batmac/zephyr-7b-beta-mlx-4bit
This model was converted to MLX format from HuggingFaceH4/zephyr-7b-beta.
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("batmac/zephyr-7b-beta-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 4
Model tree for batmac/zephyr-7b-beta-mlx-4bit
Base model
mistralai/Mistral-7B-v0.1Datasets used to train batmac/zephyr-7b-beta-mlx-4bit
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard62.031
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.356
- f1 score on Drop (3-Shot)validation set Open LLM Leaderboard9.662
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard57.449
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard12.737
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard61.070
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.743
- win rate on AlpacaEvalsource0.906
- score on MT-Benchsource7.340