Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Norquinal/claude_multiround_chat_30k
|
| 5 |
+
- ehartford/dolphin
|
| 6 |
+
- BAAI/COIG-PC
|
| 7 |
+
- Open-Orca/OpenOrca
|
| 8 |
+
- vikp/textbook_quality_programming
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# RWKV v4 world 7B 65k context
|
| 13 |
+
|
| 14 |
+
This is the model to replace the old rwkv 65k claude model, with special token and lower learning rate to maintain model former abilities.
|
| 15 |
+
and trained a lots of high quality textbooks with 65k context length.
|
| 16 |
+
|
| 17 |
+
using it with rwkv runner only need 16G vram.(https://github.com/josStorer/RWKV-Runner)
|
| 18 |
+
|
| 19 |
+
## trainning details
|
| 20 |
+
https://wandb.ai/one-/one-rwkv-64k/runs/jn05hyc4
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
## Testcase
|
| 25 |
+
https://rwkv-next-web.ai-creator.net/ (temporary)
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
## contributor
|
| 29 |
+
|