README.md

metadata

library_name: transformers
inference:
  parameters:
    temperature: 1
    top_p: 0.95
    top_k: 40
    repetition_penalty: 1.2
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
tags:
  - mlx
base_model: ministral/Ministral-3b-instruct

ubaitur5/Ministral-3b-instruct-Q4-mlx

The Model ubaitur5/Ministral-3b-instruct-Q4-mlx was converted to MLX format from ministral/Ministral-3b-instruct using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ubaitur5/Ministral-3b-instruct-Q4-mlx")

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)