MLX
English
llama
mc0ps's picture
Update README.md
9de675b verified
|
raw
history blame
656 Bytes
metadata
language:
  - en
tags:
  - mlx
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
  - allenai/tulu-v2-sft-mixture
base_model: meta-llama/Llama-2-7b-hf
model-index:
  - name: tulu-2-dpo-7b
    results: []

mlx-community/tulu-2-dpo-7b-4bit-mlx

This model was converted to MLX format from allenai/tulu-2-dpo-7b. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/tulu-2-dpo-7b-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)