Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,15 @@ language:
|
|
| 7 |
- en
|
| 8 |
---
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
Dolphin 2.1 🐬
|
| 11 |
https://erichartford.com/dolphin
|
| 12 |
|
|
|
|
| 7 |
- en
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# Note from repackager
|
| 11 |
+
|
| 12 |
+
This is just a repackage of [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)
|
| 13 |
+
- For usage in [text-generation-inference](https://github.com/huggingface/text-generation-inference) by applying a [fix suggested by user sam-ulrich1](https://github.com/huggingface/text-generation-inference/issues/1132#issuecomment-1781441165) for the error that some encountered when deploying:
|
| 14 |
+
```ValueError: Non-consecutive added token '<unk>' found. Should have index 32000 but has index 0 in saved vocabulary.```
|
| 15 |
+
- With safetensors included so that mainboard memory is not needed for a .bin -> .safetensors conversion step. This circumvents scenarios where the mainboard does not have enough memory but the GPU does.
|
| 16 |
+
|
| 17 |
+
# Below is original README from ehartford/dolphin-2.1-mistral-7b
|
| 18 |
+
|
| 19 |
Dolphin 2.1 🐬
|
| 20 |
https://erichartford.com/dolphin
|
| 21 |
|