metadata
license: apache-2.0
base_model: DeepHat/DeepHat-V1-7B
language:
- en
pipeline_tag: text-generation
library_name: mlx
tags:
- code
- qwen-coder
- cybersecurity
- devops
- mlx
Otilde/DeepHat-V1-7B-Q8-MLX
This model Otilde/DeepHat-V1-7B-Q8-MLX was converted to MLX format from DeepHat/DeepHat-V1-7B using mlx-lm version 0.28.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Otilde/DeepHat-V1-7B-Q8-MLX")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)