README.md

metadata

license: other
tags:
  - generated_from_trainer
  - mlx
base_model: meta-llama/Meta-Llama-3-8B
datasets:
  - cognitivecomputations/Dolphin-2.9
  - teknium/OpenHermes-2.5
  - m-a-p/CodeFeedback-Filtered-Instruction
  - cognitivecomputations/dolphin-coder
  - cognitivecomputations/samantha-data
  - HuggingFaceH4/ultrachat_200k
  - microsoft/orca-math-word-problems-200k
  - abacusai/SystemChat-1.1
  - Locutusque/function-calling-chatml
  - internlm/Agent-FLAN
model-index:
  - name: out
    results: []

mlx-community/dolphin-2.9-llama3-8b-4bit-mlx

This model was converted to MLX format from cognitivecomputations/dolphin-2.9-llama3-8b using mlx-lm version 0.10.0. 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-2.9-llama3-8b-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)