Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- vicgalle/alpaca-gpt4
|
| 5 |
+
pipeline_tag: conversational
|
| 6 |
+
tags:
|
| 7 |
+
- alpaca
|
| 8 |
+
- gpt4
|
| 9 |
+
- gpt-j
|
| 10 |
+
- instruction
|
| 11 |
+
- finetuning
|
| 12 |
+
- lora
|
| 13 |
+
- peft
|
| 14 |
---
|
| 15 |
+
GPT-J 6B model was finetuned on GPT-4 generations of the Alpaca prompts on [MonsterAPI](https://monsterapi.ai)'s no-code LLM finetuner, using LoRA for ~ 65,000 steps, taking over 87 hours on 1 A6000 GPU.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
+
license: apache-2.0
|
| 25 |
+
---
|