Fmuaddib/Yi-1.5-6B-mlx-4Bit

The Model Fmuaddib/Yi-1.5-6B-mlx-4Bit was converted to MLX format from unsloth/Yi-1.5-6B using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/Yi-1.5-6B-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
Downloads last month
3
Safetensors
Model size
947M params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Fmuaddib/Yi-1.5-6B-mlx-4Bit

Base model

unsloth/Yi-1.5-6B
Quantized
(2)
this model