DQN-Labs/ministral-3b-textonly
This model DQN-Labs/ministral-3b-textonly was converted to MLX format from LakoMoor/Ministral-3-3B-Text-Only using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("DQN-Labs/ministral-3b-textonly")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 33
Model size
0.5B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for DQN-Labs/ministral-3b-textonly
Base model
mistralai/Ministral-3-3B-Base-2512 Quantized
mistralai/Ministral-3-3B-Instruct-2512 Finetuned
LakoMoor/Ministral-3-3B-Text-Only