Mamba-Chat is the first chat language model based on a state-space model architecture, not a transformer.
The model is a fine-tune of Albert Gu's and Tri Dao's model Mamba-2.8B from their paper Mamba: Linear-Time Sequence Modeling with Selective State Spaces.
Check our our Github repository for training and inference code.
The prompt format is the zephyr format:
<|user|> {user_message}
<|assistant|> {assistant_message}
<|user|> {user_message}
<|assistant|> {assistant_message}
- Downloads last month
- 147
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.