metadata
license: apache-2.0
language:
- en
base_model: zeroentropy/zerank-2-reranker
pipeline_tag: text-ranking
tags:
- finance
- legal
- code
- stem
- medical
- mlx
- mlx-my-repo
library_name: sentence-transformers
model_max_length: 32768
k8smee/zerank-2-reranker-mlx-8Bit
The Model k8smee/zerank-2-reranker-mlx-8Bit was converted to MLX format from zeroentropy/zerank-2-reranker using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("k8smee/zerank-2-reranker-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)