YashJain/GitAI-Qwen2-0.5B-Instruct-MLX-v2

The Model YashJain/GitAI-Qwen2-0.5B-Instruct-MLX-v2 was converted to MLX format from Qwen/Qwen2-0.5B-Instruct-MLX using mlx-lm version 0.14.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("YashJain/GitAI-Qwen2-0.5B-Instruct-MLX-v2")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
8
Safetensors
Model size
77.3M params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.

Collection including YashJain/GitAI-Qwen2-0.5B-Instruct-MLX-v2