Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,37 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- ggml
|
| 6 |
+
- text-generation
|
| 7 |
+
- causal-lm
|
| 8 |
+
- rwkv
|
| 9 |
license: apache-2.0
|
| 10 |
+
datasets:
|
| 11 |
+
- EleutherAI/pile
|
| 12 |
+
- togethercomputer/RedPajama-Data-1T
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
**Last updated:** 2023-05-23
|
| 16 |
+
|
| 17 |
+
This is [BlinkDL/rwkv-4-pileplus](https://huggingface.co/BlinkDL/rwkv-4-pileplus) converted to GGML for use with rwkv.cpp and KoboldCpp. [rwkv.cpp's conversion instructions](https://github.com/saharNooby/rwkv.cpp#option-32-convert-and-quantize-pytorch-model) were followed.
|
| 18 |
+
|
| 19 |
+
Original model card is below.
|
| 20 |
+
|
| 21 |
+
* * *
|
| 22 |
+
|
| 23 |
+
# RWKV-4 PilePlus
|
| 24 |
+
|
| 25 |
+
## Model Description
|
| 26 |
+
|
| 27 |
+
RWKV-4-pile models finetuning on [RedPajama + some of Pile v2 = 1.7T tokens]. Updated with 2020+2021+2022 data, and better at all European languages.
|
| 28 |
+
|
| 29 |
+
Although some of these are intermedia checkpoints (XXXGtokens means finetuned for XXXG tokens), you can already use them because I am finetuning from Pile models (instead of retraining).
|
| 30 |
+
|
| 31 |
+
Note: not instruct tuned yet, and recommended to replace vanilla Pile models.
|
| 32 |
+
|
| 33 |
+
7B and 14B coming soon.
|
| 34 |
+
|
| 35 |
+
See https://github.com/BlinkDL/RWKV-LM for details.
|
| 36 |
+
|
| 37 |
+
Use https://github.com/BlinkDL/ChatRWKV to run it.
|