MaziyarPanahi commited on
Commit
4d7b51c
1 Parent(s): 8392b56

Upload folder using huggingface_hub (#1)

Browse files

- 1624ea0705d783c21c938d691fe59ff901583a494f796fb3bb4a691a5d8e0650 (a3ee3cd3200fdd665bb8198dfa5d583acd914824)
- 8f91d08c2f92028c71430894369125ec6937b3a6daa0492141c255fcb10c708d (21db55ed00ba18c0a2596d0e18f7af7d97618596)
- 3fa27357dbbc624f5142f1999cccf64882a9a68fbe6ec385c3d5ccfee38942a0 (4f48cf9374f8480330cae51910548c701b3769d9)
- b7ca2d2d0a9382d66e6ccf4f8195f4b1e5d100137fa908ffb790af78cae0a08a (dc21acd6b32cd4859572937d2e18a5bb490be355)
- 6c363e4e6543bc9e8c8b73835f2ee6df7437fce67644867893a870e6777ba6ae (433075913dc96ffbbf1c6ed25300edf2d64dfd68)
- bcaa2097dcb688afb263d5ec8964d040d02874c1690cf0fd753156761890cb4a (6e6593d010c16abc6d26800c0247fa55808ddfa5)
- c9431f2466288980965ff37a686875492f170899447d13de7eae53aa1fb4a490 (02c4569d26e29884e05cddb89d294163a93a09d8)
- e4963c537abda6ed920df9d22427ee079020cdc289fa521f703fb835c9fdabb2 (1559f09712bc7c4d50d05d4aae769ea3a0fddc44)
- 90770cc343bbf82f66fe044ce73c7aebafe86f81b966225ee9c66692a1a70090 (382b796313fb280506661a07a486f6395bda896e)
- aae0b29d043871016ea00d8b926ab01b54bb9e6f57a0bc5b246816ce17e2279b (2cb04d06e0bb9fe06db639842c74556d84494bbf)
- 6aba4a5dcd79933f7c809f29ffda0b84963d89acc73c7871951dd739944391c2 (74c2b5343f00f3c7b6e411b59c78a96efd7f4538)
- b5c8b1fed9aa79aa67df2b0fac89450f8b43c686ad0ff9ed693072aec8819ccb (ab9b8ec70c57cb52e544221a31f5b62ebeaa429c)
- ebb5a62a564b2200bed43173694297ebc5c97344d806c33117c5a877120ab17a (08f57f07c1837c00e081067c98ea67e3b7507c25)
- 9fed7671d060984ed8264f4efc0ea939c9f5822d43e36b0b46824a120aca3cf0 (a49a8878c5a7303e57f501085dc00f0de09fa106)
- e2a6981386aa5ab385561c6a2910b74c75d00b850b26bd92b940e36371b51c9d (4f4dc8393606b0c4a4cb95934fe440bd7a6834f7)
- 7fd6eff2e7ab7e53b7793b849bd6f7465bb19239d732882a8b38a23b51467d97 (b4742a22e42d7f69ba9ad506bda422d2dec391af)

.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - axolotl
5
+ - generated_from_trainer
6
+ base_model: MaziyarPanahi/Qwen1.5-8x7b
7
+ model-index:
8
+ - name: Qwen1.5-8x7b-v0.1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: MaziyarPanahi/Qwen1.5-8x7b
21
+ model_type: Qwen2ForCausalLM
22
+ tokenizer_type: Qwen2Tokenizer
23
+
24
+ trust_remote_code: true
25
+
26
+ hub_model_id: MaziyarPanahi/Qwen1.5-8x7b-v0.1
27
+ hf_use_auth_token: true
28
+
29
+ load_in_8bit: false
30
+ load_in_4bit: true
31
+ strict: false
32
+
33
+
34
+ datasets:
35
+ - path: Crystalcareai/MoD-150k
36
+ type: sharegpt
37
+
38
+
39
+ dataset_prepared_path:
40
+ val_set_size: 0.05
41
+ output_dir: ./Qwen1.5-8x7b-v0.1-lora-out
42
+
43
+ model_config:
44
+ output_router_logits: true
45
+
46
+ adapter: qlora
47
+ lora_model_dir:
48
+ sequence_len: 2048
49
+ sample_packing: true
50
+ pad_to_sequence_len: true
51
+
52
+
53
+ lora_r: 32
54
+ lora_alpha: 16
55
+ lora_dropout: 0.05
56
+ lora_target_linear: true
57
+ lora_fan_in_fan_out:
58
+
59
+
60
+ gradient_accumulation_steps: 2
61
+ micro_batch_size: 2
62
+ num_epochs: 1
63
+ optimizer: adamw_bnb_8bit
64
+ lr_scheduler: cosine
65
+ learning_rate: 0.0002
66
+
67
+
68
+ train_on_inputs: false
69
+ group_by_length: false
70
+ bf16: auto
71
+ fp16:
72
+ tf32: false
73
+
74
+
75
+ gradient_checkpointing: true
76
+ early_stopping_patience:
77
+ resume_from_checkpoint:
78
+ local_rank:
79
+ logging_steps: 1
80
+ xformers_attention:
81
+ flash_attention: true
82
+
83
+
84
+ warmup_steps: 10
85
+ evals_per_epoch: 4
86
+ eval_table_size:
87
+ eval_max_new_tokens: 128
88
+ saves_per_epoch: 1
89
+ debug:
90
+ deepspeed:
91
+ weight_decay: 0.0
92
+ fsdp:
93
+ fsdp_config:
94
+ special_tokens:
95
+ ```
96
+
97
+ </details><br>
98
+
99
+ # Qwen1.5-8x7b-v0.1
100
+
101
+ This model is a fine-tuned version of [MaziyarPanahi/Qwen1.5-8x7b](https://huggingface.co/MaziyarPanahi/Qwen1.5-8x7b) on the None dataset.
102
+ It achieves the following results on the evaluation set:
103
+ - Loss: 0.7945
104
+
105
+ ## Model description
106
+
107
+ More information needed
108
+
109
+ ## Intended uses & limitations
110
+
111
+ More information needed
112
+
113
+ ## Training and evaluation data
114
+
115
+ More information needed
116
+
117
+ ## Training procedure
118
+
119
+ ### Training hyperparameters
120
+
121
+ The following hyperparameters were used during training:
122
+ - learning_rate: 0.0002
123
+ - train_batch_size: 2
124
+ - eval_batch_size: 2
125
+ - seed: 42
126
+ - distributed_type: multi-GPU
127
+ - num_devices: 4
128
+ - gradient_accumulation_steps: 2
129
+ - total_train_batch_size: 16
130
+ - total_eval_batch_size: 8
131
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
132
+ - lr_scheduler_type: cosine
133
+ - lr_scheduler_warmup_steps: 10
134
+ - num_epochs: 1
135
+
136
+ ### Training results
137
+
138
+ | Training Loss | Epoch | Step | Validation Loss |
139
+ |:-------------:|:-----:|:----:|:---------------:|
140
+ | 6.2196 | 0.0 | 1 | 6.1942 |
141
+ | 0.7772 | 0.25 | 513 | 0.8037 |
142
+ | 0.656 | 0.5 | 1026 | 0.7977 |
143
+ | 0.6967 | 0.75 | 1539 | 0.7945 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - PEFT 0.8.2
149
+ - Transformers 4.39.0.dev0
150
+ - Pytorch 2.2.0+cu121
151
+ - Datasets 2.17.0
152
+ - Tokenizers 0.15.0
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MaziyarPanahi/Qwen1.5-8x7b",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "num_local_experts": 8,
21
+ "output_router_logits": true,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.39.0.dev0",
29
+ "use_cache": false,
30
+ "use_sliding_window": false,
31
+ "vocab_size": 151936
32
+ }
.ipynb_checkpoints/generation_config-checkpoint.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "transformers_version": "4.39.0.dev0",
6
+ "use_cache": false
7
+ }
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null,
43
+ "use_fast": true
44
+ }
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - axolotl
5
+ - generated_from_trainer
6
+ - moe
7
+ - qwen
8
+ - text-generation-inference
9
+ base_model: MaziyarPanahi/Qwen1.5-8x7b
10
+ model-index:
11
+ - name: Qwen1.5-8x7b-v0.1
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
19
+ <details><summary>See axolotl config</summary>
20
+
21
+ axolotl version: `0.4.0`
22
+ ```yaml
23
+ base_model: MaziyarPanahi/Qwen1.5-8x7b
24
+ model_type: Qwen2ForCausalLM
25
+ tokenizer_type: Qwen2Tokenizer
26
+
27
+ trust_remote_code: true
28
+
29
+ hub_model_id: MaziyarPanahi/Qwen1.5-8x7b-v0.1
30
+ hf_use_auth_token: true
31
+
32
+ load_in_8bit: false
33
+ load_in_4bit: true
34
+ strict: false
35
+
36
+
37
+ datasets:
38
+ - path: Crystalcareai/MoD-150k
39
+ type: sharegpt
40
+
41
+
42
+ dataset_prepared_path:
43
+ val_set_size: 0.05
44
+ output_dir: ./Qwen1.5-8x7b-v0.1-lora-out
45
+
46
+ model_config:
47
+ output_router_logits: true
48
+
49
+ adapter: qlora
50
+ lora_model_dir:
51
+ sequence_len: 2048
52
+ sample_packing: true
53
+ pad_to_sequence_len: true
54
+
55
+
56
+ lora_r: 32
57
+ lora_alpha: 16
58
+ lora_dropout: 0.05
59
+ lora_target_linear: true
60
+ lora_fan_in_fan_out:
61
+
62
+
63
+ gradient_accumulation_steps: 2
64
+ micro_batch_size: 2
65
+ num_epochs: 1
66
+ optimizer: adamw_bnb_8bit
67
+ lr_scheduler: cosine
68
+ learning_rate: 0.0002
69
+
70
+
71
+ train_on_inputs: false
72
+ group_by_length: false
73
+ bf16: auto
74
+ fp16:
75
+ tf32: false
76
+
77
+
78
+ gradient_checkpointing: true
79
+ early_stopping_patience:
80
+ resume_from_checkpoint:
81
+ local_rank:
82
+ logging_steps: 1
83
+ xformers_attention:
84
+ flash_attention: true
85
+
86
+
87
+ warmup_steps: 10
88
+ evals_per_epoch: 4
89
+ eval_table_size:
90
+ eval_max_new_tokens: 128
91
+ saves_per_epoch: 1
92
+ debug:
93
+ deepspeed:
94
+ weight_decay: 0.0
95
+ fsdp:
96
+ fsdp_config:
97
+ special_tokens:
98
+ ```
99
+
100
+ </details><br>
101
+
102
+ # Qwen1.5-8x7b-v0.1
103
+
104
+ This model is a fine-tuned version of [MaziyarPanahi/Qwen1.5-8x7b](https://huggingface.co/MaziyarPanahi/Qwen1.5-8x7b) on the [Crystalcareai/MoD-150k](https://huggingface.co/datasets/Crystalcareai/MoD-150k) dataset.
105
+ It achieves the following results on the evaluation set:
106
+ - Loss: 0.7945
107
+
108
+ ## Model description
109
+
110
+ More information needed
111
+
112
+ ## Intended uses & limitations
113
+
114
+ More information needed
115
+
116
+ ## Training and evaluation data
117
+
118
+ More information needed
119
+
120
+ ## Training procedure
121
+
122
+ ### Training hyperparameters
123
+
124
+ The following hyperparameters were used during training:
125
+ - learning_rate: 0.0002
126
+ - train_batch_size: 2
127
+ - eval_batch_size: 2
128
+ - seed: 42
129
+ - distributed_type: multi-GPU
130
+ - num_devices: 4
131
+ - gradient_accumulation_steps: 2
132
+ - total_train_batch_size: 16
133
+ - total_eval_batch_size: 8
134
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
135
+ - lr_scheduler_type: cosine
136
+ - lr_scheduler_warmup_steps: 10
137
+ - num_epochs: 1
138
+
139
+ ### Training results
140
+
141
+ | Training Loss | Epoch | Step | Validation Loss |
142
+ |:-------------:|:-----:|:----:|:---------------:|
143
+ | 6.2196 | 0.0 | 1 | 6.1942 |
144
+ | 0.7772 | 0.25 | 513 | 0.8037 |
145
+ | 0.656 | 0.5 | 1026 | 0.7977 |
146
+ | 0.6967 | 0.75 | 1539 | 0.7945 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - PEFT 0.8.2
152
+ - Transformers 4.39.0.dev0
153
+ - Pytorch 2.2.0+cu121
154
+ - Datasets 2.17.0
155
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MaziyarPanahi/Qwen1.5-8x7b",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "num_local_experts": 8,
21
+ "output_router_logits": true,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.39.0.dev0",
29
+ "use_cache": false,
30
+ "use_sliding_window": false,
31
+ "vocab_size": 151936
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "transformers_version": "4.39.0.dev0",
6
+ "use_cache": false
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16e0bef51a005228c4962bdb4e6741106e69eece1b9829d03729ead11f6b1bd
3
+ size 4940007936
pytorch_model-00002-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e38d1d7d7b49cca63ec3c3b04d43a9ea9807e7e059f5b3566b4f369a92cdb6
3
+ size 4957855554
pytorch_model-00003-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9404ea7de50fa260564c13532c23f17500b3a42e56e8077e4d4aad9ef724a9
3
+ size 4957855590
pytorch_model-00004-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03426e84d4b7241743c136f748992e88970325cbc4dc7b09829b9723ba8fa4f2
3
+ size 4911801956
pytorch_model-00005-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bfefd373b5e0b1a48ce100b6679c69577aec0fdbce1d1af087e1a568f81d1c
3
+ size 4957855566
pytorch_model-00006-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283c321b199a8af454b5e08978153f06c2f5db1e82fc4c3a55835a6a4853cb12
3
+ size 4957855618
pytorch_model-00007-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadd5130aa0b9f2cdb00a43879a17cd175a9a9eda0346046d2960a59a89078df
3
+ size 4957855618
pytorch_model-00008-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7450592add1461fe58c3a68b98d25556d000a973c770a726bc4e9386edb476
3
+ size 4957855618
pytorch_model-00009-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fae39a89af2241474aa0a37f0093900396fc1e298a82aba029e0bc1ac3e90e4
3
+ size 4957855642
pytorch_model-00010-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4b6f9dccec967ad0b3b09764e6b9e09b3daaabfa4c89ab867c362f4af37863
3
+ size 4991427572
pytorch_model-00011-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583226e17c10b45948490cd467533e9563d976ff37dd8ac6eb22e7564026f515
3
+ size 4968408028
pytorch_model-00012-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c28aea4b3f3a5ff3c1e9b7fb27bcd243a71648c9e2548229179113e076205be
3
+ size 4957855618
pytorch_model-00013-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d21a5728a4d02e21200e5620254b808eb1a075d8019f55ac1b671d3153eb23d
3
+ size 4957855618
pytorch_model-00014-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b45b0d8ba0e60d3fea522353741aa86b7b9696b76e4c6d4a9a3fed4a7054e7
3
+ size 4957855618
pytorch_model-00015-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:950b34e57f285002989ecec495d99d59b0ee01fda426ea49468ac4cacacb01a5
3
+ size 4957855630
pytorch_model-00016-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3da2e1c632af935df50e1a7b9d9f9ae148c587498c672d2a9c3633c1ea350fd5
3
+ size 1695576013
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,1002 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 76043264000
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00016-of-00016.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00016.bin",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00016.bin",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00016.bin",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00016.bin",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00016.bin",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00016.bin",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00016.bin",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00016.bin",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00016.bin",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00016.bin",
17
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00016.bin",
18
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00016.bin",
19
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00016.bin",
20
+ "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00016.bin",
21
+ "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00016.bin",
22
+ "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00016.bin",
23
+ "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00016.bin",
24
+ "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00016.bin",
25
+ "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00016.bin",
26
+ "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00016.bin",
27
+ "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00016.bin",
28
+ "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00016.bin",
29
+ "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00016.bin",
30
+ "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00016.bin",
31
+ "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00016.bin",
32
+ "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00016.bin",
33
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00016.bin",
34
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00016.bin",
35
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00016.bin",
36
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00016.bin",
37
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00016.bin",
38
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00016.bin",
39
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00016.bin",
40
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00016.bin",
41
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00016.bin",
42
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00016.bin",
43
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00016.bin",
44
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00016.bin",
45
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00016.bin",
46
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00016.bin",
47
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00016.bin",
48
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00016.bin",
49
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00016.bin",
50
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00016.bin",
51
+ "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00016.bin",
52
+ "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00016.bin",
53
+ "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00016.bin",
54
+ "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00016.bin",
55
+ "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00016.bin",
56
+ "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00016.bin",
57
+ "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00016.bin",
58
+ "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00016.bin",
59
+ "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00016.bin",
60
+ "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00016.bin",
61
+ "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00016.bin",
62
+ "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00016.bin",
63
+ "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00016.bin",
64
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
65
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
66
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00016.bin",
67
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00016.bin",
68
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00016.bin",
69
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00016.bin",
70
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00016.bin",
71
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00016.bin",
72
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00016.bin",
73
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00016.bin",
74
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00016.bin",
75
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00016.bin",
76
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00016.bin",
77
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00016.bin",
78
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00016.bin",
79
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00016.bin",
80
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00016.bin",
81
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00016.bin",
82
+ "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00016.bin",
83
+ "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00016.bin",
84
+ "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00016.bin",
85
+ "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00016.bin",
86
+ "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00016.bin",
87
+ "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00016.bin",
88
+ "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00016.bin",
89
+ "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00016.bin",
90
+ "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00016.bin",
91
+ "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00016.bin",
92
+ "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00016.bin",
93
+ "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00016.bin",
94
+ "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00016.bin",
95
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
96
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
97
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
98
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
99
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
100
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
101
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00016.bin",
102
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00016.bin",
103
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00016.bin",
104
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00016.bin",
105
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00016.bin",
106
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00016.bin",
107
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00016.bin",
108
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00016.bin",
109
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00016.bin",
110
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00016.bin",
111
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00016.bin",
112
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00016.bin",
113
+ "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00016.bin",
114
+ "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00016.bin",
115
+ "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00016.bin",
116
+ "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00016.bin",
117
+ "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00016.bin",
118
+ "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00016.bin",
119
+ "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00016.bin",
120
+ "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00016.bin",
121
+ "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00016.bin",
122
+ "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00016.bin",
123
+ "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00016.bin",
124
+ "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00016.bin",
125
+ "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00016.bin",
126
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
127
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
128
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00016.bin",
129
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
130
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
131
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
132
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00016.bin",
133
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00016.bin",
134
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00016.bin",
135
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00016.bin",
136
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00016.bin",
137
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00016.bin",
138
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00016.bin",
139
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00016.bin",
140
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00016.bin",
141
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00016.bin",
142
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00016.bin",
143
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00016.bin",
144
+ "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00016.bin",
145
+ "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00016.bin",
146
+ "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00016.bin",
147
+ "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00016.bin",
148
+ "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00016.bin",
149
+ "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00016.bin",
150
+ "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00016.bin",
151
+ "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00016.bin",
152
+ "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00016.bin",
153
+ "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00016.bin",
154
+ "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00016.bin",
155
+ "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00016.bin",
156
+ "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00016.bin",
157
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
158
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
159
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00016.bin",
160
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
161
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
162
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
163
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00016.bin",
164
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00016.bin",
165
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00016.bin",
166
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00016.bin",
167
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00016.bin",
168
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00016.bin",
169
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00016.bin",
170
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00016.bin",
171
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00016.bin",
172
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00016.bin",
173
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00016.bin",
174
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00016.bin",
175
+ "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00016.bin",
176
+ "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00016.bin",
177
+ "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00016.bin",
178
+ "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00016.bin",
179
+ "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00016.bin",
180
+ "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00016.bin",
181
+ "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00016.bin",
182
+ "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00016.bin",
183
+ "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00016.bin",
184
+ "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00016.bin",
185
+ "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00016.bin",
186
+ "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00016.bin",
187
+ "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00016.bin",
188
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
189
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
190
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00016.bin",
191
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
192
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00016.bin",
193
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00016.bin",
194
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00016.bin",
195
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00016.bin",
196
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00016.bin",
197
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00016.bin",
198
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00016.bin",
199
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00016.bin",
200
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00016.bin",
201
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00016.bin",
202
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00016.bin",
203
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00016.bin",
204
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00016.bin",
205
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00016.bin",
206
+ "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00016.bin",
207
+ "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00016.bin",
208
+ "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00016.bin",
209
+ "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00016.bin",
210
+ "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00016.bin",
211
+ "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00016.bin",
212
+ "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00016.bin",
213
+ "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00016.bin",
214
+ "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00016.bin",
215
+ "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00016.bin",
216
+ "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00016.bin",
217
+ "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00016.bin",
218
+ "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00016.bin",
219
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
220
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
221
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00016.bin",
222
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
223
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00016.bin",
224
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00016.bin",
225
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00016.bin",
226
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00016.bin",
227
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00016.bin",
228
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00016.bin",
229
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00016.bin",
230
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00016.bin",
231
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00016.bin",
232
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00016.bin",
233
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00016.bin",
234
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00016.bin",
235
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00016.bin",
236
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00016.bin",
237
+ "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00016.bin",
238
+ "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00016.bin",
239
+ "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00016.bin",
240
+ "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00016.bin",
241
+ "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00016.bin",
242
+ "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00016.bin",
243
+ "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00016.bin",
244
+ "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00016.bin",
245
+ "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00016.bin",
246
+ "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00016.bin",
247
+ "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00016.bin",
248
+ "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00016.bin",
249
+ "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00016.bin",
250
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
251
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
252
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
253
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
254
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
255
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
256
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00016.bin",
257
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00016.bin",
258
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00016.bin",
259
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00016.bin",
260
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00016.bin",
261
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00016.bin",
262
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00016.bin",
263
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00016.bin",
264
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00016.bin",
265
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00016.bin",
266
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00016.bin",
267
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00016.bin",
268
+ "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00016.bin",
269
+ "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00016.bin",
270
+ "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00016.bin",
271
+ "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00016.bin",
272
+ "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00016.bin",
273
+ "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00016.bin",
274
+ "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00016.bin",
275
+ "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00016.bin",
276
+ "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00016.bin",
277
+ "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00016.bin",
278
+ "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00016.bin",
279
+ "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00016.bin",
280
+ "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00016.bin",
281
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
282
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
283
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
284
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
285
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
286
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
287
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00016.bin",
288
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00016.bin",
289
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00016.bin",
290
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00016.bin",
291
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00016.bin",
292
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00016.bin",
293
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00016.bin",
294
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00016.bin",
295
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00016.bin",
296
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00016.bin",
297
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00016.bin",
298
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00016.bin",
299
+ "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00016.bin",
300
+ "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00016.bin",
301
+ "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00016.bin",
302
+ "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00016.bin",
303
+ "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00016.bin",
304
+ "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00016.bin",
305
+ "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00016.bin",
306
+ "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00016.bin",
307
+ "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00016.bin",
308
+ "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00016.bin",
309
+ "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00016.bin",
310
+ "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00016.bin",
311
+ "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00016.bin",
312
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
313
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
314
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
315
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
316
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
317
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
318
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00016.bin",
319
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00016.bin",
320
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00016.bin",
321
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00016.bin",
322
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00016.bin",
323
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00016.bin",
324
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00016.bin",
325
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00016.bin",
326
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00016.bin",
327
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00016.bin",
328
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00016.bin",
329
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00016.bin",
330
+ "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00016.bin",
331
+ "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00016.bin",
332
+ "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00016.bin",
333
+ "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00016.bin",
334
+ "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00016.bin",
335
+ "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00016.bin",
336
+ "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00016.bin",
337
+ "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00016.bin",
338
+ "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00016.bin",
339
+ "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00016.bin",
340
+ "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00016.bin",
341
+ "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00016.bin",
342
+ "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00016.bin",
343
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
344
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
345
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
346
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
347
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
348
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
349
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00016.bin",
350
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00016.bin",
351
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00016.bin",
352
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00016.bin",
353
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00016.bin",
354
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00016.bin",
355
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00016.bin",
356
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00016.bin",
357
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00016.bin",
358
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00016.bin",
359
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00016.bin",
360
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00016.bin",
361
+ "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00016.bin",
362
+ "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00016.bin",
363
+ "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00016.bin",
364
+ "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00016.bin",
365
+ "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00016.bin",
366
+ "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00016.bin",
367
+ "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00016.bin",
368
+ "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00016.bin",
369
+ "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00016.bin",
370
+ "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00016.bin",
371
+ "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00016.bin",
372
+ "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00016.bin",
373
+ "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00016.bin",
374
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
375
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
376
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
377
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
378
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
379
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
380
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00016.bin",
381
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00016.bin",
382
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00016.bin",
383
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00016.bin",
384
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00016.bin",
385
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00016.bin",
386
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00016.bin",
387
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00016.bin",
388
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00016.bin",
389
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00016.bin",
390
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00016.bin",
391
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00016.bin",
392
+ "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00016.bin",
393
+ "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00016.bin",
394
+ "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00016.bin",
395
+ "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00016.bin",
396
+ "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00016.bin",
397
+ "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00016.bin",
398
+ "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00016.bin",
399
+ "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00016.bin",
400
+ "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00016.bin",
401
+ "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00016.bin",
402
+ "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00016.bin",
403
+ "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00016.bin",
404
+ "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00016.bin",
405
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
406
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
407
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
408
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
409
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
410
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
411
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00016.bin",
412
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00016.bin",
413
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00016.bin",
414
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00016.bin",
415
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00016.bin",
416
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00016.bin",
417
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00016.bin",
418
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00016.bin",
419
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00016.bin",
420
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00016.bin",
421
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00016.bin",
422
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00016.bin",
423
+ "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00016.bin",
424
+ "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00016.bin",
425
+ "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00016.bin",
426
+ "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00016.bin",
427
+ "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00016.bin",
428
+ "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00016.bin",
429
+ "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00016.bin",
430
+ "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00016.bin",
431
+ "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00016.bin",
432
+ "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00016.bin",
433
+ "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00016.bin",
434
+ "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00016.bin",
435
+ "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00016.bin",
436
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
437
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
438
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
439
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
440
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
441
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
442
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00016.bin",
443
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00016.bin",
444
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00016.bin",
445
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00016.bin",
446
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00016.bin",
447
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00016.bin",
448
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00016.bin",
449
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00016.bin",
450
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00016.bin",
451
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00016.bin",
452
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00016.bin",
453
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00016.bin",
454
+ "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00016.bin",
455
+ "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00016.bin",
456
+ "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00016.bin",
457
+ "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00016.bin",
458
+ "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00016.bin",
459
+ "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00016.bin",
460
+ "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00016.bin",
461
+ "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00016.bin",
462
+ "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00016.bin",
463
+ "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00016.bin",
464
+ "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00016.bin",
465
+ "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00016.bin",
466
+ "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00016.bin",
467
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
468
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
469
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
470
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
471
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
472
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
473
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00016.bin",
474
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00016.bin",
475
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00016.bin",
476
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00016.bin",
477
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00016.bin",
478
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00016.bin",
479
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00016.bin",
480
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00016.bin",
481
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00016.bin",
482
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00016.bin",
483
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00016.bin",
484
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00016.bin",
485
+ "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00016.bin",
486
+ "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00016.bin",
487
+ "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00016.bin",
488
+ "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00016.bin",
489
+ "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00016.bin",
490
+ "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00016.bin",
491
+ "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00016.bin",
492
+ "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00016.bin",
493
+ "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00016.bin",
494
+ "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00016.bin",
495
+ "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00016.bin",
496
+ "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00016.bin",
497
+ "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00016.bin",
498
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
499
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
500
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
501
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
502
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
503
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
504
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00016.bin",
505
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00016.bin",
506
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00016.bin",
507
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00016.bin",
508
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00016.bin",
509
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00016.bin",
510
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00016.bin",
511
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00016.bin",
512
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00016.bin",
513
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00016.bin",
514
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00016.bin",
515
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00016.bin",
516
+ "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00016.bin",
517
+ "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00016.bin",
518
+ "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00016.bin",
519
+ "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00016.bin",
520
+ "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00016.bin",
521
+ "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00016.bin",
522
+ "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00016.bin",
523
+ "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00016.bin",
524
+ "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00016.bin",
525
+ "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00016.bin",
526
+ "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00016.bin",
527
+ "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00016.bin",
528
+ "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00016.bin",
529
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
530
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
531
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
532
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
533
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
534
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
535
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00016.bin",
536
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00016.bin",
537
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00016.bin",
538
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00016.bin",
539
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00016.bin",
540
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00016.bin",
541
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00016.bin",
542
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00016.bin",
543
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00016.bin",
544
+ "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00016.bin",
545
+ "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00016.bin",
546
+ "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00016.bin",
547
+ "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00016.bin",
548
+ "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00016.bin",
549
+ "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00016.bin",
550
+ "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00016.bin",
551
+ "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00016.bin",
552
+ "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00016.bin",
553
+ "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00016.bin",
554
+ "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00016.bin",
555
+ "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00016.bin",
556
+ "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00016.bin",
557
+ "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00016.bin",
558
+ "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00016.bin",
559
+ "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00016.bin",
560
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
561
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
562
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
563
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
564
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
565
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
566
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00016.bin",
567
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00016.bin",
568
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00016.bin",
569
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00016.bin",
570
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00016.bin",
571
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00016.bin",
572
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00016.bin",
573
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00016.bin",
574
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00016.bin",
575
+ "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00016.bin",
576
+ "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00016.bin",
577
+ "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00016.bin",
578
+ "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00016.bin",
579
+ "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00016.bin",
580
+ "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00016.bin",
581
+ "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00016.bin",
582
+ "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00016.bin",
583
+ "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00016.bin",
584
+ "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00016.bin",
585
+ "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00016.bin",
586
+ "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00016.bin",
587
+ "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00016.bin",
588
+ "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00016.bin",
589
+ "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00016.bin",
590
+ "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00016.bin",
591
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
592
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
593
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
594
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
595
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
596
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
597
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00016.bin",
598
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00016.bin",
599
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00016.bin",
600
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00016.bin",
601
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00016.bin",
602
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00016.bin",
603
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00016.bin",
604
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00016.bin",
605
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00016.bin",
606
+ "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00016.bin",
607
+ "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00016.bin",
608
+ "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00016.bin",
609
+ "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00016.bin",
610
+ "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00016.bin",
611
+ "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00016.bin",
612
+ "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00016.bin",
613
+ "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00016.bin",
614
+ "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00016.bin",
615
+ "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00016.bin",
616
+ "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00016.bin",
617
+ "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00016.bin",
618
+ "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00016.bin",
619
+ "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00016.bin",
620
+ "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00016.bin",
621
+ "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00016.bin",
622
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
623
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
624
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
625
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
626
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
627
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
628
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00016.bin",
629
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00016.bin",
630
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00016.bin",
631
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00016.bin",
632
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00016.bin",
633
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00016.bin",
634
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00016.bin",
635
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00016.bin",
636
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00016.bin",
637
+ "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00016.bin",
638
+ "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00016.bin",
639
+ "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00016.bin",
640
+ "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00016.bin",
641
+ "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00016.bin",
642
+ "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00016.bin",
643
+ "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00016.bin",
644
+ "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00016.bin",
645
+ "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00016.bin",
646
+ "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00016.bin",
647
+ "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00016.bin",
648
+ "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00016.bin",
649
+ "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00016.bin",
650
+ "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00016.bin",
651
+ "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00016.bin",
652
+ "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00016.bin",
653
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
654
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
655
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
656
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
657
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
658
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
659
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00016.bin",
660
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00016.bin",
661
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00016.bin",
662
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00016.bin",
663
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00016.bin",
664
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00016.bin",
665
+ "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00016.bin",
666
+ "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00016.bin",
667
+ "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00016.bin",
668
+ "model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00016.bin",
669
+ "model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00016.bin",
670
+ "model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00016.bin",
671
+ "model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00016.bin",
672
+ "model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00016.bin",
673
+ "model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00016.bin",
674
+ "model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00016.bin",
675
+ "model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00016.bin",
676
+ "model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00016.bin",
677
+ "model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00016.bin",
678
+ "model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00016.bin",
679
+ "model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00016.bin",
680
+ "model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00016.bin",
681
+ "model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00016.bin",
682
+ "model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00016.bin",
683
+ "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00016.bin",
684
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
685
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
686
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
687
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
688
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
689
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00014-of-00016.bin",
690
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00016.bin",
691
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00016.bin",
692
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00016.bin",
693
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00016.bin",
694
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00016.bin",
695
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00016.bin",
696
+ "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00016.bin",
697
+ "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00016.bin",
698
+ "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00016.bin",
699
+ "model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00016.bin",
700
+ "model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00016.bin",
701
+ "model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00016.bin",
702
+ "model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00016.bin",
703
+ "model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00016.bin",
704
+ "model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00016.bin",
705
+ "model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00016.bin",
706
+ "model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00016.bin",
707
+ "model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00016.bin",
708
+ "model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00016.bin",
709
+ "model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00016.bin",
710
+ "model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00016.bin",
711
+ "model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00016.bin",
712
+ "model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00016.bin",
713
+ "model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00016.bin",
714
+ "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00016.bin",
715
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
716
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
717
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
718
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
719
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
720
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00014-of-00016.bin",
721
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00016.bin",
722
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00016.bin",
723
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00016.bin",
724
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00016.bin",
725
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00016.bin",
726
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00016.bin",
727
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00016.bin",
728
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00016.bin",
729
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00016.bin",
730
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00016.bin",
731
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00016.bin",
732
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00016.bin",
733
+ "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00016.bin",
734
+ "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00016.bin",
735
+ "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00016.bin",
736
+ "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00016.bin",
737
+ "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00016.bin",
738
+ "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00016.bin",
739
+ "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00016.bin",
740
+ "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00016.bin",
741
+ "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00016.bin",
742
+ "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00016.bin",
743
+ "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00016.bin",
744
+ "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00016.bin",
745
+ "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00016.bin",
746
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
747
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
748
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
749
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
750
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
751
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
752
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00016.bin",
753
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00016.bin",
754
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00016.bin",
755
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00016.bin",
756
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00016.bin",
757
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00016.bin",
758
+ "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00016.bin",
759
+ "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00016.bin",
760
+ "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00016.bin",
761
+ "model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00016.bin",
762
+ "model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00016.bin",
763
+ "model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00016.bin",
764
+ "model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00016.bin",
765
+ "model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00016.bin",
766
+ "model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00016.bin",
767
+ "model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00016.bin",
768
+ "model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00016.bin",
769
+ "model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00016.bin",
770
+ "model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00016.bin",
771
+ "model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00016.bin",
772
+ "model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00016.bin",
773
+ "model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00016.bin",
774
+ "model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00016.bin",
775
+ "model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00016.bin",
776
+ "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00016.bin",
777
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
778
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
779
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00015-of-00016.bin",
780
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
781
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00015-of-00016.bin",
782
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00015-of-00016.bin",
783
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00016.bin",
784
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00016.bin",
785
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00016.bin",
786
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00016.bin",
787
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00016.bin",
788
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00016.bin",
789
+ "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00016.bin",
790
+ "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00016.bin",
791
+ "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00016.bin",
792
+ "model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00016.bin",
793
+ "model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00016.bin",
794
+ "model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00016.bin",
795
+ "model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00016.bin",
796
+ "model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00016.bin",
797
+ "model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00016.bin",
798
+ "model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00016.bin",
799
+ "model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00016.bin",
800
+ "model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00016.bin",
801
+ "model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00016.bin",
802
+ "model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00016.bin",
803
+ "model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00016.bin",
804
+ "model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00016.bin",
805
+ "model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00016.bin",
806
+ "model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00016.bin",
807
+ "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00016.bin",
808
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00016-of-00016.bin",
809
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00016-of-00016.bin",
810
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00015-of-00016.bin",
811
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
812
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00015-of-00016.bin",
813
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00015-of-00016.bin",
814
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00016.bin",
815
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00016.bin",
816
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00016.bin",
817
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00016.bin",
818
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00016.bin",
819
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00016.bin",
820
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00016.bin",
821
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00016.bin",
822
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00016.bin",
823
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00016.bin",
824
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00016.bin",
825
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00016.bin",
826
+ "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00016.bin",
827
+ "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00016.bin",
828
+ "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00016.bin",
829
+ "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00016.bin",
830
+ "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00016.bin",
831
+ "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00016.bin",
832
+ "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00016.bin",
833
+ "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00016.bin",
834
+ "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00016.bin",
835
+ "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00016.bin",
836
+ "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00016.bin",
837
+ "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00016.bin",
838
+ "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00016.bin",
839
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
840
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
841
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00016.bin",
842
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
843
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
844
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00016.bin",
845
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00016.bin",
846
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00016.bin",
847
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00016.bin",
848
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00016.bin",
849
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00016.bin",
850
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00016.bin",
851
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00016.bin",
852
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00016.bin",
853
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00016.bin",
854
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00016.bin",
855
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00016.bin",
856
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00016.bin",
857
+ "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00016.bin",
858
+ "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00016.bin",
859
+ "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00016.bin",
860
+ "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00016.bin",
861
+ "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00016.bin",
862
+ "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00016.bin",
863
+ "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00016.bin",
864
+ "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00016.bin",
865
+ "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00016.bin",
866
+ "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00016.bin",
867
+ "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00016.bin",
868
+ "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00016.bin",
869
+ "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00016.bin",
870
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
871
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
872
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00016.bin",
873
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
874
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
875
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00016.bin",
876
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00016.bin",
877
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00016.bin",
878
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00016.bin",
879
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00016.bin",
880
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00016.bin",
881
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00016.bin",
882
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00016.bin",
883
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00016.bin",
884
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00016.bin",
885
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00016.bin",
886
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00016.bin",
887
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00016.bin",
888
+ "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00016.bin",
889
+ "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00016.bin",
890
+ "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00016.bin",
891
+ "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00016.bin",
892
+ "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00016.bin",
893
+ "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00016.bin",
894
+ "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00016.bin",
895
+ "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00016.bin",
896
+ "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00016.bin",
897
+ "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00016.bin",
898
+ "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00016.bin",
899
+ "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00016.bin",
900
+ "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00016.bin",
901
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
902
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
903
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00016.bin",
904
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
905
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00016.bin",
906
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00016.bin",
907
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00016.bin",
908
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00016.bin",
909
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00016.bin",
910
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00016.bin",
911
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00016.bin",
912
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00016.bin",
913
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00016.bin",
914
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00016.bin",
915
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00016.bin",
916
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00016.bin",
917
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00016.bin",
918
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00016.bin",
919
+ "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00016.bin",
920
+ "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00016.bin",
921
+ "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00016.bin",
922
+ "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00016.bin",
923
+ "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00016.bin",
924
+ "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00016.bin",
925
+ "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00016.bin",
926
+ "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00016.bin",
927
+ "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00016.bin",
928
+ "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00016.bin",
929
+ "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00016.bin",
930
+ "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00016.bin",
931
+ "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00016.bin",
932
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
933
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
934
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00016.bin",
935
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
936
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00016.bin",
937
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00016.bin",
938
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00016.bin",
939
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00016.bin",
940
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00016.bin",
941
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00016.bin",
942
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00016.bin",
943
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00016.bin",
944
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00016.bin",
945
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00016.bin",
946
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00016.bin",
947
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00016.bin",
948
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00016.bin",
949
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00016.bin",
950
+ "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00016.bin",
951
+ "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00016.bin",
952
+ "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00016.bin",
953
+ "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00016.bin",
954
+ "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00016.bin",
955
+ "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00016.bin",
956
+ "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00016.bin",
957
+ "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00016.bin",
958
+ "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00016.bin",
959
+ "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00016.bin",
960
+ "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00016.bin",
961
+ "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00016.bin",
962
+ "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00016.bin",
963
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
964
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
965
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00016.bin",
966
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
967
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00016.bin",
968
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00016.bin",
969
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00016.bin",
970
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00016.bin",
971
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00016.bin",
972
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00016.bin",
973
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00016.bin",
974
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00016.bin",
975
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00016.bin",
976
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00016.bin",
977
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00016.bin",
978
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00016.bin",
979
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00016.bin",
980
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00016.bin",
981
+ "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00016.bin",
982
+ "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00016.bin",
983
+ "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00016.bin",
984
+ "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00016.bin",
985
+ "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00016.bin",
986
+ "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00016.bin",
987
+ "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00016.bin",
988
+ "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00016.bin",
989
+ "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00016.bin",
990
+ "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00016.bin",
991
+ "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00016.bin",
992
+ "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00016.bin",
993
+ "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00016.bin",
994
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
995
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
996
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
997
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
998
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
999
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
1000
+ "model.norm.weight": "pytorch_model-00016-of-00016.bin"
1001
+ }
1002
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null,
43
+ "use_fast": true
44
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff