Upload 13 files
Browse filesFine-tuned model
- WarBot/.gitattributes +1 -0
- WarBot/added_tokens.json +3 -0
- WarBot/config.json +43 -0
- WarBot/desciption.txt +1 -0
- WarBot/eval_results.txt +1 -0
- WarBot/generation_config.json +6 -0
- WarBot/merges.txt +0 -0
- WarBot/pytorch_model.bin +3 -0
- WarBot/special_tokens_map.json +19 -0
- WarBot/tokenizer.json +0 -0
- WarBot/tokenizer_config.json +32 -0
- WarBot/training_args.bin +3 -0
- WarBot/vocab.json +0 -0
WarBot/.gitattributes
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
.bin filter=lfs diff=lfs merge=lfs -text
|
WarBot/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 50257
|
| 3 |
+
}
|
WarBot/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Kirili4ik/ruDialoGpt3-medium-finetuned-telegram",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "gpt2",
|
| 21 |
+
"n_ctx": 2048,
|
| 22 |
+
"n_embd": 1024,
|
| 23 |
+
"n_head": 16,
|
| 24 |
+
"n_inner": null,
|
| 25 |
+
"n_layer": 24,
|
| 26 |
+
"n_positions": 2048,
|
| 27 |
+
"n_special": 0,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"predict_special_tokens": true,
|
| 30 |
+
"reorder_and_upcast_attn": false,
|
| 31 |
+
"resid_pdrop": 0.1,
|
| 32 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 33 |
+
"scale_attn_weights": true,
|
| 34 |
+
"summary_activation": null,
|
| 35 |
+
"summary_first_dropout": 0.1,
|
| 36 |
+
"summary_proj_to_labels": true,
|
| 37 |
+
"summary_type": "cls_index",
|
| 38 |
+
"summary_use_proj": true,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.26.0",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50258
|
| 43 |
+
}
|
WarBot/desciption.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Fitted by the entire data on 11.02.2023
|
WarBot/eval_results.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
perplexity = tensor(32.1212)
|
WarBot/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": "4.26.0"
|
| 6 |
+
}
|
WarBot/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
WarBot/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21a29d5a157c6faa633224b6ae1029057c11fb5c461939a78874b4ac0d0b496d
|
| 3 |
+
size 1524265245
|
WarBot/special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<mask>",
|
| 4 |
+
"</s>",
|
| 5 |
+
"<unk>",
|
| 6 |
+
"<pad>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<|endoftext|>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": "</s>",
|
| 16 |
+
"mask_token": "<mask>",
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
WarBot/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
WarBot/tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"errors": "replace",
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"name_or_path": "Kirili4ik/ruDialoGpt3-medium-finetuned-telegram",
|
| 22 |
+
"special_tokens_map_file": null,
|
| 23 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 24 |
+
"unk_token": {
|
| 25 |
+
"__type": "AddedToken",
|
| 26 |
+
"content": "<|endoftext|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": true,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
}
|
| 32 |
+
}
|
WarBot/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62a5482077f77a9152bed96457a29a4ed0448316f2d69218c6e193faf9931dd9
|
| 3 |
+
size 1339
|
WarBot/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|