Hugging Face's logo

stanford-crfm
/
eowyn-gpt2-medium-x777

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
 Community
yifanmai J38 commited on
Commit
5999c47
·
0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files

Co-authored-by: J38 <J38@users.noreply.huggingface.co>

Files changed (27) hide show
  1. .gitattributes +27 -0
  2. config.json +41 -0
  3. global_step400009/mp_rank_00_model_states.pt +3 -0
  4. global_step400009/zero_pp_rank_0_mp_rank_00optim_states.pt +3 -0
  5. global_step400009/zero_pp_rank_10_mp_rank_00optim_states.pt +3 -0
  6. global_step400009/zero_pp_rank_11_mp_rank_00optim_states.pt +3 -0
  7. global_step400009/zero_pp_rank_12_mp_rank_00optim_states.pt +3 -0
  8. global_step400009/zero_pp_rank_13_mp_rank_00optim_states.pt +3 -0
  9. global_step400009/zero_pp_rank_14_mp_rank_00optim_states.pt +3 -0
  10. global_step400009/zero_pp_rank_15_mp_rank_00optim_states.pt +3 -0
  11. global_step400009/zero_pp_rank_1_mp_rank_00optim_states.pt +3 -0
  12. global_step400009/zero_pp_rank_2_mp_rank_00optim_states.pt +3 -0
  13. global_step400009/zero_pp_rank_3_mp_rank_00optim_states.pt +3 -0
  14. global_step400009/zero_pp_rank_4_mp_rank_00optim_states.pt +3 -0
  15. global_step400009/zero_pp_rank_5_mp_rank_00optim_states.pt +3 -0
  16. global_step400009/zero_pp_rank_6_mp_rank_00optim_states.pt +3 -0
  17. global_step400009/zero_pp_rank_7_mp_rank_00optim_states.pt +3 -0
  18. global_step400009/zero_pp_rank_8_mp_rank_00optim_states.pt +3 -0
  19. global_step400009/zero_pp_rank_9_mp_rank_00optim_states.pt +3 -0
  20. latest +1 -0
  21. merges.txt +0 -0
  22. pytorch_model.bin +3 -0
  23. special_tokens_map.json +1 -0
  24. tokenizer_config.json +1 -0
  25. trainer_state.json +3 -0
  26. training_args.bin +3 -0
  27. vocab.json +0 -0
.gitattributes ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.onnx filter=lfs diff=lfs merge=lfs -text
14
+ *.ot filter=lfs diff=lfs merge=lfs -text
15
+ *.parquet filter=lfs diff=lfs merge=lfs -text
16
+ *.pb filter=lfs diff=lfs merge=lfs -text
17
+ *.pt filter=lfs diff=lfs merge=lfs -text
18
+ *.pth filter=lfs diff=lfs merge=lfs -text
19
+ *.rar filter=lfs diff=lfs merge=lfs -text
20
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
22
+ *.tflite filter=lfs diff=lfs merge=lfs -text
23
+ *.tgz filter=lfs diff=lfs merge=lfs -text
24
+ *.xz filter=lfs diff=lfs merge=lfs -text
25
+ *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stanford-crfm/eowyn-gpt2-medium-x777",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 1024,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 1024,
21
+ "n_special": 0,
22
+ "predict_special_tokens": true,
23
+ "reorder_and_upcast_attn": true,
24
+ "resid_pdrop": 0.1,
25
+ "scale_attn_by_inverse_layer_idx": true,
26
+ "scale_attn_weights": true,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "task_specific_params": {
33
+ "text-generation": {
34
+ "do_sample": true,
35
+ "max_length": 50
36
+ }
37
+ },
38
+ "transformers_version": "4.12.5",
39
+ "use_cache": false,
40
+ "vocab_size": 50257
41
+ }
global_step400009/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384b59de737c4d0f262fb0a3d549e71cbd15237683108e272a0ea583b614071b
3
+ size 734884708
global_step400009/zero_pp_rank_0_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d963c8b5566e261f73aba942219edbe80cfbf7271f53267e45f219554e7cff
3
+ size 266119230
global_step400009/zero_pp_rank_10_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e56a1cb4b185a79b5840b5b6e1dfe1090b2d2ea962e0f2751054f3838fb9177
3
+ size 266119230
global_step400009/zero_pp_rank_11_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee4d5a33abbc778fcd7454ee1b510f6f9ef006114c1140c0e698c1cdc211685
3
+ size 266119230
global_step400009/zero_pp_rank_12_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5b75b275b152c876d9e6ede5b18db22e38929609cd7f41e2b2b770b69a9bf6
3
+ size 266119230
global_step400009/zero_pp_rank_13_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ebb44b5f7231f9650942ad54305868de73cb00f8d23d66e16c09d606e71177
3
+ size 266119230
global_step400009/zero_pp_rank_14_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1101767b5e12f4aa4b2936c903a062b8c7654e32bbb8173c06bf2f585f5f34d0
3
+ size 266119228
global_step400009/zero_pp_rank_15_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c463f70d357528f2ab2d19e737a8b48e1f3625709929994ac54a756683cfe9
3
+ size 266119230
global_step400009/zero_pp_rank_1_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa9b74a668bf8fde76b35395b10bf4571c515eb19cdce7a11bee757c243276f
3
+ size 266119230
global_step400009/zero_pp_rank_2_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2320b431ac1e3b5c30b9ea1ba8b89f107e076df0e2f38795381e57d5ad174454
3
+ size 266119228
global_step400009/zero_pp_rank_3_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5687cdc81e39e9c85dd57a518b7540e945e270bfa52acb348d3d6cfc14f6b0b4
3
+ size 266119230
global_step400009/zero_pp_rank_4_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6ec132fcf886c15d5f8ff6878aaf84b7155e8b5d50853fbb7224b6e3fdc3ed
3
+ size 266119230
global_step400009/zero_pp_rank_5_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821415f9fc7259ec197b7e733860f400d89bf7b70cc0f763fce25062ed924f9c
3
+ size 266119230
global_step400009/zero_pp_rank_6_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46313eb2a8fcdb90f7fcdd11fb9430e9d9e9808667e656d333a225c24947ce83
3
+ size 266119230
global_step400009/zero_pp_rank_7_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afde54319c8af36e65b07290780435334a93fac38cec8171e0f95eac94b2def0
3
+ size 266119230
global_step400009/zero_pp_rank_8_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e83714747705befc9c5ef9b844316cba877380be16d20b307cb597eba373278
3
+ size 266119230
global_step400009/zero_pp_rank_9_mp_rank_00optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3dc169b9fd055a92c089ceb2c87f343d4293d50e6cde9043013a8f8db9c941
3
+ size 266119230
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step400009
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 sha256:4118b5e29068ceedf75befd6796385e26d88a0fe86c553fde294d8a6db76747c
3
+ size 734884388
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
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-medium"}
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957eaa30026391e6d844b79a09c6b528657d5fa8a2b5624c2507b989a0f8d688
3
+ size 27992245
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309dc7216be23bcb593efdd95f0044242941ef3ff5231d361d5fa9067693436c
3
+ size 2415
vocab.json ADDED
The diff for this file is too large to render. See raw diff