mlx-community/Writer-Palmyra-Fin-70B-32K
The Model mlx-community/Writer-Palmyra-Fin-70B-32K was converted to MLX format from Writer/Palmyra-Fin-70B-32K using mlx-lm version 0.16.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Writer-Palmyra-Fin-70B-32K")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 5
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.