mlx-community/Yi-6B-Chat-4bit

The Model mlx-community/Yi-6B-Chat-4bit was converted to MLX format from 01-ai/Yi-6B-Chat using mlx-lm version 0.19.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Yi-6B-Chat-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
11
Safetensors
Model size
947M params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.

Model tree for mlx-community/Yi-6B-Chat-4bit

Base model

01-ai/Yi-6B-Chat
Quantized
(9)
this model