Downloads · 30 days
212
7% of all-time downloads
hsefz-ChenJunJie/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B-mlx-4Bit
L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B-mlx-4Bit is a text generation model from hsefz-ChenJunJie. 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 hsefz-ChenJunJie/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B-mlx-4Bit was converted to MLX format from DavidAU/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B using ml…
Downloads · 30 days
212
7% of all-time downloads
All-time downloads
2.9K
Public
Parameters
36.2B
20.4 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors20.4 GB · 100%
How the weights are stored.
U3236.2B · 100%
From the Hugging Face model README
The Model hsefz-ChenJunJie/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B-mlx-4Bit was converted to MLX format from DavidAU/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B using mlx-lm version 0.22.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("hsefz-ChenJunJie/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-Hermes-R1-Uncensored-36B-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)