underwater45 commited on
Commit
ae4e916
1 Parent(s): 2f5735e

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +28 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +24 -0
  4. starllm-3.pth +3 -0
  5. tokenizer_config.json +22 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "attn_pdrop": 0.1,
4
+ "bos_token_id": 50256,
5
+ "embd_pdrop": 0.1,
6
+ "eos_token_id": 50256,
7
+ "initializer_range": 0.02,
8
+ "layer_norm_epsilon": 1e-05,
9
+ "model_type": "gpt2",
10
+ "n_embd": 784,
11
+ "n_head": 14,
12
+ "n_inner": null,
13
+ "n_layer": 14,
14
+ "n_positions": 1024,
15
+ "pad_token_id": 50256,
16
+ "reorder_and_upcast_attn": false,
17
+ "resid_pdrop": 0.1,
18
+ "scale_attn_by_inverse_layer_idx": false,
19
+ "scale_attn_weights": true,
20
+ "summary_activation": null,
21
+ "summary_first_dropout": 0.1,
22
+ "summary_proj_to_labels": true,
23
+ "summary_type": "cls_index",
24
+ "summary_use_proj": true,
25
+ "transformers_version": "4.41.2",
26
+ "use_cache": true,
27
+ "vocab_size": 190000
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
starllm-3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871434134ffdd443016a6c9925e5af2a864802a7444828a09737f977c524c6a6
3
+ size 1012739450
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1024,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff