metadata
license: mit
pipeline_tag: text-generation
tags:
- ocean
- text-generation-inference
- oceangpt
- mlx
- mlx-my-repo
language:
- en
- zh
datasets:
- zjunlp/OceanInstruct
base_model: zjunlp/OceanGPT-basic-2B-v0.1
introvoyz041/OceanGPT-basic-2B-v0.1-mlx-4Bit
The Model introvoyz041/OceanGPT-basic-2B-v0.1-mlx-4Bit was converted to MLX format from zjunlp/OceanGPT-basic-2B-v0.1 using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/OceanGPT-basic-2B-v0.1-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)