Hugging Face's logo

mcxfrank
/
childes-gpt2-ladder

Text Generation
Transformers
Safetensors
gpt2
childes
child-directed-speech
language-acquisition
developmental
sample-efficient-pretraining
Model card Files
xet
 Community
mcxfrank commited on
Commit
b60d7fe
·
verified ·
1 Parent(s): a7fb423

add development/seed4/rung1.5M

Browse files
Files changed (9) hide show
  1. development/seed4/rung1.5M/config.json +39 -0
  2. development/seed4/rung1.5M/generation_config.json +6 -0
  3. development/seed4/rung1.5M/merges.txt +0 -0
  4. development/seed4/rung1.5M/model.safetensors +3 -0
  5. development/seed4/rung1.5M/provenance.json +1 -0
  6. development/seed4/rung1.5M/special_tokens_map.json +26 -0
  7. development/seed4/rung1.5M/tokenizer.json +0 -0
  8. development/seed4/rung1.5M/tokenizer_config.json +31 -0
  9. development/seed4/rung1.5M/vocab.json +0 -0
development/seed4/rung1.5M/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data2/mcfrank/ladder/retrain_dev/seed4_1.5M/checkpoint-4248",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 0,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.49.0",
37
+ "use_cache": true,
38
+ "vocab_size": 52000
39
+ }
development/seed4/rung1.5M/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.49.0"
6
+ }
development/seed4/rung1.5M/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
development/seed4/rung1.5M/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604e48d7e04d70280a022f6d3f61bac4bfc5c5dc3af13bf24c20a90ae16e51fb
3
+ size 251571904
development/seed4/rung1.5M/provenance.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"condition":"development","seed":4,"budget_words":"1.5M","epochs_max":40,"early_stop_patience":4,"dtype":"bfloat16"}
development/seed4/rung1.5M/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<UNK>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "unk_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ }
26
+ }
development/seed4/rung1.5M/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
development/seed4/rung1.5M/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<UNK>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "additional_special_tokens": [
22
+ "<UNK>"
23
+ ],
24
+ "bos_token": "<|endoftext|>",
25
+ "clean_up_tokenization_spaces": true,
26
+ "eos_token": "<|endoftext|>",
27
+ "extra_special_tokens": {},
28
+ "model_max_length": 1024,
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }
development/seed4/rung1.5M/vocab.json ADDED
The diff for this file is too large to render. See raw diff