metadata
base_model: LLM360/K2-Think
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- mlx
m-i/K2-Think-mlx-8Bit
The Model m-i/K2-Think-mlx-8Bit was converted to MLX format from LLM360/K2-Think using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("m-i/K2-Think-mlx-8Bit")
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)