Views
No views yet
GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.
| Layers | Context | Template (Text Representation) | Template (Text Generation) |
|---|---|---|---|
32 | 32768 | <s><|user|> {instruction} <|embed|> {sample} | <s><|user|> {prompt} <|assistant|> {response} |