jbeiroa/mlx_lora_llama-3.2-1b-q8

The Model jbeiroa/mlx_lora_llama-3.2-1b-q8 was converted to MLX format from jbeiroa/mlx_llama-3.2-1b-q8 using mlx-lm version 0.20.4.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("jbeiroa/mlx_lora_llama-3.2-1b-q8")

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
19
Safetensors
Model size
1.24B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for jbeiroa/mlx_lora_llama-3.2-1b-q8

Finetuned
(1)
this model
Quantizations
1 model