metadata
base_model: unsloth/DeepSeek-R1-0528-BF16
language:
- en
library_name: transformers
license: mit
tags:
- deepseek
- unsloth
- transformers
- mlx
- mlx-my-repo
cs2764/DeepSeek-R1-0528-BF16-mlx-3Bit-gs32
The Model cs2764/DeepSeek-R1-0528-BF16-mlx-3Bit-gs32 was converted to MLX format from unsloth/DeepSeek-R1-0528-BF16 using mlx-lm version 0.26.2.
Quantization Details
This model was converted with the following quantization settings:
- Quantization Strategy: 3-bit quantization
- Group Size: 32
- Average bits per weight: 4.002
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cs2764/DeepSeek-R1-0528-BF16-mlx-3Bit-gs32")
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)