Configuration Parsing Warning: In config.json: "quantization_config.bits" must be greater than or equal to 2

Hjgugugjhuhjggg/xddd-mlx-2Bit-mlx-1Bit

The Model Hjgugugjhuhjggg/xddd-mlx-2Bit-mlx-1Bit was converted to MLX format from Hjgugugjhuhjggg/xddd-mlx-2Bit using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Hjgugugjhuhjggg/xddd-mlx-2Bit-mlx-1Bit")

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)
Downloads last month
46
Safetensors
Model size
301M params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Hjgugugjhuhjggg/xddd-mlx-2Bit-mlx-1Bit

Finetuned
(1)
this model