zeta-2-4bit / README.md
NexVeridian's picture
Add files using upload-large-folder tool
f795827 verified
metadata
base_model: zed-industries/zeta-2
tags:
  - text-generation-inference
  - transformers
  - edit-prediction
  - next-edit-suggestion
  - mlx
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
library_name: mlx

NexVeridian/zeta-2-4bit

This model NexVeridian/zeta-2-4bit was converted to MLX format from zed-industries/zeta-2 using mlx-lm version 0.31.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/zeta-2-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)