Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-342/config.json +29 -0
- checkpoint-342/generation_config.json +6 -0
- checkpoint-342/global_step342/mp_rank_00_model_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/global_step342/zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- checkpoint-342/latest +1 -0
- checkpoint-342/pytorch_model-00001-of-00005.bin +3 -0
- checkpoint-342/pytorch_model-00002-of-00005.bin +3 -0
- checkpoint-342/pytorch_model-00003-of-00005.bin +3 -0
- checkpoint-342/pytorch_model-00004-of-00005.bin +3 -0
- checkpoint-342/pytorch_model-00005-of-00005.bin +3 -0
- checkpoint-342/pytorch_model.bin.index.json +479 -0
- checkpoint-342/rng_state_0.pth +3 -0
- checkpoint-342/rng_state_1.pth +3 -0
- checkpoint-342/rng_state_2.pth +3 -0
- checkpoint-342/rng_state_3.pth +3 -0
- checkpoint-342/rng_state_4.pth +3 -0
- checkpoint-342/rng_state_5.pth +3 -0
- checkpoint-342/rng_state_6.pth +3 -0
- checkpoint-342/rng_state_7.pth +3 -0
- checkpoint-342/special_tokens_map.json +14 -0
- checkpoint-342/tokenizer.json +0 -0
- checkpoint-342/tokenizer_config.json +9 -0
- checkpoint-342/trainer_state.json +526 -0
- checkpoint-342/training_args.bin +3 -0
- checkpoint-342/zero_to_fp32.py +578 -0
- checkpoint-513/config.json +29 -0
- checkpoint-513/generation_config.json +6 -0
- checkpoint-513/global_step513/mp_rank_00_model_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/global_step513/zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- checkpoint-513/latest +1 -0
- checkpoint-513/pytorch_model-00001-of-00005.bin +3 -0
- checkpoint-513/pytorch_model-00002-of-00005.bin +3 -0
- checkpoint-513/pytorch_model-00003-of-00005.bin +3 -0
- checkpoint-513/pytorch_model-00004-of-00005.bin +3 -0
- checkpoint-513/pytorch_model-00005-of-00005.bin +3 -0
- checkpoint-513/pytorch_model.bin.index.json +479 -0
checkpoint-342/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "toanbku/oa-pythia-12b-rlhf-df",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": 0.1,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 5120,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 20480,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"model_type": "gpt_neox",
|
18 |
+
"num_attention_heads": 40,
|
19 |
+
"num_hidden_layers": 36,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rotary_emb_base": 10000,
|
22 |
+
"rotary_pct": 0.25,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.31.0.dev0",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_parallel_residual": true,
|
28 |
+
"vocab_size": 50288
|
29 |
+
}
|
checkpoint-342/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.31.0.dev0"
|
6 |
+
}
|
checkpoint-342/global_step342/mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55bdd1476345c2f04a842ffb43ac564728d467e0746c508ef61375fa392a97fd
|
3 |
+
size 23684097854
|
checkpoint-342/global_step342/zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9f1b055d7d4991d58c7066cb8c93a71c3e5217f9ff6707d55869ffdb342c46
|
3 |
+
size 17762971806
|
checkpoint-342/global_step342/zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e990b6cff16b4612332a3a4cd8be00e5ee189d7edc3a11b9634946d166625096
|
3 |
+
size 17762972766
|
checkpoint-342/global_step342/zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d7859d2475aaea2d6b5b1056f9b1cef319b0b3856df1f948b428bf871287e8d
|
3 |
+
size 17762972766
|
checkpoint-342/global_step342/zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5ec63440900ca51c1919e35f92345bfd52a53c2e803254d243369789f867215
|
3 |
+
size 17762972446
|
checkpoint-342/global_step342/zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a6c23d414f9cb60d13bf9e0f80a99d1baf375fdc8bf4639361d165d4ef6ef3
|
3 |
+
size 17762972702
|
checkpoint-342/global_step342/zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56227481180a90df9fdbc784417e5b4058f1257f2358c50c865132c339429c74
|
3 |
+
size 17762972830
|
checkpoint-342/global_step342/zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eb87993b7e48d14f815055e40d35508c196304312ed96d470669d047614a82b
|
3 |
+
size 17762972638
|
checkpoint-342/global_step342/zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00305e46139b956fc56b3dca838cb481fe07b38c89bb7ed9ca98fe81c47908bd
|
3 |
+
size 17762971742
|
checkpoint-342/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step342
|
checkpoint-342/pytorch_model-00001-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dff00c45af3df3e650643894523894bdaf898f00a402f6b88345c3de17aef50
|
3 |
+
size 9839916213
|
checkpoint-342/pytorch_model-00002-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eeecbb8d8adaf51731db56963f6444b61f4df464b8c2b90c172f130f0ce2d20
|
3 |
+
size 9648960597
|
checkpoint-342/pytorch_model-00003-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d9c11cc8272e808861f36c50e02fc766d5bef655773eb9035f5e75deb7a05e8
|
3 |
+
size 9648982897
|
checkpoint-342/pytorch_model-00004-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cf69fc06344395b471cf37f74c1828b6e2d4db9013ffcd726f43be5ae581bf8
|
3 |
+
size 9963617221
|
checkpoint-342/pytorch_model-00005-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcffc30bb91af54f63b9540ccc0f669eacda4d48327d015c0bdb353c16f7c587
|
3 |
+
size 8266593363
|
checkpoint-342/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,479 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 47367907584
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"embed_out.weight": "pytorch_model-00005-of-00005.bin",
|
7 |
+
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00005.bin",
|
8 |
+
"gpt_neox.final_layer_norm.bias": "pytorch_model-00005-of-00005.bin",
|
9 |
+
"gpt_neox.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
|
10 |
+
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
11 |
+
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
12 |
+
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
13 |
+
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
14 |
+
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
15 |
+
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
16 |
+
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
17 |
+
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
18 |
+
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
19 |
+
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
20 |
+
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
21 |
+
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
22 |
+
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
23 |
+
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
24 |
+
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
25 |
+
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
26 |
+
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
27 |
+
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
28 |
+
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
29 |
+
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
30 |
+
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
31 |
+
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
32 |
+
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
33 |
+
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
34 |
+
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
35 |
+
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
36 |
+
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
37 |
+
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
38 |
+
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
39 |
+
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
40 |
+
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
41 |
+
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
42 |
+
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
43 |
+
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
44 |
+
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
45 |
+
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
46 |
+
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
47 |
+
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
48 |
+
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
49 |
+
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
50 |
+
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
51 |
+
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
52 |
+
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
53 |
+
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
54 |
+
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
55 |
+
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
56 |
+
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
57 |
+
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
58 |
+
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
59 |
+
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
60 |
+
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
61 |
+
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
62 |
+
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
63 |
+
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
64 |
+
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
65 |
+
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
66 |
+
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
67 |
+
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
68 |
+
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
69 |
+
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
70 |
+
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
71 |
+
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
72 |
+
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
73 |
+
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
74 |
+
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
75 |
+
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
76 |
+
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
77 |
+
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
78 |
+
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
79 |
+
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
80 |
+
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
81 |
+
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
82 |
+
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
83 |
+
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
84 |
+
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
85 |
+
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
86 |
+
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
87 |
+
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
88 |
+
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
89 |
+
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
90 |
+
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
91 |
+
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
92 |
+
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
93 |
+
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
94 |
+
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
95 |
+
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
96 |
+
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
97 |
+
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
98 |
+
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
99 |
+
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
100 |
+
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
101 |
+
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
102 |
+
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
103 |
+
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
104 |
+
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
105 |
+
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
106 |
+
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
107 |
+
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
108 |
+
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
109 |
+
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
110 |
+
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
111 |
+
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
112 |
+
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
113 |
+
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
114 |
+
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
115 |
+
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
116 |
+
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
117 |
+
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
118 |
+
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
119 |
+
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
120 |
+
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
121 |
+
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
122 |
+
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
123 |
+
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
124 |
+
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
125 |
+
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
126 |
+
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
127 |
+
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
128 |
+
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
129 |
+
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
130 |
+
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
131 |
+
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
132 |
+
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
133 |
+
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
134 |
+
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
135 |
+
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
136 |
+
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
137 |
+
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
138 |
+
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
139 |
+
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
140 |
+
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
141 |
+
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
142 |
+
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
143 |
+
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
144 |
+
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
145 |
+
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
146 |
+
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
147 |
+
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
148 |
+
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
149 |
+
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
150 |
+
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
151 |
+
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
152 |
+
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
153 |
+
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
154 |
+
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
155 |
+
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
156 |
+
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
157 |
+
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
158 |
+
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
159 |
+
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
160 |
+
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
161 |
+
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
162 |
+
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
163 |
+
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
164 |
+
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
165 |
+
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
166 |
+
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
167 |
+
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
168 |
+
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
169 |
+
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
170 |
+
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
171 |
+
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
172 |
+
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
173 |
+
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
174 |
+
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
175 |
+
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
176 |
+
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
177 |
+
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
178 |
+
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
179 |
+
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
180 |
+
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
181 |
+
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
182 |
+
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
183 |
+
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
184 |
+
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
185 |
+
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
186 |
+
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
187 |
+
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
188 |
+
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
189 |
+
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
190 |
+
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
191 |
+
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
192 |
+
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
193 |
+
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
194 |
+
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
195 |
+
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
196 |
+
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
197 |
+
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
198 |
+
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
199 |
+
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
200 |
+
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
201 |
+
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
202 |
+
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
203 |
+
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
204 |
+
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
205 |
+
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
206 |
+
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
207 |
+
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
208 |
+
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
209 |
+
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
210 |
+
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
211 |
+
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
212 |
+
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
213 |
+
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
214 |
+
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
215 |
+
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
216 |
+
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
217 |
+
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
218 |
+
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
219 |
+
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
220 |
+
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
221 |
+
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
222 |
+
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
223 |
+
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
224 |
+
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
225 |
+
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
226 |
+
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
227 |
+
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
228 |
+
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
229 |
+
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
230 |
+
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
231 |
+
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
232 |
+
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
233 |
+
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
234 |
+
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
235 |
+
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
236 |
+
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
237 |
+
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
238 |
+
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
239 |
+
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
240 |
+
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
241 |
+
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
242 |
+
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
243 |
+
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
244 |
+
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
245 |
+
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
246 |
+
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
247 |
+
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
248 |
+
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
249 |
+
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
250 |
+
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
251 |
+
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
252 |
+
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
253 |
+
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
254 |
+
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
255 |
+
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
256 |
+
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
257 |
+
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
258 |
+
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
259 |
+
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
260 |
+
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
261 |
+
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
262 |
+
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
263 |
+
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
264 |
+
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
265 |
+
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
266 |
+
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
267 |
+
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
268 |
+
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
269 |
+
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
270 |
+
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
271 |
+
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
272 |
+
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
273 |
+
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
274 |
+
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
275 |
+
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
276 |
+
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
277 |
+
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
278 |
+
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
279 |
+
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
280 |
+
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
281 |
+
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
282 |
+
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
283 |
+
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
284 |
+
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
285 |
+
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
286 |
+
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
287 |
+
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
288 |
+
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
289 |
+
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
290 |
+
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
291 |
+
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
292 |
+
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
293 |
+
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
294 |
+
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
295 |
+
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
296 |
+
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
297 |
+
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
298 |
+
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
299 |
+
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
300 |
+
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
301 |
+
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
302 |
+
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
303 |
+
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
304 |
+
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
305 |
+
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
306 |
+
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
307 |
+
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
308 |
+
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
309 |
+
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
310 |
+
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
311 |
+
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
312 |
+
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
313 |
+
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
314 |
+
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
315 |
+
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
316 |
+
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
317 |
+
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
318 |
+
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
319 |
+
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
320 |
+
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
321 |
+
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
322 |
+
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
323 |
+
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
324 |
+
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
325 |
+
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
326 |
+
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
327 |
+
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
328 |
+
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
329 |
+
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
330 |
+
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
331 |
+
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
332 |
+
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
333 |
+
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
334 |
+
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
335 |
+
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
336 |
+
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
337 |
+
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
338 |
+
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
339 |
+
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
340 |
+
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
341 |
+
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
342 |
+
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
343 |
+
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
344 |
+
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
345 |
+
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
346 |
+
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
347 |
+
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
348 |
+
"gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
349 |
+
"gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
350 |
+
"gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
351 |
+
"gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
352 |
+
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
353 |
+
"gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
354 |
+
"gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
355 |
+
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
356 |
+
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
357 |
+
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
358 |
+
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
359 |
+
"gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
360 |
+
"gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
361 |
+
"gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
362 |
+
"gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
363 |
+
"gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
364 |
+
"gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
365 |
+
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
366 |
+
"gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
367 |
+
"gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
368 |
+
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
369 |
+
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
370 |
+
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
371 |
+
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
372 |
+
"gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
373 |
+
"gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
374 |
+
"gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
375 |
+
"gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
376 |
+
"gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
377 |
+
"gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
378 |
+
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
379 |
+
"gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
380 |
+
"gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
381 |
+
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
382 |
+
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
383 |
+
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
384 |
+
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
385 |
+
"gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
386 |
+
"gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
387 |
+
"gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
388 |
+
"gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
389 |
+
"gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
390 |
+
"gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
391 |
+
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
392 |
+
"gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
393 |
+
"gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
394 |
+
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
395 |
+
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
396 |
+
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
397 |
+
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
398 |
+
"gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
399 |
+
"gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
400 |
+
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
401 |
+
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
402 |
+
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
403 |
+
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
404 |
+
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
405 |
+
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
406 |
+
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
407 |
+
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
408 |
+
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
409 |
+
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
410 |
+
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
411 |
+
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
412 |
+
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
413 |
+
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
414 |
+
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
415 |
+
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
416 |
+
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
417 |
+
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
418 |
+
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
419 |
+
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
420 |
+
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
421 |
+
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
422 |
+
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
423 |
+
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
424 |
+
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
425 |
+
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
426 |
+
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
427 |
+
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
428 |
+
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
429 |
+
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
430 |
+
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
431 |
+
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
432 |
+
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
433 |
+
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
434 |
+
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
435 |
+
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
436 |
+
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
437 |
+
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
438 |
+
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
439 |
+
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
440 |
+
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
441 |
+
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
442 |
+
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
443 |
+
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
444 |
+
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
445 |
+
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
446 |
+
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
447 |
+
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
448 |
+
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
449 |
+
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
450 |
+
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
451 |
+
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
452 |
+
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
453 |
+
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
454 |
+
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
455 |
+
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
456 |
+
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
457 |
+
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
458 |
+
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
459 |
+
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
460 |
+
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
461 |
+
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
462 |
+
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
463 |
+
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
464 |
+
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
465 |
+
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
466 |
+
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
467 |
+
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
468 |
+
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
469 |
+
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
470 |
+
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
471 |
+
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
472 |
+
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
473 |
+
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
474 |
+
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
475 |
+
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
476 |
+
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
477 |
+
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin"
|
478 |
+
}
|
479 |
+
}
|
checkpoint-342/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7627a4adf319d8b3560071c74ece8be9b66a0992b0472b04ced3306a7a3e51a1
|
3 |
+
size 21623
|
checkpoint-342/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:633074840bb9fdb66ade01ef38767085a06a413a9fdc9cef4f3ae65fa90eead0
|
3 |
+
size 21623
|
checkpoint-342/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5e95e1661b4b4eeaa074607d4189adb1774e66e7bd55da196323d897919a95a
|
3 |
+
size 21623
|
checkpoint-342/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56238fa338ce9ef74d74fc101050f9d039163f6560c23a5e82249053377f2b9a
|
3 |
+
size 21623
|
checkpoint-342/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e40a0070b17b7832a9830020e66cff56f4570d0449d5ff9b85e0bc82fe22e513
|
3 |
+
size 21623
|
checkpoint-342/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d5c0f5081eebeb8196e230a6a40c33e915e2c4f8fb504923a0f35702ed012de
|
3 |
+
size 21623
|
checkpoint-342/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:117dd360c36456343804c467246c92bd880afd134fea1b85648b60401a37ff2f
|
3 |
+
size 21623
|
checkpoint-342/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61c395ed5b2a3aa084d3353a1644d8d5c58603e2c4ca3b6eb41ca368333e44a5
|
3 |
+
size 21623
|
checkpoint-342/special_tokens_map.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|prefix_begin|>",
|
4 |
+
"<|prefix_end|>",
|
5 |
+
"<|prompter|>",
|
6 |
+
"<|assistant|>",
|
7 |
+
"<|system|>"
|
8 |
+
],
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"eos_token": "<|endoftext|>",
|
11 |
+
"pad_token": "<|padding|>",
|
12 |
+
"sep_token": "<|endoftext|>",
|
13 |
+
"unk_token": "<|endoftext|>"
|
14 |
+
}
|
checkpoint-342/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-342/tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
checkpoint-342/trainer_state.json
ADDED
@@ -0,0 +1,526 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 342,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.06,
|
12 |
+
"learning_rate": 5.917808219178082e-06,
|
13 |
+
"loss": 0.0322,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"eval_oasst_export_accuracy": 0.49051699074786653,
|
19 |
+
"eval_oasst_export_loss": 3.484375,
|
20 |
+
"eval_oasst_export_runtime": 6.0372,
|
21 |
+
"eval_oasst_export_samples_per_second": 181.21,
|
22 |
+
"eval_oasst_export_steps_per_second": 2.982,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12,
|
27 |
+
"learning_rate": 5.800391389432485e-06,
|
28 |
+
"loss": 0.0246,
|
29 |
+
"step": 20
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.12,
|
33 |
+
"eval_oasst_export_accuracy": 0.489678997143981,
|
34 |
+
"eval_oasst_export_loss": 3.779296875,
|
35 |
+
"eval_oasst_export_runtime": 6.056,
|
36 |
+
"eval_oasst_export_samples_per_second": 180.647,
|
37 |
+
"eval_oasst_export_steps_per_second": 2.972,
|
38 |
+
"step": 20
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.18,
|
42 |
+
"learning_rate": 5.682974559686888e-06,
|
43 |
+
"loss": 0.0203,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.18,
|
48 |
+
"eval_oasst_export_accuracy": 0.4914062900826022,
|
49 |
+
"eval_oasst_export_loss": 3.734375,
|
50 |
+
"eval_oasst_export_runtime": 6.0349,
|
51 |
+
"eval_oasst_export_samples_per_second": 181.279,
|
52 |
+
"eval_oasst_export_steps_per_second": 2.983,
|
53 |
+
"step": 30
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.23,
|
57 |
+
"learning_rate": 5.565557729941292e-06,
|
58 |
+
"loss": 0.0187,
|
59 |
+
"step": 40
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.23,
|
63 |
+
"eval_oasst_export_accuracy": 0.4879859080259265,
|
64 |
+
"eval_oasst_export_loss": 3.7109375,
|
65 |
+
"eval_oasst_export_runtime": 6.0607,
|
66 |
+
"eval_oasst_export_samples_per_second": 180.508,
|
67 |
+
"eval_oasst_export_steps_per_second": 2.97,
|
68 |
+
"step": 40
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.29,
|
72 |
+
"learning_rate": 5.448140900195694e-06,
|
73 |
+
"loss": 0.0162,
|
74 |
+
"step": 50
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.29,
|
78 |
+
"eval_oasst_export_accuracy": 0.4880030099362099,
|
79 |
+
"eval_oasst_export_loss": 3.783203125,
|
80 |
+
"eval_oasst_export_runtime": 6.0304,
|
81 |
+
"eval_oasst_export_samples_per_second": 181.415,
|
82 |
+
"eval_oasst_export_steps_per_second": 2.985,
|
83 |
+
"step": 50
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.35,
|
87 |
+
"learning_rate": 5.330724070450098e-06,
|
88 |
+
"loss": 0.0159,
|
89 |
+
"step": 60
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.35,
|
93 |
+
"eval_oasst_export_accuracy": 0.486292818907872,
|
94 |
+
"eval_oasst_export_loss": 3.7890625,
|
95 |
+
"eval_oasst_export_runtime": 6.0367,
|
96 |
+
"eval_oasst_export_samples_per_second": 181.224,
|
97 |
+
"eval_oasst_export_steps_per_second": 2.982,
|
98 |
+
"step": 60
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.41,
|
102 |
+
"learning_rate": 5.213307240704501e-06,
|
103 |
+
"loss": 0.0172,
|
104 |
+
"step": 70
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.41,
|
108 |
+
"eval_oasst_export_accuracy": 0.48716501633232434,
|
109 |
+
"eval_oasst_export_loss": 3.806640625,
|
110 |
+
"eval_oasst_export_runtime": 6.0405,
|
111 |
+
"eval_oasst_export_samples_per_second": 181.11,
|
112 |
+
"eval_oasst_export_steps_per_second": 2.98,
|
113 |
+
"step": 70
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.47,
|
117 |
+
"learning_rate": 5.095890410958904e-06,
|
118 |
+
"loss": 0.0157,
|
119 |
+
"step": 80
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.47,
|
123 |
+
"eval_oasst_export_accuracy": 0.48454842405896736,
|
124 |
+
"eval_oasst_export_loss": 3.791015625,
|
125 |
+
"eval_oasst_export_runtime": 6.0411,
|
126 |
+
"eval_oasst_export_samples_per_second": 181.092,
|
127 |
+
"eval_oasst_export_steps_per_second": 2.98,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.53,
|
132 |
+
"learning_rate": 4.978473581213307e-06,
|
133 |
+
"loss": 0.0163,
|
134 |
+
"step": 90
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.53,
|
138 |
+
"eval_oasst_export_accuracy": 0.49138918817231886,
|
139 |
+
"eval_oasst_export_loss": 3.822265625,
|
140 |
+
"eval_oasst_export_runtime": 5.6229,
|
141 |
+
"eval_oasst_export_samples_per_second": 194.561,
|
142 |
+
"eval_oasst_export_steps_per_second": 3.201,
|
143 |
+
"step": 90
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.58,
|
147 |
+
"learning_rate": 4.86105675146771e-06,
|
148 |
+
"loss": 0.0139,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.58,
|
153 |
+
"eval_oasst_export_accuracy": 0.4956817676534469,
|
154 |
+
"eval_oasst_export_loss": 3.826171875,
|
155 |
+
"eval_oasst_export_runtime": 6.0223,
|
156 |
+
"eval_oasst_export_samples_per_second": 181.659,
|
157 |
+
"eval_oasst_export_steps_per_second": 2.989,
|
158 |
+
"step": 100
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.64,
|
162 |
+
"learning_rate": 4.7436399217221134e-06,
|
163 |
+
"loss": 0.0151,
|
164 |
+
"step": 110
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.64,
|
168 |
+
"eval_oasst_export_accuracy": 0.4845655259692508,
|
169 |
+
"eval_oasst_export_loss": 3.904296875,
|
170 |
+
"eval_oasst_export_runtime": 6.0257,
|
171 |
+
"eval_oasst_export_samples_per_second": 181.554,
|
172 |
+
"eval_oasst_export_steps_per_second": 2.987,
|
173 |
+
"step": 110
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.7,
|
177 |
+
"learning_rate": 4.626223091976516e-06,
|
178 |
+
"loss": 0.0139,
|
179 |
+
"step": 120
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.7,
|
183 |
+
"eval_oasst_export_accuracy": 0.49049988883758316,
|
184 |
+
"eval_oasst_export_loss": 3.958984375,
|
185 |
+
"eval_oasst_export_runtime": 6.0136,
|
186 |
+
"eval_oasst_export_samples_per_second": 181.92,
|
187 |
+
"eval_oasst_export_steps_per_second": 2.993,
|
188 |
+
"step": 120
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.76,
|
192 |
+
"learning_rate": 4.50880626223092e-06,
|
193 |
+
"loss": 0.0133,
|
194 |
+
"step": 130
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.76,
|
198 |
+
"eval_oasst_export_accuracy": 0.4803413541292562,
|
199 |
+
"eval_oasst_export_loss": 3.845703125,
|
200 |
+
"eval_oasst_export_runtime": 6.0221,
|
201 |
+
"eval_oasst_export_samples_per_second": 181.663,
|
202 |
+
"eval_oasst_export_steps_per_second": 2.989,
|
203 |
+
"step": 130
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.82,
|
207 |
+
"learning_rate": 4.3913894324853226e-06,
|
208 |
+
"loss": 0.0142,
|
209 |
+
"step": 140
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.82,
|
213 |
+
"eval_oasst_export_accuracy": 0.4777076599456159,
|
214 |
+
"eval_oasst_export_loss": 3.828125,
|
215 |
+
"eval_oasst_export_runtime": 6.0368,
|
216 |
+
"eval_oasst_export_samples_per_second": 181.223,
|
217 |
+
"eval_oasst_export_steps_per_second": 2.982,
|
218 |
+
"step": 140
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.88,
|
222 |
+
"learning_rate": 4.273972602739726e-06,
|
223 |
+
"loss": 0.0141,
|
224 |
+
"step": 150
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.88,
|
228 |
+
"eval_oasst_export_accuracy": 0.47088399774254786,
|
229 |
+
"eval_oasst_export_loss": 3.998046875,
|
230 |
+
"eval_oasst_export_runtime": 6.0502,
|
231 |
+
"eval_oasst_export_samples_per_second": 180.82,
|
232 |
+
"eval_oasst_export_steps_per_second": 2.975,
|
233 |
+
"step": 150
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.94,
|
237 |
+
"learning_rate": 4.156555772994129e-06,
|
238 |
+
"loss": 0.0157,
|
239 |
+
"step": 160
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.94,
|
243 |
+
"eval_oasst_export_accuracy": 0.4726796983223026,
|
244 |
+
"eval_oasst_export_loss": 3.8828125,
|
245 |
+
"eval_oasst_export_runtime": 5.995,
|
246 |
+
"eval_oasst_export_samples_per_second": 182.487,
|
247 |
+
"eval_oasst_export_steps_per_second": 3.003,
|
248 |
+
"step": 160
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.99,
|
252 |
+
"learning_rate": 4.0391389432485325e-06,
|
253 |
+
"loss": 0.0139,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.99,
|
258 |
+
"eval_oasst_export_accuracy": 0.4744240931712072,
|
259 |
+
"eval_oasst_export_loss": 3.9609375,
|
260 |
+
"eval_oasst_export_runtime": 6.0696,
|
261 |
+
"eval_oasst_export_samples_per_second": 180.244,
|
262 |
+
"eval_oasst_export_steps_per_second": 2.966,
|
263 |
+
"step": 170
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.05,
|
267 |
+
"learning_rate": 3.921722113502935e-06,
|
268 |
+
"loss": 0.0125,
|
269 |
+
"step": 180
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.05,
|
273 |
+
"eval_oasst_export_accuracy": 0.48210285088844423,
|
274 |
+
"eval_oasst_export_loss": 4.03125,
|
275 |
+
"eval_oasst_export_runtime": 5.616,
|
276 |
+
"eval_oasst_export_samples_per_second": 194.8,
|
277 |
+
"eval_oasst_export_steps_per_second": 3.205,
|
278 |
+
"step": 180
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.11,
|
282 |
+
"learning_rate": 3.8043052837573385e-06,
|
283 |
+
"loss": 0.017,
|
284 |
+
"step": 190
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.11,
|
288 |
+
"eval_oasst_export_accuracy": 0.4897303028748311,
|
289 |
+
"eval_oasst_export_loss": 3.970703125,
|
290 |
+
"eval_oasst_export_runtime": 6.03,
|
291 |
+
"eval_oasst_export_samples_per_second": 181.426,
|
292 |
+
"eval_oasst_export_steps_per_second": 2.985,
|
293 |
+
"step": 190
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.17,
|
297 |
+
"learning_rate": 3.6868884540117416e-06,
|
298 |
+
"loss": 0.0137,
|
299 |
+
"step": 200
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.17,
|
303 |
+
"eval_oasst_export_accuracy": 0.4794862586150873,
|
304 |
+
"eval_oasst_export_loss": 3.986328125,
|
305 |
+
"eval_oasst_export_runtime": 6.0192,
|
306 |
+
"eval_oasst_export_samples_per_second": 181.751,
|
307 |
+
"eval_oasst_export_steps_per_second": 2.99,
|
308 |
+
"step": 200
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.23,
|
312 |
+
"learning_rate": 3.569471624266145e-06,
|
313 |
+
"loss": 0.0133,
|
314 |
+
"step": 210
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.23,
|
318 |
+
"eval_oasst_export_accuracy": 0.47693807398286386,
|
319 |
+
"eval_oasst_export_loss": 4.140625,
|
320 |
+
"eval_oasst_export_runtime": 6.0148,
|
321 |
+
"eval_oasst_export_samples_per_second": 181.886,
|
322 |
+
"eval_oasst_export_steps_per_second": 2.993,
|
323 |
+
"step": 210
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.29,
|
327 |
+
"learning_rate": 3.452054794520548e-06,
|
328 |
+
"loss": 0.0133,
|
329 |
+
"step": 220
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 1.29,
|
333 |
+
"eval_oasst_export_accuracy": 0.48713081251175755,
|
334 |
+
"eval_oasst_export_loss": 4.1484375,
|
335 |
+
"eval_oasst_export_runtime": 6.0347,
|
336 |
+
"eval_oasst_export_samples_per_second": 181.285,
|
337 |
+
"eval_oasst_export_steps_per_second": 2.983,
|
338 |
+
"step": 220
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.35,
|
342 |
+
"learning_rate": 3.334637964774951e-06,
|
343 |
+
"loss": 0.0154,
|
344 |
+
"step": 230
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.35,
|
348 |
+
"eval_oasst_export_accuracy": 0.4752620867750928,
|
349 |
+
"eval_oasst_export_loss": 4.09375,
|
350 |
+
"eval_oasst_export_runtime": 5.6373,
|
351 |
+
"eval_oasst_export_samples_per_second": 194.065,
|
352 |
+
"eval_oasst_export_steps_per_second": 3.193,
|
353 |
+
"step": 230
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.4,
|
357 |
+
"learning_rate": 3.217221135029354e-06,
|
358 |
+
"loss": 0.0139,
|
359 |
+
"step": 240
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.4,
|
363 |
+
"eval_oasst_export_accuracy": 0.4760658765584116,
|
364 |
+
"eval_oasst_export_loss": 4.09765625,
|
365 |
+
"eval_oasst_export_runtime": 6.055,
|
366 |
+
"eval_oasst_export_samples_per_second": 180.676,
|
367 |
+
"eval_oasst_export_steps_per_second": 2.973,
|
368 |
+
"step": 240
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.46,
|
372 |
+
"learning_rate": 3.099804305283757e-06,
|
373 |
+
"loss": 0.0136,
|
374 |
+
"step": 250
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.46,
|
378 |
+
"eval_oasst_export_accuracy": 0.47102081302481486,
|
379 |
+
"eval_oasst_export_loss": 4.20703125,
|
380 |
+
"eval_oasst_export_runtime": 6.0408,
|
381 |
+
"eval_oasst_export_samples_per_second": 181.103,
|
382 |
+
"eval_oasst_export_steps_per_second": 2.98,
|
383 |
+
"step": 250
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 1.52,
|
387 |
+
"learning_rate": 2.9823874755381603e-06,
|
388 |
+
"loss": 0.0129,
|
389 |
+
"step": 260
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 1.52,
|
393 |
+
"eval_oasst_export_accuracy": 0.4641458450908967,
|
394 |
+
"eval_oasst_export_loss": 4.2578125,
|
395 |
+
"eval_oasst_export_runtime": 6.0349,
|
396 |
+
"eval_oasst_export_samples_per_second": 181.279,
|
397 |
+
"eval_oasst_export_steps_per_second": 2.983,
|
398 |
+
"step": 260
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.58,
|
402 |
+
"learning_rate": 2.8649706457925635e-06,
|
403 |
+
"loss": 0.0128,
|
404 |
+
"step": 270
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.58,
|
408 |
+
"eval_oasst_export_accuracy": 0.4649838386947822,
|
409 |
+
"eval_oasst_export_loss": 4.24609375,
|
410 |
+
"eval_oasst_export_runtime": 6.0355,
|
411 |
+
"eval_oasst_export_samples_per_second": 181.26,
|
412 |
+
"eval_oasst_export_steps_per_second": 2.982,
|
413 |
+
"step": 270
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.64,
|
417 |
+
"learning_rate": 2.7475538160469666e-06,
|
418 |
+
"loss": 0.0133,
|
419 |
+
"step": 280
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.64,
|
423 |
+
"eval_oasst_export_accuracy": 0.46412874318061326,
|
424 |
+
"eval_oasst_export_loss": 4.2421875,
|
425 |
+
"eval_oasst_export_runtime": 6.0367,
|
426 |
+
"eval_oasst_export_samples_per_second": 181.224,
|
427 |
+
"eval_oasst_export_steps_per_second": 2.982,
|
428 |
+
"step": 280
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.7,
|
432 |
+
"learning_rate": 2.63013698630137e-06,
|
433 |
+
"loss": 0.013,
|
434 |
+
"step": 290
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.7,
|
438 |
+
"eval_oasst_export_accuracy": 0.47182460280813365,
|
439 |
+
"eval_oasst_export_loss": 4.28125,
|
440 |
+
"eval_oasst_export_runtime": 6.0187,
|
441 |
+
"eval_oasst_export_samples_per_second": 181.768,
|
442 |
+
"eval_oasst_export_steps_per_second": 2.991,
|
443 |
+
"step": 290
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.75,
|
447 |
+
"learning_rate": 2.512720156555773e-06,
|
448 |
+
"loss": 0.0133,
|
449 |
+
"step": 300
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.75,
|
453 |
+
"eval_oasst_export_accuracy": 0.47093530347339796,
|
454 |
+
"eval_oasst_export_loss": 4.30078125,
|
455 |
+
"eval_oasst_export_runtime": 6.0452,
|
456 |
+
"eval_oasst_export_samples_per_second": 180.969,
|
457 |
+
"eval_oasst_export_steps_per_second": 2.978,
|
458 |
+
"step": 300
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.81,
|
462 |
+
"learning_rate": 2.395303326810176e-06,
|
463 |
+
"loss": 0.0117,
|
464 |
+
"step": 310
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.81,
|
468 |
+
"eval_oasst_export_accuracy": 0.4726454945017358,
|
469 |
+
"eval_oasst_export_loss": 4.41796875,
|
470 |
+
"eval_oasst_export_runtime": 6.0234,
|
471 |
+
"eval_oasst_export_samples_per_second": 181.624,
|
472 |
+
"eval_oasst_export_steps_per_second": 2.988,
|
473 |
+
"step": 310
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.87,
|
477 |
+
"learning_rate": 2.2778864970645793e-06,
|
478 |
+
"loss": 0.0121,
|
479 |
+
"step": 320
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.87,
|
483 |
+
"eval_oasst_export_accuracy": 0.47096950729396475,
|
484 |
+
"eval_oasst_export_loss": 4.4375,
|
485 |
+
"eval_oasst_export_runtime": 6.0349,
|
486 |
+
"eval_oasst_export_samples_per_second": 181.279,
|
487 |
+
"eval_oasst_export_steps_per_second": 2.983,
|
488 |
+
"step": 320
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.93,
|
492 |
+
"learning_rate": 2.1604696673189825e-06,
|
493 |
+
"loss": 0.0121,
|
494 |
+
"step": 330
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.93,
|
498 |
+
"eval_oasst_export_accuracy": 0.480375557949823,
|
499 |
+
"eval_oasst_export_loss": 4.421875,
|
500 |
+
"eval_oasst_export_runtime": 6.0242,
|
501 |
+
"eval_oasst_export_samples_per_second": 181.602,
|
502 |
+
"eval_oasst_export_steps_per_second": 2.988,
|
503 |
+
"step": 330
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.99,
|
507 |
+
"learning_rate": 2.0430528375733853e-06,
|
508 |
+
"loss": 0.0128,
|
509 |
+
"step": 340
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 1.99,
|
513 |
+
"eval_oasst_export_accuracy": 0.4811964496434252,
|
514 |
+
"eval_oasst_export_loss": 4.40625,
|
515 |
+
"eval_oasst_export_runtime": 6.0198,
|
516 |
+
"eval_oasst_export_samples_per_second": 181.734,
|
517 |
+
"eval_oasst_export_steps_per_second": 2.99,
|
518 |
+
"step": 340
|
519 |
+
}
|
520 |
+
],
|
521 |
+
"max_steps": 513,
|
522 |
+
"num_train_epochs": 3,
|
523 |
+
"total_flos": 2.4125538591477596e+18,
|
524 |
+
"trial_name": null,
|
525 |
+
"trial_params": null
|
526 |
+
}
|
checkpoint-342/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd9117c7e28390071fd5803c147bec189553c57f7a0a906d42ece025a148af8a
|
3 |
+
size 5499
|
checkpoint-342/zero_to_fp32.py
ADDED
@@ -0,0 +1,578 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
|
3 |
+
# Copyright (c) Microsoft Corporation.
|
4 |
+
# SPDX-License-Identifier: Apache-2.0
|
5 |
+
|
6 |
+
# DeepSpeed Team
|
7 |
+
|
8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
11 |
+
# application.
|
12 |
+
#
|
13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
14 |
+
|
15 |
+
import argparse
|
16 |
+
import torch
|
17 |
+
import glob
|
18 |
+
import math
|
19 |
+
import os
|
20 |
+
import re
|
21 |
+
from collections import OrderedDict
|
22 |
+
from dataclasses import dataclass
|
23 |
+
|
24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
26 |
+
from deepspeed.utils import logger
|
27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
30 |
+
|
31 |
+
|
32 |
+
@dataclass
|
33 |
+
class zero_model_state:
|
34 |
+
buffers: dict()
|
35 |
+
param_shapes: dict()
|
36 |
+
shared_params: list
|
37 |
+
ds_version: int
|
38 |
+
frozen_param_shapes: dict()
|
39 |
+
frozen_param_fragments: dict()
|
40 |
+
|
41 |
+
|
42 |
+
debug = 0
|
43 |
+
|
44 |
+
# load to cpu
|
45 |
+
device = torch.device('cpu')
|
46 |
+
|
47 |
+
|
48 |
+
def atoi(text):
|
49 |
+
return int(text) if text.isdigit() else text
|
50 |
+
|
51 |
+
|
52 |
+
def natural_keys(text):
|
53 |
+
'''
|
54 |
+
alist.sort(key=natural_keys) sorts in human order
|
55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
56 |
+
(See Toothy's implementation in the comments)
|
57 |
+
'''
|
58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
59 |
+
|
60 |
+
|
61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
62 |
+
if not os.path.isdir(checkpoint_dir):
|
63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
64 |
+
|
65 |
+
# there should be only one file
|
66 |
+
if zero_stage <= 2:
|
67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
68 |
+
elif zero_stage == 3:
|
69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
70 |
+
|
71 |
+
if not os.path.exists(file):
|
72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
73 |
+
|
74 |
+
return file
|
75 |
+
|
76 |
+
|
77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
80 |
+
|
81 |
+
if len(ckpt_files) == 0:
|
82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
83 |
+
|
84 |
+
return ckpt_files
|
85 |
+
|
86 |
+
|
87 |
+
def get_optim_files(checkpoint_dir):
|
88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
89 |
+
|
90 |
+
|
91 |
+
def get_model_state_files(checkpoint_dir):
|
92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
93 |
+
|
94 |
+
|
95 |
+
def parse_model_states(files):
|
96 |
+
zero_model_states = []
|
97 |
+
for file in files:
|
98 |
+
state_dict = torch.load(file, map_location=device)
|
99 |
+
|
100 |
+
if BUFFER_NAMES not in state_dict:
|
101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
103 |
+
if debug:
|
104 |
+
print("Found buffers:", buffer_names)
|
105 |
+
|
106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
109 |
+
|
110 |
+
# collect parameters that are included in param_shapes
|
111 |
+
param_names = []
|
112 |
+
for s in param_shapes:
|
113 |
+
for name in s.keys():
|
114 |
+
param_names.append(name)
|
115 |
+
|
116 |
+
# update with frozen parameters
|
117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
118 |
+
if frozen_param_shapes is not None:
|
119 |
+
if debug:
|
120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
121 |
+
param_names += list(frozen_param_shapes.keys())
|
122 |
+
|
123 |
+
# handle shared params
|
124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
125 |
+
|
126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
127 |
+
|
128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
129 |
+
|
130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
131 |
+
param_shapes=param_shapes,
|
132 |
+
shared_params=shared_params,
|
133 |
+
ds_version=ds_version,
|
134 |
+
frozen_param_shapes=frozen_param_shapes,
|
135 |
+
frozen_param_fragments=frozen_param_fragments)
|
136 |
+
zero_model_states.append(z_model_state)
|
137 |
+
|
138 |
+
return zero_model_states
|
139 |
+
|
140 |
+
|
141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
142 |
+
|
143 |
+
total_files = len(files)
|
144 |
+
state_dicts = []
|
145 |
+
for f in files:
|
146 |
+
state_dicts.append(torch.load(f, map_location=device))
|
147 |
+
|
148 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
149 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
150 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
151 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
152 |
+
|
153 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
154 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
155 |
+
# use the max of the partition_count to get the dp world_size.
|
156 |
+
|
157 |
+
if type(world_size) is list:
|
158 |
+
world_size = max(world_size)
|
159 |
+
|
160 |
+
if world_size != total_files:
|
161 |
+
raise ValueError(
|
162 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
163 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
164 |
+
)
|
165 |
+
|
166 |
+
# the groups are named differently in each stage
|
167 |
+
if zero_stage <= 2:
|
168 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
169 |
+
elif zero_stage == 3:
|
170 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
171 |
+
else:
|
172 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
173 |
+
|
174 |
+
if zero_stage <= 2:
|
175 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
176 |
+
elif zero_stage == 3:
|
177 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
178 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
179 |
+
#
|
180 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
181 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
182 |
+
|
183 |
+
fp32_flat_groups = [
|
184 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
185 |
+
]
|
186 |
+
|
187 |
+
return zero_stage, world_size, fp32_flat_groups
|
188 |
+
|
189 |
+
|
190 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
191 |
+
"""
|
192 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
193 |
+
|
194 |
+
Args:
|
195 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
196 |
+
|
197 |
+
"""
|
198 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
199 |
+
|
200 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
201 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
202 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
203 |
+
|
204 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
205 |
+
|
206 |
+
zero_model_states = parse_model_states(model_files)
|
207 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
208 |
+
|
209 |
+
if zero_stage <= 2:
|
210 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
211 |
+
elif zero_stage == 3:
|
212 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
213 |
+
|
214 |
+
|
215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
217 |
+
return
|
218 |
+
|
219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
221 |
+
|
222 |
+
if debug:
|
223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
225 |
+
|
226 |
+
wanted_params = len(frozen_param_shapes)
|
227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
231 |
+
|
232 |
+
total_params = 0
|
233 |
+
total_numel = 0
|
234 |
+
for name, shape in frozen_param_shapes.items():
|
235 |
+
total_params += 1
|
236 |
+
unpartitioned_numel = shape.numel()
|
237 |
+
total_numel += unpartitioned_numel
|
238 |
+
|
239 |
+
state_dict[name] = frozen_param_fragments[name]
|
240 |
+
|
241 |
+
if debug:
|
242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
243 |
+
|
244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
245 |
+
|
246 |
+
|
247 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
248 |
+
param_shapes = zero_model_states[0].param_shapes
|
249 |
+
|
250 |
+
# Reconstruction protocol:
|
251 |
+
#
|
252 |
+
# XXX: document this
|
253 |
+
|
254 |
+
if debug:
|
255 |
+
for i in range(world_size):
|
256 |
+
for j in range(len(fp32_flat_groups[0])):
|
257 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
258 |
+
|
259 |
+
# XXX: memory usage doubles here (zero2)
|
260 |
+
num_param_groups = len(fp32_flat_groups[0])
|
261 |
+
merged_single_partition_of_fp32_groups = []
|
262 |
+
for i in range(num_param_groups):
|
263 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
264 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
265 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
266 |
+
avail_numel = sum(
|
267 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
268 |
+
|
269 |
+
if debug:
|
270 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
271 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
272 |
+
# not asserting if there is a mismatch due to possible padding
|
273 |
+
print(f"Have {avail_numel} numels to process.")
|
274 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
275 |
+
|
276 |
+
# params
|
277 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
278 |
+
# out-of-core computing solution
|
279 |
+
total_numel = 0
|
280 |
+
total_params = 0
|
281 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
282 |
+
offset = 0
|
283 |
+
avail_numel = full_single_fp32_vector.numel()
|
284 |
+
for name, shape in shapes.items():
|
285 |
+
|
286 |
+
unpartitioned_numel = shape.numel()
|
287 |
+
total_numel += unpartitioned_numel
|
288 |
+
total_params += 1
|
289 |
+
|
290 |
+
if debug:
|
291 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
292 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
293 |
+
offset += unpartitioned_numel
|
294 |
+
|
295 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
296 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
297 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
298 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
299 |
+
align_to = 2 * world_size
|
300 |
+
|
301 |
+
def zero2_align(x):
|
302 |
+
return align_to * math.ceil(x / align_to)
|
303 |
+
|
304 |
+
if debug:
|
305 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
306 |
+
|
307 |
+
offset = zero2_align(offset)
|
308 |
+
avail_numel = zero2_align(avail_numel)
|
309 |
+
|
310 |
+
if debug:
|
311 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
312 |
+
|
313 |
+
# Sanity check
|
314 |
+
if offset != avail_numel:
|
315 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
316 |
+
|
317 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
318 |
+
|
319 |
+
|
320 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
321 |
+
state_dict = OrderedDict()
|
322 |
+
|
323 |
+
# buffers
|
324 |
+
buffers = zero_model_states[0].buffers
|
325 |
+
state_dict.update(buffers)
|
326 |
+
if debug:
|
327 |
+
print(f"added {len(buffers)} buffers")
|
328 |
+
|
329 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
330 |
+
|
331 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
332 |
+
|
333 |
+
# recover shared parameters
|
334 |
+
for pair in zero_model_states[0].shared_params:
|
335 |
+
if pair[1] in state_dict:
|
336 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
337 |
+
|
338 |
+
return state_dict
|
339 |
+
|
340 |
+
|
341 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
342 |
+
remainder = unpartitioned_numel % world_size
|
343 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
344 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
345 |
+
return partitioned_numel, padding_numel
|
346 |
+
|
347 |
+
|
348 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
349 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
350 |
+
return
|
351 |
+
|
352 |
+
if debug:
|
353 |
+
for i in range(world_size):
|
354 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
355 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
356 |
+
|
357 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
358 |
+
wanted_params = len(frozen_param_shapes)
|
359 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
360 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
361 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
362 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
363 |
+
|
364 |
+
total_params = 0
|
365 |
+
total_numel = 0
|
366 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
367 |
+
total_params += 1
|
368 |
+
unpartitioned_numel = shape.numel()
|
369 |
+
total_numel += unpartitioned_numel
|
370 |
+
|
371 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
372 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
373 |
+
|
374 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
375 |
+
|
376 |
+
if debug:
|
377 |
+
print(
|
378 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
379 |
+
)
|
380 |
+
|
381 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
382 |
+
|
383 |
+
|
384 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
385 |
+
param_shapes = zero_model_states[0].param_shapes
|
386 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
387 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
388 |
+
# param, re-consolidating each param, while dealing with padding if any
|
389 |
+
|
390 |
+
# merge list of dicts, preserving order
|
391 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
392 |
+
|
393 |
+
if debug:
|
394 |
+
for i in range(world_size):
|
395 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
396 |
+
|
397 |
+
wanted_params = len(param_shapes)
|
398 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
399 |
+
# not asserting if there is a mismatch due to possible padding
|
400 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
401 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
402 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
403 |
+
|
404 |
+
# params
|
405 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
406 |
+
# out-of-core computing solution
|
407 |
+
offset = 0
|
408 |
+
total_numel = 0
|
409 |
+
total_params = 0
|
410 |
+
for name, shape in param_shapes.items():
|
411 |
+
|
412 |
+
unpartitioned_numel = shape.numel()
|
413 |
+
total_numel += unpartitioned_numel
|
414 |
+
total_params += 1
|
415 |
+
|
416 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
417 |
+
|
418 |
+
if debug:
|
419 |
+
print(
|
420 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
421 |
+
)
|
422 |
+
|
423 |
+
# XXX: memory usage doubles here
|
424 |
+
state_dict[name] = torch.cat(
|
425 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
426 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
427 |
+
offset += partitioned_numel
|
428 |
+
|
429 |
+
offset *= world_size
|
430 |
+
|
431 |
+
# Sanity check
|
432 |
+
if offset != avail_numel:
|
433 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
434 |
+
|
435 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
436 |
+
|
437 |
+
|
438 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
439 |
+
state_dict = OrderedDict()
|
440 |
+
|
441 |
+
# buffers
|
442 |
+
buffers = zero_model_states[0].buffers
|
443 |
+
state_dict.update(buffers)
|
444 |
+
if debug:
|
445 |
+
print(f"added {len(buffers)} buffers")
|
446 |
+
|
447 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
448 |
+
|
449 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
450 |
+
|
451 |
+
# recover shared parameters
|
452 |
+
for pair in zero_model_states[0].shared_params:
|
453 |
+
if pair[1] in state_dict:
|
454 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
455 |
+
|
456 |
+
return state_dict
|
457 |
+
|
458 |
+
|
459 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
460 |
+
"""
|
461 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
462 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
463 |
+
via a model hub.
|
464 |
+
|
465 |
+
Args:
|
466 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
467 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
468 |
+
|
469 |
+
Returns:
|
470 |
+
- pytorch ``state_dict``
|
471 |
+
|
472 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
473 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
474 |
+
the checkpoint.
|
475 |
+
|
476 |
+
A typical usage might be ::
|
477 |
+
|
478 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
479 |
+
# do the training and checkpoint saving
|
480 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
481 |
+
model = model.cpu() # move to cpu
|
482 |
+
model.load_state_dict(state_dict)
|
483 |
+
# submit to model hub or save the model to share with others
|
484 |
+
|
485 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
486 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
487 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
488 |
+
|
489 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
490 |
+
|
491 |
+
"""
|
492 |
+
if tag is None:
|
493 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
494 |
+
if os.path.isfile(latest_path):
|
495 |
+
with open(latest_path, 'r') as fd:
|
496 |
+
tag = fd.read().strip()
|
497 |
+
else:
|
498 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
499 |
+
|
500 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
501 |
+
|
502 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
503 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
504 |
+
|
505 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
506 |
+
|
507 |
+
|
508 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
509 |
+
"""
|
510 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
511 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
512 |
+
|
513 |
+
Args:
|
514 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
515 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
516 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
517 |
+
"""
|
518 |
+
|
519 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
520 |
+
print(f"Saving fp32 state dict to {output_file}")
|
521 |
+
torch.save(state_dict, output_file)
|
522 |
+
|
523 |
+
|
524 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
525 |
+
"""
|
526 |
+
1. Put the provided model to cpu
|
527 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
528 |
+
3. Load it into the provided model
|
529 |
+
|
530 |
+
Args:
|
531 |
+
- ``model``: the model object to update
|
532 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
533 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
534 |
+
|
535 |
+
Returns:
|
536 |
+
- ``model`: modified model
|
537 |
+
|
538 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
539 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
540 |
+
conveniently placed for you in the checkpoint folder.
|
541 |
+
|
542 |
+
A typical usage might be ::
|
543 |
+
|
544 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
545 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
546 |
+
# submit to model hub or save the model to share with others
|
547 |
+
|
548 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
549 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
550 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
551 |
+
|
552 |
+
"""
|
553 |
+
logger.info(f"Extracting fp32 weights")
|
554 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
555 |
+
|
556 |
+
logger.info(f"Overwriting model with fp32 weights")
|
557 |
+
model = model.cpu()
|
558 |
+
model.load_state_dict(state_dict, strict=False)
|
559 |
+
|
560 |
+
return model
|
561 |
+
|
562 |
+
|
563 |
+
if __name__ == "__main__":
|
564 |
+
|
565 |
+
parser = argparse.ArgumentParser()
|
566 |
+
parser.add_argument("checkpoint_dir",
|
567 |
+
type=str,
|
568 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
569 |
+
parser.add_argument(
|
570 |
+
"output_file",
|
571 |
+
type=str,
|
572 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
573 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
574 |
+
args = parser.parse_args()
|
575 |
+
|
576 |
+
debug = args.debug
|
577 |
+
|
578 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)
|
checkpoint-513/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "toanbku/oa-pythia-12b-rlhf-df",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": 0.1,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 5120,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 20480,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"model_type": "gpt_neox",
|
18 |
+
"num_attention_heads": 40,
|
19 |
+
"num_hidden_layers": 36,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rotary_emb_base": 10000,
|
22 |
+
"rotary_pct": 0.25,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.31.0.dev0",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_parallel_residual": true,
|
28 |
+
"vocab_size": 50288
|
29 |
+
}
|
checkpoint-513/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.31.0.dev0"
|
6 |
+
}
|
checkpoint-513/global_step513/mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c02057b4f5996f47e9848f3dcbf6797470c46585425925cac2db63632bc5c95
|
3 |
+
size 23684097854
|
checkpoint-513/global_step513/zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb503443e65f4375f0a53ca2a0e8703908df1ef073f4fd28cd77b80d8fa9095
|
3 |
+
size 17762971806
|
checkpoint-513/global_step513/zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ff5885de281d970b62bdca900b50dc44441d290603425711ec7dd875b4da1f4
|
3 |
+
size 17762972766
|
checkpoint-513/global_step513/zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e7bbec5d200cced122d44295f3fe68f2955aaa5eb47d6b30a50f06dbfb1408
|
3 |
+
size 17762972766
|
checkpoint-513/global_step513/zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbe34267d2118c3ce832e5d2bad89a5902605f1d490a7ab46d85da58e0a14b2c
|
3 |
+
size 17762972446
|
checkpoint-513/global_step513/zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff79336950b7bcd0aa717255abb0c860f011370c8a0f2c6401a4552e22bfe56b
|
3 |
+
size 17762972702
|
checkpoint-513/global_step513/zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf8a1f1ee7a0c1a79070922e5a0eff973a2967c8feb214977787ba917b55b570
|
3 |
+
size 17762972830
|
checkpoint-513/global_step513/zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf35798822d734dd1d9bd316a5bc1729dd83ca376b004a4c83370aeedcd49c29
|
3 |
+
size 17762972638
|
checkpoint-513/global_step513/zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b66df4d3fcc0ea5509fcbb599e8bbb1bc801f0f791d34d3426430a1b03285399
|
3 |
+
size 17762971742
|
checkpoint-513/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step513
|
checkpoint-513/pytorch_model-00001-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b44de8a5f6e3a987cb844e673119b4b6c43c634add97be72ce93cd381c8dcd5
|
3 |
+
size 9839916213
|
checkpoint-513/pytorch_model-00002-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48c1f9303879a4b159ff12d7be944f3f2ae4cd5309ce403e4c5a1d41a2f0defd
|
3 |
+
size 9648960597
|
checkpoint-513/pytorch_model-00003-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:744472a05950d41eeef5ff9b60243798e9781a9234a5c4efdd57da8b52869ff1
|
3 |
+
size 9648982897
|
checkpoint-513/pytorch_model-00004-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44afbd599aea7be2c1b2cb81507ef3504d671bc23f195847cb1f3977a509eaa6
|
3 |
+
size 9963617221
|
checkpoint-513/pytorch_model-00005-of-00005.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbaf88c791efc698a58eaf2235bcaf24b8c7868255f2fca4a043b7cb393aec73
|
3 |
+
size 8266593363
|
checkpoint-513/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,479 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 47367907584
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"embed_out.weight": "pytorch_model-00005-of-00005.bin",
|
7 |
+
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00005.bin",
|
8 |
+
"gpt_neox.final_layer_norm.bias": "pytorch_model-00005-of-00005.bin",
|
9 |
+
"gpt_neox.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
|
10 |
+
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
11 |
+
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
12 |
+
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
13 |
+
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
14 |
+
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
15 |
+
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
16 |
+
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
17 |
+
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
18 |
+
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
19 |
+
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
20 |
+
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
21 |
+
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
22 |
+
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
23 |
+
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
24 |
+
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
25 |
+
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
26 |
+
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
27 |
+
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
28 |
+
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
29 |
+
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
30 |
+
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
31 |
+
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
32 |
+
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
33 |
+
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
34 |
+
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
35 |
+
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
36 |
+
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
37 |
+
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
38 |
+
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
39 |
+
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
40 |
+
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
41 |
+
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
42 |
+
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
43 |
+
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
44 |
+
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
45 |
+
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
46 |
+
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
47 |
+
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
48 |
+
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
49 |
+
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
50 |
+
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
51 |
+
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
52 |
+
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
53 |
+
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
54 |
+
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
55 |
+
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
56 |
+
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
57 |
+
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
58 |
+
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
59 |
+
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
60 |
+
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
61 |
+
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
62 |
+
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
63 |
+
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
64 |
+
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
65 |
+
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
66 |
+
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
67 |
+
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
68 |
+
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
69 |
+
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
70 |
+
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
71 |
+
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
72 |
+
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
73 |
+
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
74 |
+
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
75 |
+
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
76 |
+
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
77 |
+
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
78 |
+
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
79 |
+
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
80 |
+
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
81 |
+
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
82 |
+
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
83 |
+
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
84 |
+
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
85 |
+
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
86 |
+
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
87 |
+
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
88 |
+
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
89 |
+
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
90 |
+
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
91 |
+
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
92 |
+
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
93 |
+
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
94 |
+
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
95 |
+
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
96 |
+
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
97 |
+
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
98 |
+
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
99 |
+
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
100 |
+
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
101 |
+
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
102 |
+
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
103 |
+
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
104 |
+
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
105 |
+
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
106 |
+
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
107 |
+
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
108 |
+
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
109 |
+
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
110 |
+
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
111 |
+
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
112 |
+
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
113 |
+
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
114 |
+
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
115 |
+
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
116 |
+
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
117 |
+
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
118 |
+
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
119 |
+
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
120 |
+
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
121 |
+
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
122 |
+
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
123 |
+
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
124 |
+
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
125 |
+
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
126 |
+
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
127 |
+
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
128 |
+
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
129 |
+
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
130 |
+
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
131 |
+
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
132 |
+
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
133 |
+
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
134 |
+
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
135 |
+
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
136 |
+
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
137 |
+
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
138 |
+
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
139 |
+
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
140 |
+
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
141 |
+
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
142 |
+
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
143 |
+
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
144 |
+
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
145 |
+
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
146 |
+
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
147 |
+
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
148 |
+
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
149 |
+
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
150 |
+
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
151 |
+
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
152 |
+
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
153 |
+
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
154 |
+
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
155 |
+
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
156 |
+
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
157 |
+
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
158 |
+
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
159 |
+
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
160 |
+
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
161 |
+
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
162 |
+
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
163 |
+
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
164 |
+
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
165 |
+
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
166 |
+
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
167 |
+
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
168 |
+
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
169 |
+
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
170 |
+
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
171 |
+
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
172 |
+
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
173 |
+
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
174 |
+
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
175 |
+
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
176 |
+
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
177 |
+
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
178 |
+
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
179 |
+
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
180 |
+
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
181 |
+
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
182 |
+
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
183 |
+
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
184 |
+
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
185 |
+
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
186 |
+
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
187 |
+
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
188 |
+
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
189 |
+
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
190 |
+
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
191 |
+
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
192 |
+
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
193 |
+
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
194 |
+
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
195 |
+
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
196 |
+
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
197 |
+
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
198 |
+
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
199 |
+
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00005.bin",
|
200 |
+
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
|
201 |
+
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00005.bin",
|
202 |
+
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
|
203 |
+
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
204 |
+
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
205 |
+
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00003-of-00005.bin",
|
206 |
+
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00003-of-00005.bin",
|
207 |
+
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00005.bin",
|
208 |
+
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
|
209 |
+
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin",
|
210 |
+
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
211 |
+
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
212 |
+
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
213 |
+
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
214 |
+
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
215 |
+
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
216 |
+
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00005.bin",
|
217 |
+
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
218 |
+
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
219 |
+
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
220 |
+
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
221 |
+
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
222 |
+
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
223 |
+
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
224 |
+
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
225 |
+
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
226 |
+
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
227 |
+
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
228 |
+
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
229 |
+
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
230 |
+
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
231 |
+
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
232 |
+
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
233 |
+
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
234 |
+
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
235 |
+
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
236 |
+
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
237 |
+
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
238 |
+
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
239 |
+
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
240 |
+
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
241 |
+
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
242 |
+
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
243 |
+
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
244 |
+
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
245 |
+
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
246 |
+
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
247 |
+
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
248 |
+
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
249 |
+
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
250 |
+
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
251 |
+
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
252 |
+
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
253 |
+
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
254 |
+
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
255 |
+
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
256 |
+
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
257 |
+
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
258 |
+
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
259 |
+
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
260 |
+
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
261 |
+
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
262 |
+
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
263 |
+
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
264 |
+
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
265 |
+
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
266 |
+
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
267 |
+
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
268 |
+
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
269 |
+
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
270 |
+
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
271 |
+
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
272 |
+
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
273 |
+
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
274 |
+
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
275 |
+
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
276 |
+
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
277 |
+
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
278 |
+
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
279 |
+
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
280 |
+
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
281 |
+
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
282 |
+
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
283 |
+
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
284 |
+
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
285 |
+
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
286 |
+
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
287 |
+
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
288 |
+
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
289 |
+
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
290 |
+
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
291 |
+
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
292 |
+
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
293 |
+
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
294 |
+
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
295 |
+
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
296 |
+
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00004-of-00005.bin",
|
297 |
+
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00004-of-00005.bin",
|
298 |
+
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
299 |
+
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
300 |
+
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
301 |
+
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
302 |
+
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
303 |
+
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00005.bin",
|
304 |
+
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
|
305 |
+
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00005.bin",
|
306 |
+
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
|
307 |
+
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
308 |
+
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
309 |
+
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
310 |
+
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
311 |
+
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
312 |
+
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
313 |
+
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
314 |
+
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
315 |
+
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
316 |
+
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
317 |
+
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
318 |
+
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
319 |
+
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
320 |
+
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
321 |
+
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
322 |
+
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
323 |
+
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
324 |
+
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00004-of-00005.bin",
|
325 |
+
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
|
326 |
+
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin",
|
327 |
+
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
328 |
+
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
329 |
+
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
330 |
+
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
331 |
+
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
332 |
+
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
333 |
+
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00005.bin",
|
334 |
+
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
335 |
+
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
336 |
+
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
337 |
+
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
338 |
+
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
339 |
+
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
340 |
+
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
341 |
+
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
342 |
+
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
343 |
+
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
344 |
+
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
345 |
+
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
346 |
+
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
347 |
+
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
348 |
+
"gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
349 |
+
"gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
350 |
+
"gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
351 |
+
"gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
352 |
+
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
353 |
+
"gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
354 |
+
"gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
355 |
+
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
356 |
+
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
357 |
+
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
358 |
+
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
359 |
+
"gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
360 |
+
"gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
361 |
+
"gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
362 |
+
"gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
363 |
+
"gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
364 |
+
"gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
365 |
+
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
366 |
+
"gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
367 |
+
"gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
368 |
+
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
369 |
+
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
370 |
+
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
371 |
+
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
372 |
+
"gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
373 |
+
"gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
374 |
+
"gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
375 |
+
"gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
376 |
+
"gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
377 |
+
"gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
378 |
+
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
379 |
+
"gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
380 |
+
"gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
381 |
+
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
382 |
+
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
383 |
+
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
384 |
+
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
385 |
+
"gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
386 |
+
"gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
387 |
+
"gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00005-of-00005.bin",
|
388 |
+
"gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00005-of-00005.bin",
|
389 |
+
"gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00005-of-00005.bin",
|
390 |
+
"gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
|
391 |
+
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin",
|
392 |
+
"gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
393 |
+
"gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
394 |
+
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00005.bin",
|
395 |
+
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
|
396 |
+
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00005.bin",
|
397 |
+
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
|
398 |
+
"gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00005.bin",
|
399 |
+
"gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
400 |
+
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
401 |
+
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
402 |
+
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
403 |
+
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
404 |
+
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
405 |
+
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
406 |
+
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
407 |
+
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
408 |
+
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
409 |
+
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
410 |
+
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
411 |
+
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
412 |
+
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
413 |
+
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
414 |
+
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
415 |
+
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
416 |
+
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
417 |
+
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
418 |
+
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
419 |
+
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
420 |
+
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
421 |
+
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
422 |
+
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
423 |
+
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
424 |
+
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
425 |
+
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
426 |
+
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00005.bin",
|
427 |
+
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00005.bin",
|
428 |
+
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00005.bin",
|
429 |
+
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
|
430 |
+
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
431 |
+
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
432 |
+
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
433 |
+
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00005.bin",
|
434 |
+
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
|
435 |
+
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00005.bin",
|
436 |
+
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
|
437 |
+
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
438 |
+
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
439 |
+
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
440 |
+
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
441 |
+
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
442 |
+
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
443 |
+
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin",
|
444 |
+
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
445 |
+
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
446 |
+
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
447 |
+
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
448 |
+
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
449 |
+
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
450 |
+
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00005.bin",
|
451 |
+
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
452 |
+
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
453 |
+
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
454 |
+
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
455 |
+
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
456 |
+
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
457 |
+
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
458 |
+
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
459 |
+
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
460 |
+
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
461 |
+
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
462 |
+
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
463 |
+
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
464 |
+
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
465 |
+
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00005.bin",
|
466 |
+
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00005.bin",
|
467 |
+
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00005.bin",
|
468 |
+
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
|
469 |
+
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin",
|
470 |
+
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
471 |
+
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
472 |
+
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00005.bin",
|
473 |
+
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
|
474 |
+
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00005.bin",
|
475 |
+
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
|
476 |
+
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00005.bin",
|
477 |
+
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin"
|
478 |
+
}
|
479 |
+
}
|