VariableZee
commited on
Commit
•
508a48f
1
Parent(s):
5a032d8
Update model
Browse files- config.json +2 -3
- eval_results.txt +1 -1
- pytorch_model.bin +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
@@ -18,7 +19,6 @@
|
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
20 |
"resid_pdrop": 0.1,
|
21 |
-
"scale_attn_weights": true,
|
22 |
"summary_activation": null,
|
23 |
"summary_first_dropout": 0.1,
|
24 |
"summary_proj_to_labels": true,
|
@@ -29,8 +29,7 @@
|
|
29 |
"max_length": 1000
|
30 |
}
|
31 |
},
|
32 |
-
"
|
33 |
-
"transformers_version": "4.11.3",
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 50257
|
36 |
}
|
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
|
|
19 |
"n_layer": 12,
|
20 |
"n_positions": 1024,
|
21 |
"resid_pdrop": 0.1,
|
|
|
22 |
"summary_activation": null,
|
23 |
"summary_first_dropout": 0.1,
|
24 |
"summary_proj_to_labels": true,
|
|
|
29 |
"max_length": 1000
|
30 |
}
|
31 |
},
|
32 |
+
"transformers_version": "4.5.1",
|
|
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 50257
|
35 |
}
|
eval_results.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
perplexity = tensor(
|
|
|
1 |
+
perplexity = tensor(29.3612)
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510403817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3351b33568e477ce26c7510c209d50751cf248d2ac53d6de9294afe52b637fd5
|
3 |
size 510403817
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"
|
|
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"}
|