README.md

metadata

license: apache-2.0
language:
  - en
datasets:
  - allenai/RLVR-GSM-MATH-IF-Mixed-Constraints
base_model: allenai/OLMo-2-0325-32B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
  - mlx

codingmavin/OLMo-2-0325-32B-Instruct-mlx-6Bit

The Model codingmavin/OLMo-2-0325-32B-Instruct-mlx-6Bit was converted to MLX format from allenai/OLMo-2-0325-32B-Instruct using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("codingmavin/OLMo-2-0325-32B-Instruct-mlx-6Bit")

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)