psx7/llama4B

The Model psx7/llama4B was converted to MLX format from rasyosef/Llama-3.1-Minitron-4B-Chat using mlx-lm version 0.18.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("psx7/llama4B")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
33
Safetensors
Model size
4.51B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for psx7/llama4B

Quantized
(15)
this model

Dataset used to train psx7/llama4B