mlx-community/Nanbeige4.1-3B-heretic-bfloat16
This model mlx-community/Nanbeige4.1-3B-heretic-bfloat16 was converted to MLX format from heretic-org/Nanbeige4.1-3B-heretic using mlx-lm version 0.30.6.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Nanbeige4.1-3B-heretic-bfloat16")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 59
Model size
4B params
Tensor type
BF16
·
Hardware compatibility
Log In
to add your hardware
Quantized
Model tree for mlx-community/Nanbeige4.1-3B-heretic-bfloat16
Base model
Nanbeige/Nanbeige4-3B-Base
Finetuned
Nanbeige/Nanbeige4.1-3B
Finetuned
heretic-org/Nanbeige4.1-3B-heretic