zjunlp/OceanInstruct-v0.1
Viewer • Updated • 10k • 268 • 6
How to use introvoyz041/OceanGPT-basic-7B-v0.1-mlx-4Bit with MLX:
# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]
# Generate text with mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/OceanGPT-basic-7B-v0.1-mlx-4Bit")
prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)How to use introvoyz041/OceanGPT-basic-7B-v0.1-mlx-4Bit with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "introvoyz041/OceanGPT-basic-7B-v0.1-mlx-4Bit" --prompt "Once upon a time"
The Model introvoyz041/OceanGPT-basic-7B-v0.1-mlx-4Bit was converted to MLX format from zjunlp/OceanGPT-basic-7B-v0.1 using mlx-lm version 0.28.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/OceanGPT-basic-7B-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)
4-bit
Base model
zjunlp/OceanGPT-basic-7B-v0.1