Downloads · 30 days
17
22% of all-time downloads
AlekseyCalvin/Lyrical_ru2_en_NanBeige_3B-mlx-4Bit
Lyrical_ru2_en_NanBeige_3B-mlx-4Bit is a text generation model from AlekseyCalvin. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
The Model AlekseyCalvin/Lyricalru2enNanBeige3B-mlx-4Bit was converted to MLX format from AlekseyCalvin/Lyricalru2enNanBeige3B using mlx-lm version 0.31.2.
Downloads · 30 days
17
22% of all-time downloads
All-time downloads
78
Public
Parameters
3.9B
2.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.2 GB · 99%
How the weights are stored.
U323.9B · 100%
From the Hugging Face model README
The Model AlekseyCalvin/Lyrical_ru2_en_NanBeige_3B-mlx-4Bit was converted to MLX format from AlekseyCalvin/Lyrical_ru2_en_NanBeige_3B using mlx-lm version 0.31.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("AlekseyCalvin/Lyrical_ru2_en_NanBeige_3B-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)