Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_4bit

The Model Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_4bit was converted to MLX format from Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct using mlx-lm version 0.20.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-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
99
Safetensors
Model size
241M params
Tensor type
FP16
·
U32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_4bit

Base model

Qwen/Qwen2.5-1.5B
Quantized
(4)
this model

Dataset used to train Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-MLX_4bit