Commit ·
351c0b8
1
Parent(s): cd0f87b
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,7 @@ Combined with
|
|
| 39 |
Dataset related to STEM and NLP: garage-bAInd/Open-Platypus
|
| 40 |
|
| 41 |
### Training Procedure
|
| 42 |
-
LoRa script: https://github.com/STEM-ai/Phi-2/
|
| 43 |
|
| 44 |
A LoRa PEFT was performed on a 48 Gb A40 Nvidia GPU.
|
| 45 |
|
|
@@ -50,4 +50,6 @@ William Harbec
|
|
| 50 |
|
| 51 |
### Inference example
|
| 52 |
|
| 53 |
-
https://github.com/STEM-ai/Phi-2/
|
|
|
|
|
|
|
|
|
| 39 |
Dataset related to STEM and NLP: garage-bAInd/Open-Platypus
|
| 40 |
|
| 41 |
### Training Procedure
|
| 42 |
+
LoRa script: https://github.com/STEM-ai/Phi-2/raw/4eaa6aaa2679427a810ace5a061b9c951942d66a/LoRa.py
|
| 43 |
|
| 44 |
A LoRa PEFT was performed on a 48 Gb A40 Nvidia GPU.
|
| 45 |
|
|
|
|
| 50 |
|
| 51 |
### Inference example
|
| 52 |
|
| 53 |
+
Standard: https://github.com/STEM-ai/Phi-2/raw/4eaa6aaa2679427a810ace5a061b9c951942d66a/chat.py
|
| 54 |
+
|
| 55 |
+
GPTQ format: https://github.com/STEM-ai/Phi-2/raw/ab1ced8d7922765344d824acf1924df99606b4fc/chat-GPTQ.py
|