Hugging Face's logo

Garsa3112
/
RMFT-Checkpoints

Safetensors
Model card Files
xet
 Community
Garsa3112 commited on
Commit
93e7ccd
·
verified ·
1 Parent(s): 91834a3

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. neo_base/70e2/optimizer.pt +3 -0
  2. neo_base/70e3/optimizer.pt +3 -0
  3. neo_base/80e1/optimizer.pt +3 -0
  4. neo_base/80e2/optimizer.pt +3 -0
  5. neo_base/80e3/optimizer.pt +3 -0
  6. neo_base/90e1/optimizer.pt +3 -0
  7. neo_base/90e2/model-00001-of-00002.safetensors +3 -0
  8. neo_base/90e2/optimizer.pt +3 -0
  9. neo_base/90e3/model-00001-of-00002.safetensors +3 -0
  10. neo_base/90e3/model-00002-of-00002.safetensors +3 -0
  11. neo_base/90e3/optimizer.pt +3 -0
  12. neo_base/90e3/rng_state.pth +3 -0
  13. neo_base/90e3/scheduler.pt +3 -0
  14. neo_base/90e3/training_args.bin +3 -0
  15. neo_rmft/100e1/model-00001-of-00002.safetensors +3 -0
  16. neo_rmft/100e1/model-00002-of-00002.safetensors +3 -0
  17. neo_rmft/100e1/rng_state.pth +3 -0
  18. neo_rmft/100e1/scheduler.pt +3 -0
  19. neo_rmft/100e1/training_args.bin +3 -0
  20. neo_rmft/100e2/model-00001-of-00002.safetensors +3 -0
  21. neo_rmft/100e2/model-00002-of-00002.safetensors +3 -0
  22. neo_rmft/100e2/rng_state.pth +3 -0
  23. neo_rmft/100e2/scheduler.pt +3 -0
  24. neo_rmft/100e2/tokenizer.json +0 -0
  25. neo_rmft/100e2/tokenizer_config.json +23 -0
  26. neo_rmft/100e2/trainer_state.json +54 -0
  27. neo_rmft/100e2/training_args.bin +3 -0
  28. neo_rmft/100e2/vocab.json +0 -0
  29. neo_rmft/100e3/config.json +75 -0
  30. neo_rmft/100e3/generation_config.json +6 -0
  31. neo_rmft/100e3/merges.txt +0 -0
  32. neo_rmft/100e3/model-00001-of-00002.safetensors +3 -0
  33. neo_rmft/100e3/model-00002-of-00002.safetensors +3 -0
  34. neo_rmft/100e3/model.safetensors.index.json +323 -0
  35. neo_rmft/100e3/rng_state.pth +3 -0
  36. neo_rmft/100e3/scheduler.pt +3 -0
  37. neo_rmft/100e3/special_tokens_map.json +23 -0
  38. neo_rmft/100e3/tokenizer.json +0 -0
  39. neo_rmft/100e3/tokenizer_config.json +23 -0
  40. neo_rmft/100e3/trainer_state.json +68 -0
  41. neo_rmft/100e3/training_args.bin +3 -0
  42. neo_rmft/100e3/vocab.json +0 -0
  43. neo_rmft/10e1/config.json +75 -0
  44. neo_rmft/10e1/generation_config.json +6 -0
  45. neo_rmft/10e1/merges.txt +0 -0
  46. neo_rmft/10e1/model-00001-of-00002.safetensors +3 -0
  47. neo_rmft/10e1/model-00002-of-00002.safetensors +3 -0
  48. neo_rmft/10e1/model.safetensors.index.json +323 -0
  49. neo_rmft/10e1/rng_state.pth +3 -0
  50. neo_rmft/10e1/scheduler.pt +3 -0
neo_base/70e2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b889265339bf1f1c4b7d473919771556a6057f721bf75f874d718dae94891cc
3
+ size 10524880634
neo_base/70e3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7d8e8ab0e606853c1eb8598d07965bb15ea81a60227d8c722274a92abaa6a6
3
+ size 10524880634
neo_base/80e1/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a303da6618dac19d4153dbcf17527493b39b362d8d1e3f438ab58d53e249ca
3
+ size 10524880634
neo_base/80e2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0263ada380474cca3965d77960c1f6e6d8ddf3359e2071d424a3f050fcdb66a
3
+ size 10524880634
neo_base/80e3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7f899cad9c13638574284e206d6beec9ed3600983f51d8f39c359733541c1d
3
+ size 10524880634
neo_base/90e1/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8655c62e84e429944ceb00ed37859888aa416ba3673c4b4ea3259a957d3f2437
3
+ size 10524880634
neo_base/90e2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85caace2565618ea99567be0d1d6dcba0608d4432f4ff12519fa7dcd618acc28
3
+ size 4993794184
neo_base/90e2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77467e3a45ed4b0d15d76f862c83f06a94a2a334437603a08acc03c73e821fe7
3
+ size 10524880634
neo_base/90e3/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a277fb48c0a1d2493607a77c81292356c67f9b2d62c7ff0d27fb67dba7fdfbdf
3
+ size 4993794184
neo_base/90e3/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83496f7df8d08e06a3dca26ceafd85b2b27c1e001a8624681b0eaf6be7f777f
3
+ size 268543784
neo_base/90e3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9244aa6be1ad677d38cc7dcbc901b03ca940e9636656ef6bea3f292db17a57
3
+ size 10524880634
neo_base/90e3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
neo_base/90e3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76418d30ac040e4524f2f1bd6133e4d7def40b257feaed4c1ae5c8aebe34738
3
+ size 1064
neo_base/90e3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
3
+ size 5240
neo_rmft/100e1/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bdfde6188ebad975afdee0c7f21a7f647ab157afe67747dbabc8bd5cda11eb
3
+ size 4993794184
neo_rmft/100e1/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367e88a80efd940f4149c42d282492827b0c8b985dcaebeed23a9dca323174fd
3
+ size 268543784
neo_rmft/100e1/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
neo_rmft/100e1/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81413103c95a73af29b3c5ae177bb9ed31a1328e8278d5d46954492c80a4b23
3
+ size 1064
neo_rmft/100e1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e31a4e3ac0bb851a7028c46df2d7183c611122494ba8af9bf1408f9d9238ffc
3
+ size 5240
neo_rmft/100e2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80de08dfa55e50ac88467bbd59ffe24633673a67ed8cd76f2bc8d4616f4cb3b
3
+ size 4993794184
neo_rmft/100e2/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfab22b4f01e2b8f57e91ac9d170676557a27679de0567a06756640fdcc76bd
3
+ size 268543784
neo_rmft/100e2/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
neo_rmft/100e2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6327ca6355944c6af085a0d7000a067db6861066fd69343664dddef8928b04ba
3
+ size 1064
neo_rmft/100e2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
neo_rmft/100e2/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": null,
20
+ "return_tensors": "pt",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
neo_rmft/100e2/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.984732824427481,
5
+ "eval_steps": 500,
6
+ "global_step": 1820,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5452562704471101,
13
+ "grad_norm": 1.3763982057571411,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.0251,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0905125408942202,
20
+ "grad_norm": 1.0297070741653442,
21
+ "learning_rate": 1.555752998667259e-05,
22
+ "loss": 1.7868,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.6357688113413305,
27
+ "grad_norm": 1.0274933576583862,
28
+ "learning_rate": 1.1115059973345181e-05,
29
+ "loss": 1.6506,
30
+ "step": 1500
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 2751,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 3,
37
+ "save_steps": 91,
38
+ "stateful_callbacks": {
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": false
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 1.3509608418784051e+17,
51
+ "train_batch_size": 80,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
neo_rmft/100e2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e31a4e3ac0bb851a7028c46df2d7183c611122494ba8af9bf1408f9d9238ffc
3
+ size 5240
neo_rmft/100e2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
neo_rmft/100e3/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "classifier_dropout": 0.1,
45
+ "embed_dropout": 0,
46
+ "eos_token_id": 50256,
47
+ "gradient_checkpointing": false,
48
+ "hidden_size": 2048,
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": null,
51
+ "layer_norm_epsilon": 1e-05,
52
+ "max_position_embeddings": 2048,
53
+ "model_type": "gpt_neo",
54
+ "num_heads": 16,
55
+ "num_layers": 24,
56
+ "resid_dropout": 0,
57
+ "summary_activation": null,
58
+ "summary_first_dropout": 0.1,
59
+ "summary_proj_to_labels": true,
60
+ "summary_type": "cls_index",
61
+ "summary_use_proj": true,
62
+ "task_specific_params": {
63
+ "text-generation": {
64
+ "do_sample": true,
65
+ "max_length": 50,
66
+ "temperature": 0.9
67
+ }
68
+ },
69
+ "tokenizer_class": "GPT2Tokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.46.3",
72
+ "use_cache": true,
73
+ "vocab_size": 50257,
74
+ "window_size": 256
75
+ }
neo_rmft/100e3/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.3"
6
+ }
neo_rmft/100e3/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
neo_rmft/100e3/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b63caa1ef54c1cb63548453b0fd736c6113e143f33387519ed40d8e05374f38
3
+ size 4993794184
neo_rmft/100e3/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed68fe26e458d6eb510a2d6a0a6051def41e2617a5e3b5fb359deee9b9bc34dc
3
+ size 268543784
neo_rmft/100e3/model.safetensors.index.json ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5262303232
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
18
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
42
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
43
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
44
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
66
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
67
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
68
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
70
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
81
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
83
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
90
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
91
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
92
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
94
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
96
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
97
+ "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
99
+ "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
103
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
105
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
107
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
109
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
116
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
117
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
118
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
119
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
120
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
121
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
122
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
123
+ "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
125
+ "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
126
+ "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
129
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
130
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
131
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
132
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
133
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
134
+ "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
135
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
138
+ "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
139
+ "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
140
+ "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
142
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
143
+ "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
144
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
145
+ "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
146
+ "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
147
+ "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
148
+ "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
151
+ "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
153
+ "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
159
+ "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
161
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
163
+ "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
164
+ "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
167
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
168
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
169
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
170
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
171
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
172
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
174
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
175
+ "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
177
+ "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
179
+ "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
181
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
182
+ "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
183
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
185
+ "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
187
+ "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
190
+ "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
191
+ "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
194
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
195
+ "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
196
+ "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
197
+ "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
198
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
199
+ "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
200
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
201
+ "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
203
+ "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
204
+ "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
207
+ "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
208
+ "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
209
+ "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
210
+ "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
211
+ "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
212
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
213
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
214
+ "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
215
+ "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
216
+ "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
217
+ "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
218
+ "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
219
+ "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
220
+ "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
221
+ "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
222
+ "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
223
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
224
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
225
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
226
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
227
+ "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
229
+ "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
230
+ "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
233
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
234
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
239
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
241
+ "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
242
+ "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
243
+ "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
245
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
246
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
247
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
248
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
249
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
250
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
251
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
252
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
253
+ "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
255
+ "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
257
+ "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
259
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
260
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
261
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
262
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
263
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
264
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
265
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
266
+ "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
268
+ "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
269
+ "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
272
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
273
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
274
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
275
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
276
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
277
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
278
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
279
+ "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
281
+ "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
282
+ "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
285
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
286
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
287
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
289
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
291
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
294
+ "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
295
+ "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
296
+ "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
298
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
299
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
300
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
301
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
302
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
303
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
304
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
305
+ "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
306
+ "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
307
+ "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
308
+ "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
309
+ "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
310
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
311
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
312
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
313
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
314
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
315
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
316
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
317
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
318
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
319
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
320
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
321
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
322
+ }
323
+ }
neo_rmft/100e3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
neo_rmft/100e3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7ef157c0715ba9c59766d5e7db37043b200ad21abd49b8c6b68987119e793e
3
+ size 1064
neo_rmft/100e3/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
neo_rmft/100e3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
neo_rmft/100e3/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": null,
20
+ "return_tensors": "pt",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
neo_rmft/100e3/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9770992366412212,
5
+ "eval_steps": 500,
6
+ "global_step": 2730,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5452562704471101,
13
+ "grad_norm": 1.3763982057571411,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.0251,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0905125408942202,
20
+ "grad_norm": 1.0297070741653442,
21
+ "learning_rate": 1.555752998667259e-05,
22
+ "loss": 1.7868,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.6357688113413305,
27
+ "grad_norm": 1.0274933576583862,
28
+ "learning_rate": 1.1115059973345181e-05,
29
+ "loss": 1.6506,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.1810250817884405,
34
+ "grad_norm": 1.0356584787368774,
35
+ "learning_rate": 6.67258996001777e-06,
36
+ "loss": 1.5884,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 2.7262813522355507,
41
+ "grad_norm": 0.9679080843925476,
42
+ "learning_rate": 2.23011994669036e-06,
43
+ "loss": 1.4998,
44
+ "step": 2500
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 2751,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 3,
51
+ "save_steps": 91,
52
+ "stateful_callbacks": {
53
+ "TrainerControl": {
54
+ "args": {
55
+ "should_epoch_stop": false,
56
+ "should_evaluate": false,
57
+ "should_log": false,
58
+ "should_save": true,
59
+ "should_training_stop": false
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 2.0262695655073382e+17,
65
+ "train_batch_size": 80,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
neo_rmft/100e3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e31a4e3ac0bb851a7028c46df2d7183c611122494ba8af9bf1408f9d9238ffc
3
+ size 5240
neo_rmft/100e3/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
neo_rmft/10e1/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "classifier_dropout": 0.1,
45
+ "embed_dropout": 0,
46
+ "eos_token_id": 50256,
47
+ "gradient_checkpointing": false,
48
+ "hidden_size": 2048,
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": null,
51
+ "layer_norm_epsilon": 1e-05,
52
+ "max_position_embeddings": 2048,
53
+ "model_type": "gpt_neo",
54
+ "num_heads": 16,
55
+ "num_layers": 24,
56
+ "resid_dropout": 0,
57
+ "summary_activation": null,
58
+ "summary_first_dropout": 0.1,
59
+ "summary_proj_to_labels": true,
60
+ "summary_type": "cls_index",
61
+ "summary_use_proj": true,
62
+ "task_specific_params": {
63
+ "text-generation": {
64
+ "do_sample": true,
65
+ "max_length": 50,
66
+ "temperature": 0.9
67
+ }
68
+ },
69
+ "tokenizer_class": "GPT2Tokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.46.3",
72
+ "use_cache": true,
73
+ "vocab_size": 50257,
74
+ "window_size": 256
75
+ }
neo_rmft/10e1/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.3"
6
+ }
neo_rmft/10e1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
neo_rmft/10e1/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392c335b6242a5e9e42447918a2153c744d339b73230976ea83664f21243bbd7
3
+ size 4993794184
neo_rmft/10e1/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2191b8210ed39f2dba76c84825f51ce4bdfa49d5c0221b766231f9d7c398172
3
+ size 268543784
neo_rmft/10e1/model.safetensors.index.json ADDED
@@ -0,0 +1,323 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5262303232
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
18
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
19
+ "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
21
+ "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
42
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
43
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
44
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
47
+ "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
66
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
67
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
68
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
70
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
81
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
83
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
90
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
91
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
92
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
94
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
96
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
97
+ "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
99
+ "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
103
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
104
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
105
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
107
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
109
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
116
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
117
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
118
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
119
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
120
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
121
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
122
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
123
+ "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
125
+ "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
126
+ "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
129
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
130
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
131
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
132
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
133
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
134
+ "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
135
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
138
+ "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
139
+ "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
140
+ "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
142
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
143
+ "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
144
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
145
+ "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
146
+ "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
147
+ "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
148
+ "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
151
+ "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
153
+ "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
159
+ "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
161
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
163
+ "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
164
+ "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
167
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
168
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
169
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
170
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
171
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
172
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
174
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
175
+ "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
177
+ "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
179
+ "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
181
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
182
+ "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
183
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
185
+ "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
187
+ "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
190
+ "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
191
+ "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
194
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
195
+ "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
196
+ "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
197
+ "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
198
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
199
+ "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
200
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
201
+ "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
203
+ "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
204
+ "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
207
+ "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
208
+ "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
209
+ "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
210
+ "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
211
+ "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
212
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
213
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
214
+ "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
215
+ "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
216
+ "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
217
+ "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
218
+ "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
219
+ "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
220
+ "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
221
+ "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
222
+ "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
223
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
224
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
225
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
226
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
227
+ "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
229
+ "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
230
+ "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
233
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
234
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
239
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
241
+ "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
242
+ "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
243
+ "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
245
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
246
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
247
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
248
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
249
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
250
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
251
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
252
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
253
+ "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
255
+ "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
257
+ "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
259
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
260
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
261
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
262
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
263
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
264
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
265
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
266
+ "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
268
+ "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
269
+ "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
272
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
273
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
274
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
275
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
276
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
277
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
278
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
279
+ "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
281
+ "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
282
+ "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
285
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
286
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
287
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
289
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
291
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
294
+ "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
295
+ "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
296
+ "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
298
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
299
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
300
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
301
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
302
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
303
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
304
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
305
+ "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
306
+ "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
307
+ "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
308
+ "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
309
+ "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
310
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
311
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
312
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
313
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
314
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
315
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
316
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
317
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
318
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
319
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
320
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
321
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
322
+ }
323
+ }
neo_rmft/10e1/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
neo_rmft/10e1/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993933d6d10b6b1e5b19bd1c832f93cdaeb08fccb50f75c056b086ad08264667
3
+ size 1064