psx7/llama1B

The Model psx7/llama1B was converted to MLX format from mlx-community/Llama-3.2-1B-Instruct-bf16 using mlx-lm version 0.18.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("psx7/llama1B")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
124
Safetensors
Model size
1.24B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.