Text Generation
Transformers
Safetensors
MLX
llama
conversational
text-generation-inference
Inference Endpoints
Edit model card

ucalyptus/prem-1B-chat-MLX

This model was converted to MLX format from premai-io/prem-1B-chat. 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("ucalyptus/prem-1B-chat-MLX")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
3
Safetensors
Model size
227M params
Tensor type
FP16
·
U32
·
Inference API
Input a message to start chatting with ucalyptus/prem-1B-chat-MLX.
This model can be loaded on Inference API (serverless).

Datasets used to train ucalyptus/prem-1B-chat-MLX

Collection including ucalyptus/prem-1B-chat-MLX