cmcmaster/rheum-dolphin-2.9.4-gemma2-2b
The Model cmcmaster/rheum-dolphin-2.9.4-gemma2-2b was converted to MLX format from cognitivecomputations/dolphin-2.9.4-gemma2-2b using mlx-lm version 0.18.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cmcmaster/rheum-dolphin-2.9.4-gemma2-2b")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 12
Model size
3B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for cmcmaster/rheum-dolphin-2.9.4-gemma2-2b
Base model
google/gemma-2-2b