tags:
- chat
- mlx
base_model: Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
pipeline_tag: text-generation
library_name: mlx
mlx-community/Josiefied-Olmo-3-7B-Instruct-abliterated-v1-4bit
This model mlx-community/Josiefied-Olmo-3-7B-Instruct-abliterated-v1-4bit was
converted to MLX format from Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Josiefied-Olmo-3-7B-Instruct-abliterated-v1-4bit")
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)