Commit
•
70d5b3c
1
Parent(s):
4ca1407
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,6 @@ GGUF quants for https://huggingface.co/GritLM/GritLM-7B
|
|
| 7 |
|
| 8 |
> 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.
|
| 9 |
|
| 10 |
-
**NOTE**: There is an issue with getting correct embeddings using this model, which should be fixed once PR [#5796](https://github.com/ggerganov/llama.cpp/pull/5796) is merged.
|
| 11 |
-
|
| 12 |
| Layers | Context | [Template (Text Representation)](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference) | [Template (Text Generation)](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference) |
|
| 13 |
| --- | --- | --- | --- |
|
| 14 |
| <pre>32</pre> | <pre>32768</pre> | <pre>\<s\>\<\|user\|\><br>{instruction}<br>\<\|embed\|\><br>{sample}</pre> | <pre>\<s\>\<\|user\|\><br>{prompt}<br>\<\|assistant\|\><br>{response}</pre> |
|
|
|
|
| 7 |
|
| 8 |
> 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.
|
| 9 |
|
|
|
|
|
|
|
| 10 |
| Layers | Context | [Template (Text Representation)](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference) | [Template (Text Generation)](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference) |
|
| 11 |
| --- | --- | --- | --- |
|
| 12 |
| <pre>32</pre> | <pre>32768</pre> | <pre>\<s\>\<\|user\|\><br>{instruction}<br>\<\|embed\|\><br>{sample}</pre> | <pre>\<s\>\<\|user\|\><br>{prompt}<br>\<\|assistant\|\><br>{response}</pre> |
|