mlx-community/dolphin-2.8-mistral-7b-v02

This model was converted to MLX format from cognitivecomputations/dolphin-2.8-mistral-7b-v02 using mlx-lm version 0.7.0. 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/dolphin-2.8-mistral-7b-v02")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 66

MLX

Hardware compatibility

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlx-community/dolphin-2.8-mistral-7b-v02

Base model

mistral-community/Mistral-7B-v0.2

Finetuned

(37)

this model

Datasets used to train mlx-community/dolphin-2.8-mistral-7b-v02

Evaluation results

pass@1 on HumanEval
self-reported

0.469