prince-canuma's picture
07de28efc48882fc15cde8c6b990e07b7a04fb606fdef47dfcdd34bff31566ba
c8a9eca verified
|
raw
history blame
913 Bytes
metadata
base_model: arcee-ai/SuperNova-Medius
library_name: transformers
license: apache-2.0
tags:
  - mergekit
  - merge
  - mlx

mlx-community/SuperNova-Medius-bf16

The Model mlx-community/SuperNova-Medius-bf16 was converted to MLX format from arcee-ai/SuperNova-Medius using mlx-lm version 0.19.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/SuperNova-Medius-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)