cointegrated commited on
Commit
de4c6be
1 Parent(s): 7b68f65

The first commit

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 512,
14
+ "n_head": 8,
15
+ "n_inner": null,
16
+ "n_layer": 8,
17
+ "n_positions": 1024,
18
+ "reorder_and_upcast_attn": false,
19
+ "resid_pdrop": 0.1,
20
+ "scale_attn_by_inverse_layer_idx": false,
21
+ "scale_attn_weights": true,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.18.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 50257
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f945cfbff6c1ca89b43b259ecaaf6dc9262536a5c84de787127dccc412f3073
3
+ size 411867959
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948e6e72a5ea8563ee8f4634a8dfac60d6e33b470311dc284ff82e184bd9127b
3
+ size 317257036
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f994a31af9b1c5c9243672457f325d646fa321745b20074de0faa066349aba
3
+ size 13624
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e5b8e837092230fa3b4059ae73df90ae607dbc63b9df90fdbe98c151c2e3f4
3
+ size 13624
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef4b2391bfed9534438d4ba37087524e313de1ef2cbd3defca94930438d39ae
3
+ size 13624
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e304742af611b59a6ecc32dd8b65ff486959feed07e29c98f3c2bf0e4267f7b4
3
+ size 13624
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635d67590b9700e94b2e6da235e9388dbd366c44a13bac38479c95a2f3a883af
3
+ size 13624
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec193630a18b372116e116b829631cc625f4c855c6aad53c699a65812d6eb3db
3
+ size 13624
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd9f351a88c5f31a77a2eb384d6de05fae3e12571763adde54342851d215472
3
+ size 13624
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27dba29dd761317dd4841b252bb6df6a69d7d6e01269963f3bb2acb8b99d9cad
3
+ size 13624
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306135f314ea786fbda3ec78052de44d3d3ef37928efd5d11652ad2203e6d71b
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3a41da60454bfaea3fe49e6114eb40ddaee81fe6cf63b7b242c1f367dc8fcc
3
+ size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff