mitkox/Genstruct-7B-mlx

This model was converted to MLX format from NousResearch/Genstruct-7B. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mitkox/Genstruct-7B-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
64
Safetensors
Model size
1.24B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for mitkox/Genstruct-7B-mlx

Finetuned
(839)
this model