A newer version of this model is available: meta-llama/Llama-3.1-8B

TheBlueObserver/Meta-Llama-3-8B-MLX-393a7

The Model TheBlueObserver/Meta-Llama-3-8B-MLX-393a7 was converted to MLX format from meta-llama/Meta-Llama-3-8B using mlx-lm version 0.20.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("TheBlueObserver/Meta-Llama-3-8B-MLX-393a7")

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
0
Safetensors
Model size
2.26B params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.

Model tree for TheBlueObserver/Meta-Llama-3-8B-MLX-393a7

Quantized
(240)
this model