Downloads · 30 days
68
5% of all-time downloads
fengpeisheng1/Peach-2.0-9B-8k-Roleplay-mlx-4Bit
Peach-2.0-9B-8k-Roleplay-mlx-4Bit is a text generation model from fengpeisheng1. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
The Model fengpeisheng1/Peach-2.0-9B-8k-Roleplay-mlx-4Bit was converted to MLX format from ClosedCharacter/Peach-2.0-9B-8k-Roleplay using mlx-lm version 0.22.3.
Downloads · 30 days
68
5% of all-time downloads
All-time downloads
1.3K
Public
Parameters
8.8B
5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors5 GB · 100%
How the weights are stored.
U328.8B · 100%
From the Hugging Face model README
The Model fengpeisheng1/Peach-2.0-9B-8k-Roleplay-mlx-4Bit was converted to MLX format from ClosedCharacter/Peach-2.0-9B-8k-Roleplay using mlx-lm version 0.22.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("fengpeisheng1/Peach-2.0-9B-8k-Roleplay-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)