End of training
Browse files- README.md +6 -2
- config.json +1 -1
README.md
CHANGED
@@ -2,12 +2,16 @@
|
|
2 |
license: mit
|
3 |
base_model: gpt2
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
-
-
|
11 |
model-index:
|
12 |
- name: gpt2-cpt-dutch
|
13 |
results: []
|
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# gpt2-cpt-dutch
|
20 |
|
21 |
-
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
2 |
license: mit
|
3 |
base_model: gpt2
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
11 |
- alignment-handbook
|
12 |
- generated_from_trainer
|
13 |
datasets:
|
14 |
+
- wdli/deptweet_dataset
|
15 |
model-index:
|
16 |
- name: gpt2-cpt-dutch
|
17 |
results: []
|
|
|
22 |
|
23 |
# gpt2-cpt-dutch
|
24 |
|
25 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wdli/deptweet_dataset dataset.
|
26 |
|
27 |
## Model description
|
28 |
|
config.json
CHANGED
@@ -34,6 +34,6 @@
|
|
34 |
},
|
35 |
"torch_dtype": "bfloat16",
|
36 |
"transformers_version": "4.40.2",
|
37 |
-
"use_cache":
|
38 |
"vocab_size": 50257
|
39 |
}
|
|
|
34 |
},
|
35 |
"torch_dtype": "bfloat16",
|
36 |
"transformers_version": "4.40.2",
|
37 |
+
"use_cache": true,
|
38 |
"vocab_size": 50257
|
39 |
}
|