Upload 10 files
Browse files- config.json +1 -1
- eval_results.txt +1 -1
- generation_config.json +6 -0
- merges.txt +1 -1
- pytorch_model.bin +2 -2
- tokenizer.json +9 -5
- tokenizer_config.json +1 -2
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
}
|
| 33 |
},
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
-
"transformers_version": "4.
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 50257
|
| 38 |
}
|
|
|
|
| 32 |
}
|
| 33 |
},
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.28.1",
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 50257
|
| 38 |
}
|
eval_results.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
perplexity = tensor(1.
|
|
|
|
| 1 |
+
perplexity = tensor(1.5243)
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.28.1"
|
| 6 |
+
}
|
merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:142dcf76d97dc77f993dc86af5a0f17aac6e437e901db4bae6190bb441239f01
|
| 3 |
+
size 510398013
|
tokenizer.json
CHANGED
|
@@ -5,29 +5,32 @@
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
| 8 |
-
"special": true,
|
| 9 |
"content": "<|endoftext|>",
|
| 10 |
"single_word": false,
|
| 11 |
"lstrip": false,
|
| 12 |
"rstrip": false,
|
| 13 |
-
"normalized": true
|
|
|
|
| 14 |
}
|
| 15 |
],
|
| 16 |
"normalizer": null,
|
| 17 |
"pre_tokenizer": {
|
| 18 |
"type": "ByteLevel",
|
| 19 |
"add_prefix_space": false,
|
| 20 |
-
"trim_offsets": true
|
|
|
|
| 21 |
},
|
| 22 |
"post_processor": {
|
| 23 |
"type": "ByteLevel",
|
| 24 |
"add_prefix_space": true,
|
| 25 |
-
"trim_offsets": false
|
|
|
|
| 26 |
},
|
| 27 |
"decoder": {
|
| 28 |
"type": "ByteLevel",
|
| 29 |
"add_prefix_space": true,
|
| 30 |
-
"trim_offsets": true
|
|
|
|
| 31 |
},
|
| 32 |
"model": {
|
| 33 |
"type": "BPE",
|
|
@@ -36,6 +39,7 @@
|
|
| 36 |
"continuing_subword_prefix": "",
|
| 37 |
"end_of_word_suffix": "",
|
| 38 |
"fuse_unk": false,
|
|
|
|
| 39 |
"vocab": {
|
| 40 |
"!": 0,
|
| 41 |
"\"": 1,
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
|
|
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"single_word": false,
|
| 10 |
"lstrip": false,
|
| 11 |
"rstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"special": true
|
| 14 |
}
|
| 15 |
],
|
| 16 |
"normalizer": null,
|
| 17 |
"pre_tokenizer": {
|
| 18 |
"type": "ByteLevel",
|
| 19 |
"add_prefix_space": false,
|
| 20 |
+
"trim_offsets": true,
|
| 21 |
+
"use_regex": true
|
| 22 |
},
|
| 23 |
"post_processor": {
|
| 24 |
"type": "ByteLevel",
|
| 25 |
"add_prefix_space": true,
|
| 26 |
+
"trim_offsets": false,
|
| 27 |
+
"use_regex": true
|
| 28 |
},
|
| 29 |
"decoder": {
|
| 30 |
"type": "ByteLevel",
|
| 31 |
"add_prefix_space": true,
|
| 32 |
+
"trim_offsets": true,
|
| 33 |
+
"use_regex": true
|
| 34 |
},
|
| 35 |
"model": {
|
| 36 |
"type": "BPE",
|
|
|
|
| 39 |
"continuing_subword_prefix": "",
|
| 40 |
"end_of_word_suffix": "",
|
| 41 |
"fuse_unk": false,
|
| 42 |
+
"byte_fallback": false,
|
| 43 |
"vocab": {
|
| 44 |
"!": 0,
|
| 45 |
"\"": 1,
|
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"eos_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<|endoftext|>",
|
|
@@ -19,9 +20,7 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
-
"name_or_path": "microsoft/DialoGPT-small",
|
| 23 |
"pad_token": null,
|
| 24 |
-
"special_tokens_map_file": null,
|
| 25 |
"tokenizer_class": "GPT2Tokenizer",
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "<|endoftext|>",
|
|
|
|
| 20 |
},
|
| 21 |
"errors": "replace",
|
| 22 |
"model_max_length": 1024,
|
|
|
|
| 23 |
"pad_token": null,
|
|
|
|
| 24 |
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be6afa05e21f4092da7064719386bca54623aa11f600c3b96ac8abeb360b19d4
|
| 3 |
+
size 1339
|