metadata
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- mlx
base_model: ai21labs/AI21-Jamba2-Mini
ncls-p/AI21-Jamba2-Mini-mlx-8Bit
The Model ncls-p/AI21-Jamba2-Mini-mlx-8Bit was converted to MLX format from ai21labs/AI21-Jamba2-Mini using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ncls-p/AI21-Jamba2-Mini-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)