instruct + model_id: meta-llama/Llama-3.1-70B-Instruct provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p1-70b-instruct - metadata: {} - model_id: fireworks/llama-v3p1-405b-instruct + model_id: meta-llama/Llama-3.1-405B-Instruct-FP8 provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p1-405b-instruct - metadata: {} - model_id: fireworks/llama-v3p2-1b-instruct + model_id: meta-llama/Llama-3.2-3B-Instruct provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p2-1b-instruct - metadata: {} - model_id: fireworks/llama-v3p2-3b-instruct + model_id: meta-llama/Llama-3.2-11B-Vision-Instruct provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p2-3b-instruct - metadata: {} - model_id: fireworks/llama-v3p2-11b-vision-instruct + model_id: meta-llama/Llama-3.2-11B-Vision-Instruct provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p2-11b-vision-instruct - metadata: {} - model_id: fireworks/llama-v3p2-90b-vision-instruct + model_id: meta-llama/Llama-3.2-90B-Vision-Instruct provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-v3p2-90b-vision-instruct - metadata: {} - model_id: fireworks/llama-guard-3-8b + model_id: meta-llama/Llama-Guard-3-8B provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-guard-3-8b - metadata: {} - model_id: fireworks/llama-guard-3-11b-vision + model_id: meta-llama/Llama-Guard-3-11B-Vision provider_id: null - provider_model_id: null + provider_model_id: fireworks/llama-guard-3-11b-vision shields: - params: null shield_id: meta-llama/Llama-Guard-3-8B diff --git a/llama_stack/templates/together/run.yaml b/llama_stack/templates/together/run.yaml index a2082c691..bd28f0de3 100644 --- a/llama_stack/templates/together/run.yaml +++ b/llama_stack/templates/together/run.yaml @@ -45,37 +45,37 @@ metadata_store: db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db models: - metadata: {} - model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo + model_id: meta-llama/Llama-3.1-8B-Instruct provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo - metadata: {} - model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo + model_id: meta-llama/Llama-3.1-70B-Instruct provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo - metadata: {} - model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo + model_id: meta-llama/Llama-3.1-405B-Instruct-FP8 provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo - metadata: {} - model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo + model_id: meta-llama/Llama-3.2-3B-Instruct provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo - metadata: {} - model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo + model_id: meta-llama/Llama-3.2-11B-Vision-Instruct provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo - metadata: {} - model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo + model_id: meta-llama/Llama-3.2-90B-Vision-Instruct provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo - metadata: {} - model_id: meta-llama/Meta-Llama-Guard-3-8B + model_id: meta-llama/Llama-Guard-3-8B provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Meta-Llama-Guard-3-8B - metadata: {} - model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo + model_id: meta-llama/Llama-Guard-3-11B-Vision provider_id: null - provider_model_id: null + provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo shields: - params: null shield_id: meta-llama/Llama-Guard-3-1B diff --git a/llama_stack/templates/together/together.py b/llama_stack/templates/together/together.py index 250ef02c3..70748f2d6 100644 --- a/llama_stack/templates/together/together.py +++ b/llama_stack/templates/together/together.py @@ -6,6 +6,8 @@ from pathlib import Path +from llama_models.sku_list import all_registered_models + from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput from llama_stack.providers.remote.inference.together import TogetherImplConfig from llama_stack.providers.remote.inference.together.together import MODEL_ALIASES @@ -28,7 +30,16 @@ def get_distribution_template() -> DistributionTemplate: config=TogetherImplConfig.sample_run_config(), ) - default_models = [ModelInput(model_id=m.provider_model_id) for m in MODEL_ALIASES] + core_model_to_hf_repo = { + m.descriptor(): m.huggingface_repo for m in all_registered_models() + } + default_models = [ + ModelInput( + model_id=core_model_to_hf_repo[m.llama_model], + provider_model_id=m.provider_model_id, + ) + for m in MODEL_ALIASES + ] return DistributionTemplate( name="together",