mlx-community/Valkyrie-49B-v1-bf16

The Model mlx-community/Valkyrie-49B-v1-bf16 was converted to MLX format from TheDrummer/Valkyrie-49B-v1 using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Valkyrie-49B-v1-bf16")

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
17
Safetensors
Model size
50B params
Tensor type
F16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mlx-community/Valkyrie-49B-v1-bf16

Finetuned
(1)
this model