Hugging Face's logo

magicslabnu
/
OPT-350m

Text Generation
Transformers
PyTorch
Safetensors
opt
text-generation-inference
Model card Files
xet
Community
robinzixuan1997 commited on
Commit
d145d5a
·
1 Parent(s): c6e7148

350m

Browse files
Files changed (18) hide show
  1. README.md +3 -3
  2. all_results.json +1 -0
  3. checkpoints/checkpoint_30000/model.safetensors +3 -0
  4. checkpoints/checkpoint_30000/optimizer.bin +3 -0
  5. checkpoints/checkpoint_30000/random_states_0.pkl +3 -0
  6. checkpoints/checkpoint_30000/random_states_1.pkl +3 -0
  7. checkpoints/checkpoint_30000/random_states_2.pkl +3 -0
  8. checkpoints/checkpoint_30000/random_states_3.pkl +3 -0
  9. checkpoints/checkpoint_30000/scaler.pt +3 -0
  10. checkpoints/checkpoint_30000/scheduler.bin +3 -0
  11. config.json +28 -0
  12. generation_config.json +7 -0
  13. merges.txt +0 -0
  14. pytorch_model.bin +3 -0
  15. special_tokens_map.json +30 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +40 -0
  18. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,3 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
1
+ ---
2
+ license: mit
3
+ ---
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 19.42920457709152}
checkpoints/checkpoint_30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe53a6f5439f6b25de085741d2c087271af0e62e2619b9d9d5bfb98667107c89
3
+ size 1374220688
checkpoints/checkpoint_30000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c823f6755f78513782d7b613ff172da94e368ab4baefaf85d1b7ad973a195fd
3
+ size 2748676900
checkpoints/checkpoint_30000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946df4f2e38c6b37f292075f87dfa09af43f303941a2496031e6e3f187fff6d8
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:ba47e201838f4711c503d725096fc2eff0197d152a6b306886a45086720fd834
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 sha256:999626b680b54b16ef944aa927d84d8823abcd0deb5df1ff8df15cbdf1e8c08e
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 sha256:151c749e2ff2fe4fcfe4dfbd6c727f3beef1d449007cc8aa3546259c83288d98
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:e72df4a5db936de0b8fc8e85758ce73904799b9bc75661c73065a6aec9c7543c
3
+ size 988
checkpoints/checkpoint_30000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e5fecb55870f3b7e5634108ec8bce358e221f3c7b6568b16d1a8849ab28e74
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": 4096,
14
+ "hidden_size": 1024,
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": 16,
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 sha256:1dba6c03ee6c23fe3a39dd06f923bf132e9a3de732b6712a922107755aaa09c9
3
+ size 1374307938
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