Edit model card

mlx-community/llm-jp-3-13b-instruct-4bit

The Model mlx-community/llm-jp-3-13b-instruct-4bit was converted to MLX format from llm-jp/llm-jp-3-13b-instruct using mlx-lm version 0.17.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/llm-jp-3-13b-instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
17
Safetensors
Model size
2.14B params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) has been turned off for this model.