rltakashige
39c39e8199
## Motivation <!-- Why is this change needed? What problem does it solve? --> <!-- If it fixes an open issue, please link to the issue here --> ## Changes <!-- Describe what you changed in detail --> ## Why It Works <!-- Explain why your approach solves the problem --> ## Test Plan ### Manual Testing <!-- Hardware: (e.g., MacBook Pro M1 Max 32GB, Mac Mini M2 16GB, connected via Thunderbolt 4) --> <!-- What you did: --> <!-- - --> ### Automated Testing <!-- Describe changes to automated tests, or how existing tests cover this change --> <!-- - -->
15 lines
314 B
TOML
15 lines
314 B
TOML
model_id = "mlx-community/NVIDIA-Nemotron-Nano-9B-v2-4bits"
|
|
n_layers = 56
|
|
hidden_size = 4480
|
|
supports_tensor = true
|
|
tasks = ["TextGeneration"]
|
|
family = "nemotron"
|
|
quantization = "4bit"
|
|
base_model = "NVIDIA Nemotron-Nano-9B-v2"
|
|
capabilities = ["text"]
|
|
|
|
context_length = 131072
|
|
|
|
[storage_size]
|
|
in_bytes = 5002791936
|