Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ Please use better calibrated version at https://huggingface.co/LnL-AI/dbrx-base-
|
|
| 10 |
Run:
|
| 11 |
1. Use PR https://github.com/AutoGPTQ/AutoGPTQ/pull/625
|
| 12 |
2. Need ~68GB of VRAM (1xA100 80G will do)
|
| 13 |
-
3. Use
|
| 14 |
|
| 15 |
```json
|
| 16 |
{
|
|
|
|
| 10 |
Run:
|
| 11 |
1. Use PR https://github.com/AutoGPTQ/AutoGPTQ/pull/625
|
| 12 |
2. Need ~68GB of VRAM (1xA100 80G will do)
|
| 13 |
+
3. Use combine_tensors.sh script to combine the two split files into one. HF has max 50GB file size limit.
|
| 14 |
|
| 15 |
```json
|
| 16 |
{
|