metadata
license: apache-2.0
language:
- en
pipeline_tag: text-generation
base_model: allenai/OLMo-2-1124-13B-Instruct
library_name: transformers
datasets:
- allenai/RLVR-MATH
tags:
- mlx
Linuss4880/OLMo-2-1124-13B-Instruct-mlx-4Bit
The Model Linuss4880/OLMo-2-1124-13B-Instruct-mlx-4Bit was converted to MLX format from allenai/OLMo-2-1124-13B-Instruct using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Linuss4880/OLMo-2-1124-13B-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)