igitman commited on
Commit
3249d1f
1 Parent(s): 80fb177

Add model files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. nemo_model/02464b0b96d640c4b06ea3cd770b2fd4_tokenizer.model +3 -0
  3. nemo_model/6bee419a805843c98fa9979dd8a12634_tokenizer.model +3 -0
  4. nemo_model/model_config.yaml +122 -0
  5. nemo_model/model_weights/common.pt +3 -0
  6. nemo_model/model_weights/metadata.json +3 -0
  7. nemo_model/model_weights/model.decoder.final_layernorm.weight/.zarray +3 -0
  8. nemo_model/model_weights/model.decoder.final_layernorm.weight/0 +3 -0
  9. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_0_48.pt +3 -0
  10. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_10_48.pt +3 -0
  11. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_11_48.pt +3 -0
  12. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_12_48.pt +3 -0
  13. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_13_48.pt +3 -0
  14. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_14_48.pt +3 -0
  15. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_15_48.pt +3 -0
  16. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_16_48.pt +3 -0
  17. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_17_48.pt +3 -0
  18. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_18_48.pt +3 -0
  19. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_19_48.pt +3 -0
  20. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_1_48.pt +3 -0
  21. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_20_48.pt +3 -0
  22. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_21_48.pt +3 -0
  23. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_22_48.pt +3 -0
  24. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_23_48.pt +3 -0
  25. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_24_48.pt +3 -0
  26. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_25_48.pt +3 -0
  27. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_26_48.pt +3 -0
  28. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_27_48.pt +3 -0
  29. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_28_48.pt +3 -0
  30. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_29_48.pt +3 -0
  31. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_2_48.pt +3 -0
  32. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_30_48.pt +3 -0
  33. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_31_48.pt +3 -0
  34. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_32_48.pt +3 -0
  35. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_33_48.pt +3 -0
  36. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_34_48.pt +3 -0
  37. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_35_48.pt +3 -0
  38. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_36_48.pt +3 -0
  39. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_37_48.pt +3 -0
  40. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_38_48.pt +3 -0
  41. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_39_48.pt +3 -0
  42. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_3_48.pt +3 -0
  43. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_40_48.pt +3 -0
  44. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_41_48.pt +3 -0
  45. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_42_48.pt +3 -0
  46. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_43_48.pt +3 -0
  47. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_44_48.pt +3 -0
  48. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_45_48.pt +3 -0
  49. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_46_48.pt +3 -0
  50. nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_47_48.pt +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ nemo_model/model_weights/** filter=lfs diff=lfs merge=lfs -text
nemo_model/02464b0b96d640c4b06ea3cd770b2fd4_tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
nemo_model/6bee419a805843c98fa9979dd8a12634_tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
nemo_model/model_config.yaml ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ mcore_gpt: true
2
+ micro_batch_size: 4
3
+ global_batch_size: 8
4
+ tensor_model_parallel_size: 1
5
+ pipeline_model_parallel_size: 1
6
+ virtual_pipeline_model_parallel_size: null
7
+ encoder_seq_length: 16384
8
+ max_position_embeddings: 16384
9
+ num_layers: 48
10
+ hidden_size: 8192
11
+ ffn_hidden_size: 22016
12
+ num_attention_heads: 64
13
+ init_method_std: 0.02
14
+ use_scaled_init_method: true
15
+ hidden_dropout: 0.0
16
+ attention_dropout: 0.0
17
+ ffn_dropout: 0.0
18
+ kv_channels: null
19
+ apply_query_key_layer_scaling: true
20
+ normalization: rmsnorm
21
+ layernorm_epsilon: 1.0e-05
22
+ do_layer_norm_weight_decay: false
23
+ make_vocab_size_divisible_by: 128
24
+ pre_process: true
25
+ post_process: true
26
+ persist_layer_norm: true
27
+ bias: false
28
+ activation: fast-swiglu
29
+ headscale: false
30
+ transformer_block_type: pre_ln
31
+ openai_gelu: false
32
+ normalize_attention_scores: true
33
+ position_embedding_type: rope
34
+ rotary_percentage: 1.0
35
+ attention_type: multihead
36
+ share_embeddings_and_output_weights: false
37
+ overlap_p2p_comm: false
38
+ batch_p2p_comm: true
39
+ num_query_groups: 8
40
+ tokenizer:
41
+ library: sentencepiece
42
+ type: null
43
+ model: nemo:02464b0b96d640c4b06ea3cd770b2fd4_tokenizer.model
44
+ vocab_file: null
45
+ merge_file: null
46
+ delimiter: null
47
+ sentencepiece_legacy: false
48
+ tokenizer_model: nemo:6bee419a805843c98fa9979dd8a12634_tokenizer.model
49
+ native_amp_init_scale: 4294967296
50
+ native_amp_growth_interval: 1000
51
+ hysteresis: 2
52
+ fp32_residual_connection: false
53
+ fp16_lm_cross_entropy: false
54
+ megatron_amp_O2: false
55
+ grad_allreduce_chunk_size_mb: 125
56
+ grad_div_ar_fusion: true
57
+ gradient_accumulation_fusion: false
58
+ bias_activation_fusion: false
59
+ bias_dropout_add_fusion: false
60
+ masked_softmax_fusion: true
61
+ get_attention_mask_from_fusion: true
62
+ seed: 1234
63
+ resume_from_checkpoint: null
64
+ use_cpu_initialization: false
65
+ onnx_safe: false
66
+ apex_transformer_log_level: 30
67
+ gradient_as_bucket_view: true
68
+ sync_batch_comm: false
69
+ activations_checkpoint_granularity: null
70
+ activations_checkpoint_method: null
71
+ activations_checkpoint_num_layers: null
72
+ num_micro_batches_with_partial_activation_checkpoints: null
73
+ activations_checkpoint_layers_per_pipeline: null
74
+ sequence_parallel: false
75
+ transformer_engine: true
76
+ fp8: false
77
+ fp8_e4m3: false
78
+ fp8_hybrid: false
79
+ fp8_margin: 0
80
+ fp8_interval: 1
81
+ fp8_amax_history_len: 1
82
+ fp8_amax_compute_algo: most_recent
83
+ reduce_amax: true
84
+ use_emha: false
85
+ data:
86
+ index_mapping_dir: null
87
+ data_impl: mmap
88
+ splits_string: 900,50,50
89
+ seq_length: 16384
90
+ skip_warmup: true
91
+ num_workers: 2
92
+ dataloader_type: single
93
+ reset_position_ids: false
94
+ reset_attention_mask: false
95
+ eod_mask_loss: false
96
+ validation_drop_last: true
97
+ no_seqlen_plus_one_input_tokens: false
98
+ pad_samples_to_global_batch_size: false
99
+ shuffle_documents: true
100
+ nsys_profile:
101
+ enabled: false
102
+ start_step: 10
103
+ end_step: 10
104
+ ranks:
105
+ - 0
106
+ gen_shape: false
107
+ optim:
108
+ name: fused_adam
109
+ lr: 0.0002
110
+ weight_decay: 0.01
111
+ betas:
112
+ - 0.9
113
+ - 0.98
114
+ sched:
115
+ name: CosineAnnealing
116
+ warmup_steps: 500
117
+ constant_steps: 50000
118
+ min_lr: 2.0e-05
119
+ precision: bf16
120
+ target: nemo.collections.nlp.models.language_modeling.megatron_gpt_model.MegatronGPTModel
121
+ nemo_version: 1.21.0
122
+ rotary_base: 1000000
nemo_model/model_weights/common.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f76b3dce7c5093ec2d3695b2941694e85e0dfe6360e80e33028ef64500f7195
3
+ size 25150
nemo_model/model_weights/metadata.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f502ab47c9b1fe00615afb88074d49cf6f9b4c85f482734543160c5cb2f76af9
3
+ size 113
nemo_model/model_weights/model.decoder.final_layernorm.weight/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a79a4a7e13f7d36fdbd516372f73511e69cb78cc03b3ab3b898e9d02f2013587
3
+ size 207
nemo_model/model_weights/model.decoder.final_layernorm.weight/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f348c2c4d32f72f8d72ce9cf08ff6f9466432beae73bb7e82d4862d994093e56
3
+ size 16384
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_0_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e336b599b42f4789116a85356ed4632fa498547bbbc018a69cc925d0e0f7b7
3
+ size 1836
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_10_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3598bef492cdb08c585f44bbc509448854a5ded1e915d6c93cfc3edd9c6fece
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_11_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2453d57195cd918d7979190f9080037e865cf1516bf7fa321bc5ae0aa43a64
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_12_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f6c8931009b6c45c260912f49dabdb86c950ac54162f38b1836dea0d948540
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_13_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23ee7c2c8aa3b484fa61e8be4f14d224da3d1fcf7c4fcde4c55bc1386fe3e76
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_14_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb15ca9db86f4ca8d94433728afb41db35dcbf9f6af87ff0e2dd3316008a3d5a
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_15_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2128bfdfc1004dd86acf2b6644047ce68c49e1f36dc17867324ebc4dbe2599d2
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_16_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a31958150bcc7b0c81f7dcf783986a63f146cedc4f70598ac4989bf7f0ffea6
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_17_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5e6100b481e1829af26af49244a29fa59e03c9a3223e1779ec9086359a76bb
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_18_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bc3e77147df92b000fe370714530c0f8ea7170eec17275edef0a976caf872d
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_19_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d486d40f550a197ee7a6fe5ac9faff818c78662467facfb389809d7a55dc8de
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_1_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c831ae32b8aa18cadef5f7b184d122cc59146d5c3ddc585c7462949f941ae0dc
3
+ size 1836
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_20_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:184970634e18c83d4300822759383ffefd0b7dbe4bcffe1114a1867b44199357
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_21_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47140ce58486538eb658766f56f0378b4c2cc7d2594f486575b6f0da2c7642cd
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_22_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22526dc04cee98c943fb0337472822f061eda220f08461548efa66819650e89f
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_23_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a240b9dabe3d5d69a1ceb154d34e0078e8c94a6b95ca065bdbe7a5e9be178594
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_24_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdfd0cf9d55e3bf88027fadb69dd7deb17153a9e278f9ea79da5a65d952ff731
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_25_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6160b8e92e045c7469e7f23f04fd5e54f2db40a82f9ba037adb1e3ba9ade924
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_26_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78626061394c35dd655499720f08cd9f629371316d816525452d6429b2390fa
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_27_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ccf5296ff27bf83dfd5d1865b587f5a35579e515f329f6b3f54577811b600d
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_28_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78794f13a82ea89e2521d9e40b48b546377ccad8c45a8ba5c80cc0c960fdfad
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_29_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12232392f59f5c9f60b7861c6de2701288e1e177ac606a4e7f23c16846d7593a
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_2_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec38adac32c846177e2483ceb27c0bba9a2a4bb395682a18543ccbab98536a9
3
+ size 1836
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_30_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6054011df6a1db7e3f034da581c11d17f364476bab2d1dd01e3f0f3427e815
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_31_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9172bb94e946db4d20ff8f1df4450df81d9bd0a086becd57eaa687371b84a7
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_32_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45df07ab43caec460fa5ce1d5161c696dfe5e66a4d40aab6d64d9a6ac9341609
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_33_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a210333bfd137302bf8d25441e1621f957c2accfdd86be33291457710177475
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_34_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b016b1d2c6f2a6b2d825482cc5e9a9235f39601d3b8bf0a6765e38a307c8712
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_35_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab9345c1f363137f28fe59591e0a21b9ab5452ea793e2a60d433986c069b019
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_36_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff76edd3d3bc0e3d0740f186bd89fb3f62908ff223011d02002f293cd47a404b
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_37_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9c16e201d81332768733290d18681ec1ff91a4c37a7e68253a77645686826e
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_38_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107ff2c3079aabae927ab83a0ea3ff3d81ee7ada95b77fd78350d69e90ddf4dd
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_39_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad334531054f84daded64229e3d94ab3d1e70f7cde7e9bbf0c489b2d8bdde2a1
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_3_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c49572def7fb6f562aea95e4d9f75294ce22b207eb967b6b4c3071fa11b451
3
+ size 1836
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_40_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00a0243ef5f6e2bc55fff640460ad6cbfac20f0f48823b5fffeb00f1404b92a
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_41_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a75892ee0e23763e3106a9fde3e2d686617b1efb86060b5bc5e409b73c1c3ba
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_42_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6694fdeb0828d2b6a730eee89d7294876d96bb25914b8de865f5243dffc61524
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_43_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f517119bc78ae610542e3d8a6db9e1fb6aff392eee8c0b55d4d1a1d4ea93c3
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_44_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec93dd708d61ef20fe24ccf83647b00bf09826b646ad61db6f0ce5fe00ae909
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_45_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33657ed3335a88c7577d5699856df704151211b3339817fe05919d9a0c6cac2
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_46_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f343e3916cd839ed8f5688e0407689cf2ee11d4edc2bef562122f426f30b88
3
+ size 1840
nemo_model/model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_47_48.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7c969607d43a2a412536bdb38e545c3fc68d5ede0a4bf9776620c4c660fca1
3
+ size 1840