Downloads · 30 days
46
4% of all-time downloads
mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-8bit
IQuest-Coder-V1-40B-Loop-Instruct-8bit is a text generation model from mlx-community. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.
This model mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-8bit was converted to MLX format from IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct using mlx-lm version 0.30.0.
Downloads · 30 days
46
4% of all-time downloads
All-time downloads
1.1K
Public
Parameters
39.8B
42.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors42.3 GB · 100%
How the weights are stored.
U3239.8B · 100%
From the Hugging Face model README
This model mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-8bit was converted to MLX format from IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct using mlx-lm version 0.30.0.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-8bit")
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)