Hugging Face's logo

magicslabnu
/
OPT-1.3b

Text Generation
Transformers
PyTorch
Safetensors
opt
text-generation-inference
Model card Files
xet
Community
robinzixuan1997 commited on
Commit
f00697a
·
1 Parent(s): 359a4e0

OPT-1.3b

Browse files
Files changed (17) hide show
  1. all_results.json +1 -0
  2. checkpoints/checkpoint_30000/model.safetensors +3 -0
  3. checkpoints/checkpoint_30000/optimizer.bin +3 -0
  4. checkpoints/checkpoint_30000/random_states_0.pkl +3 -0
  5. checkpoints/checkpoint_30000/random_states_1.pkl +3 -0
  6. checkpoints/checkpoint_30000/random_states_2.pkl +3 -0
  7. checkpoints/checkpoint_30000/random_states_3.pkl +3 -0
  8. checkpoints/checkpoint_30000/scaler.pt +3 -0
  9. checkpoints/checkpoint_30000/scheduler.bin +3 -0
  10. config.json +28 -0
  11. generation_config.json +7 -0
  12. merges.txt +0 -0
  13. pytorch_model.bin +3 -0
  14. special_tokens_map.json +30 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +40 -0
  17. vocab.json +0 -0
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 16.333818060199437}
checkpoints/checkpoint_30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0fafadc75f9f59fdb55f01dbdbbebddf7e6473530190c63e89a2015c616fd1
3
+ size 5009879832
checkpoints/checkpoint_30000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148d47513bc8d396bec2495f52bed98dc1a871706ed763fabf1b545d349020f4
3
+ size 10020009668
checkpoints/checkpoint_30000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb0d6510b408b06f092b9710cbbe03854045e496e436a08cf9d4707bdf3f292
3
+ size 15060
checkpoints/checkpoint_30000/random_states_1.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d1c8bf2247359823b668ef449aa26d455bbf973b6be3a26af655ea4e3b63c9
3
+ size 15060
checkpoints/checkpoint_30000/random_states_2.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:787b78630204347f101d29437027573afa36c4bb5914f1a4834d8f98e33e3aea
3
+ size 15060
checkpoints/checkpoint_30000/random_states_3.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efa200dec8ae94e77c886e8981e09e3aac29d68e65e5c324bc6fe8deb05d619
3
+ size 15060
checkpoints/checkpoint_30000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acd99e85e3349a6e35c9e0b523b167cfda3db60b992682e2b09cf0024c47aa5
3
+ size 988
checkpoints/checkpoint_30000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923f50aabb565a7a7ebb4155fa8fa4841389ca3996ffa123160f31993741e2ec
3
+ size 1064
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_remove_final_layer_norm": false,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "OPTForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "do_layer_norm_before": true,
10
+ "dropout": 0.1,
11
+ "enable_bias": true,
12
+ "eos_token_id": 2,
13
+ "ffn_dim": 8192,
14
+ "hidden_size": 2048,
15
+ "init_std": 0.006,
16
+ "layer_norm_elementwise_affine": true,
17
+ "layerdrop": 0.0,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "opt",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 24,
22
+ "pad_token_id": 1,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "use_cache": true,
26
+ "vocab_size": 50272,
27
+ "word_embed_proj_dim": 768
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.31.0"
7
+ }
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:b34a5613ca18eac8680435e6133bdd48163f8a09eda5785b0061c29a103094eb
3
+ size 5009967394
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff