TheBakerCat commited on
Commit
d87ed6a
1 Parent(s): 88ab93e

Firs version of the 2chanruGPT-small model

Browse files
README.md ADDED
@@ -0,0 +1 @@
 
1
+ ruGPT3-small model, trained on some 2chan posts
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 2,
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bad_words_ids": null,
9
+ "bos_token_id": 50256,
10
+ "decoder_start_token_id": null,
11
+ "do_sample": false,
12
+ "early_stopping": false,
13
+ "embd_pdrop": 0.1,
14
+ "eos_token_id": 50256,
15
+ "finetuning_task": null,
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "is_decoder": false,
23
+ "is_encoder_decoder": false,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1
27
+ },
28
+ "layer_norm_epsilon": 1e-05,
29
+ "length_penalty": 1.0,
30
+ "max_length": 20,
31
+ "min_length": 0,
32
+ "model_type": "gpt2",
33
+ "n_ctx": 2048,
34
+ "n_embd": 768,
35
+ "n_head": 12,
36
+ "n_inner": null,
37
+ "n_layer": 12,
38
+ "n_positions": 2048,
39
+ "no_repeat_ngram_size": 0,
40
+ "num_beams": 1,
41
+ "num_return_sequences": 1,
42
+ "output_attentions": false,
43
+ "output_hidden_states": false,
44
+ "output_past": true,
45
+ "pad_token_id": null,
46
+ "prefix": null,
47
+ "pruned_heads": {},
48
+ "repetition_penalty": 1.0,
49
+ "resid_pdrop": 0.1,
50
+ "summary_activation": null,
51
+ "summary_first_dropout": 0.1,
52
+ "summary_proj_to_labels": true,
53
+ "summary_type": "cls_index",
54
+ "summary_use_proj": true,
55
+ "task_specific_params": null,
56
+ "temperature": 1.0,
57
+ "top_k": 50,
58
+ "top_p": 1.0,
59
+ "torchscript": false,
60
+ "use_bfloat16": false,
61
+ "vocab_size": 50257
62
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132e021719b69bc23815dbd4bf0d222d293301f00b931f1298e89c4bb8e3fac2
3
+ size 702293775
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95455257980784d02be31f438a514424c55f7e85330e9e10b3b6000f8e488bf8
3
+ size 1711
vocab.json ADDED
The diff for this file is too large to render. See raw diff