Commit
•
b8185c1
1
Parent(s):
655e516
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,8 @@ base_model: databricks/dbrx-instruct
|
|
| 9 |
**2024-04-11**: Support for this model is still being worked on - [`PR #6515`](https://github.com/ggerganov/llama.cpp/pull/6515).
|
| 10 |
We are currently testing quants and I will upload them once they are working.
|
| 11 |
|
|
|
|
|
|
|
| 12 |
* GGUF importance matrix (imatrix) quants for https://huggingface.co/databricks/dbrx-instruct
|
| 13 |
* The importance matrix is trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
|
| 14 |
* [Which GGUF is right for me? (from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) - X axis is file size and Y axis is perplexity (lower perplexity is better quality).
|
|
|
|
| 9 |
**2024-04-11**: Support for this model is still being worked on - [`PR #6515`](https://github.com/ggerganov/llama.cpp/pull/6515).
|
| 10 |
We are currently testing quants and I will upload them once they are working.
|
| 11 |
|
| 12 |
+
**NOTE**: Do not download the model unless it states above that testing is conclusive, otherwise the model won't work.
|
| 13 |
+
|
| 14 |
* GGUF importance matrix (imatrix) quants for https://huggingface.co/databricks/dbrx-instruct
|
| 15 |
* The importance matrix is trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
|
| 16 |
* [Which GGUF is right for me? (from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) - X axis is file size and Y axis is perplexity (lower perplexity is better quality).
|