Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQi
|
|
| 27 |
|
| 28 |
## Important note: files must be joined before use
|
| 29 |
|
| 30 |
-
It is not currently possible to shard GPTQ files, therefore the model file is one single
|
| 31 |
|
| 32 |
Huggingface Hub has a 50GB per-file limit. I have therefore been forced to split the file in to three parts for upload.
|
| 33 |
|
|
|
|
| 27 |
|
| 28 |
## Important note: files must be joined before use
|
| 29 |
|
| 30 |
+
It is not currently possible to shard GPTQ files, therefore the model file is one single 94GB `safetensors` file.
|
| 31 |
|
| 32 |
Huggingface Hub has a 50GB per-file limit. I have therefore been forced to split the file in to three parts for upload.
|
| 33 |
|