Files
wehub-resource-sync ba4be087d5
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
CICD NeMo / cicd-test-container-build (push) Has been cancelled
CICD NeMo / cicd-import-tests (push) Has been cancelled
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Has been cancelled
CICD NeMo / cicd-main-unit-tests (push) Has been cancelled
CICD NeMo / cicd-main-speech (push) Has been cancelled
CICD NeMo / Nemo_CICD_Test (push) Has been cancelled
CICD NeMo / Coverage (e2e) (push) Has been cancelled
CICD NeMo / Coverage (unit-test) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
CICD NeMo / cicd-wait-in-queue (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:28:58 +08:00

39 lines
1.1 KiB
YAML

# Model registry configuration
# Centralized registry of available models and their corresponding configuration files
#
# "reasoning_supported=true" means that there's a another llm yaml file with the same name but addidional "_think.yaml" suffix,
# which is tested to work as expected, otherwise you need to mamually modify the llm yaml to enable their reasoning mode.
llm_models:
"nvidia/NVIDIA-Nemotron-Nano-9B-v2":
yaml_id: "nemotron_nano_v2.yaml"
reasoning_supported: false
"meta-llama/Llama-3.1-8B-Instruct":
yaml_id: "llama3.1-8B-instruct.yaml"
reasoning_supported: false
"Qwen/Qwen2.5-7B-Instruct":
yaml_id: "qwen2.5-7B.yaml"
reasoning_supported: false
"Qwen/Qwen3-8B":
yaml_id: "qwen3-8B.yaml"
reasoning_supported: true
"hf_llm_generic":
yaml_id: "hf_llm_generic.yaml"
reasoning_supported: false
tts_models:
"fastpitch-hifigan":
yaml_id: "nemo_fastpitch-hifigan.yaml"
"hexgrad/Kokoro-82M":
yaml_id: "kokoro_82M.yaml"
stt_models:
"stt_en_fastconformer_hybrid_large_streaming_80ms":
yaml_id: "nemo_cache_aware_streaming.yaml"
type: "nemo"