RWKV-1b5-finetuned-overfit
Browse files- README.md +2 -0
- tokenizer.json +1 -6
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
model-index:
|
| 6 |
- name: RWKV-1b5-finetuned-overfit
|
| 7 |
results: []
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -57,6 +58,7 @@ The following hyperparameters were used during training:
|
|
| 57 |
|
| 58 |
### Framework versions
|
| 59 |
|
|
|
|
| 60 |
- Transformers 4.31.0
|
| 61 |
- Pytorch 2.0.1+cu117
|
| 62 |
- Datasets 2.13.1
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: RWKV-1b5-finetuned-overfit
|
| 7 |
results: []
|
| 8 |
+
library_name: peft
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 58 |
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
+
- PEFT 0.4.0
|
| 62 |
- Transformers 4.31.0
|
| 63 |
- Pytorch 2.0.1+cu117
|
| 64 |
- Datasets 2.13.1
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|