N8Programs commited on
Commit
8d309eb
1 Parent(s): 5bf1e99

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,140 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: N8Programs/llamoe-8x1b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: out
8
+ results: []
9
  ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<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)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.0`
18
+ ```yaml
19
+ base_model: N8Programs/llamoe-8x1b
20
+ model_type: MixtralForCausalLM
21
+ tokenizer_type: LlamaTokenizer
22
+
23
+ load_in_8bit: false
24
+ load_in_4bit: false
25
+ strict: false
26
+
27
+ datasets:
28
+ - path: mhenrichsen/alpaca_2k_test
29
+ type: alpaca
30
+ dataset_prepared_path:
31
+ val_set_size: 0.05
32
+ output_dir: ./out
33
+
34
+ sequence_len: 2048
35
+ sample_packing: true
36
+ eval_sample_packing: false
37
+ pad_to_sequence_len: true
38
+
39
+ wandb_project: tinyllamoe
40
+ wandb_entity:
41
+ wandb_watch:
42
+ wandb_name: run-1
43
+ wandb_log_model: run-1
44
+
45
+ gradient_accumulation_steps: 4
46
+ micro_batch_size: 2
47
+ num_epochs: 4
48
+ optimizer: adafactor
49
+ lr_scheduler: cosine
50
+ learning_rate: 0.0002
51
+
52
+ train_on_inputs: false
53
+ group_by_length: false
54
+ bf16: auto
55
+ fp16:
56
+ tf32: false
57
+
58
+ gradient_checkpointing: true
59
+ early_stopping_patience:
60
+ resume_from_checkpoint:
61
+ local_rank:
62
+ logging_steps: 1
63
+ xformers_attention:
64
+ flash_attention: true
65
+
66
+ warmup_steps: 10
67
+ evals_per_epoch: 4
68
+ saves_per_epoch: 1
69
+ debug:
70
+ deepspeed:
71
+ weight_decay: 0.0
72
+ fsdp:
73
+ fsdp_config:
74
+ special_tokens:
75
+
76
+ ```
77
+
78
+ </details><br>
79
+
80
+ # out
81
+
82
+ This model is a fine-tuned version of [N8Programs/llamoe-8x1b](https://huggingface.co/N8Programs/llamoe-8x1b) on the None dataset.
83
+ It achieves the following results on the evaluation set:
84
+ - Loss: 1.7176
85
+
86
+ ## Model description
87
+
88
+ More information needed
89
+
90
+ ## Intended uses & limitations
91
+
92
+ More information needed
93
+
94
+ ## Training and evaluation data
95
+
96
+ More information needed
97
+
98
+ ## Training procedure
99
+
100
+ ### Training hyperparameters
101
+
102
+ The following hyperparameters were used during training:
103
+ - learning_rate: 0.0002
104
+ - train_batch_size: 2
105
+ - eval_batch_size: 2
106
+ - seed: 42
107
+ - gradient_accumulation_steps: 4
108
+ - total_train_batch_size: 8
109
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
110
+ - lr_scheduler_type: cosine
111
+ - lr_scheduler_warmup_steps: 10
112
+ - num_epochs: 4
113
+
114
+ ### Training results
115
+
116
+ | Training Loss | Epoch | Step | Validation Loss |
117
+ |:-------------:|:-----:|:----:|:---------------:|
118
+ | 1.2099 | 0.04 | 1 | 1.2991 |
119
+ | 1.3823 | 0.27 | 7 | 1.4997 |
120
+ | 10.4722 | 0.54 | 14 | 2.6370 |
121
+ | 1.6521 | 0.82 | 21 | 1.4303 |
122
+ | 1.6555 | 1.07 | 28 | 1.7053 |
123
+ | 1.7864 | 1.34 | 35 | 1.8820 |
124
+ | 1.2141 | 1.61 | 42 | 1.6614 |
125
+ | 1.1488 | 1.88 | 49 | 1.5619 |
126
+ | 0.4733 | 2.14 | 56 | 1.6381 |
127
+ | 0.444 | 2.41 | 63 | 1.6311 |
128
+ | 0.4717 | 2.68 | 70 | 1.6398 |
129
+ | 0.4657 | 2.95 | 77 | 1.5938 |
130
+ | 0.1066 | 3.2 | 84 | 1.6952 |
131
+ | 0.1547 | 3.48 | 91 | 1.7209 |
132
+ | 0.1246 | 3.75 | 98 | 1.7176 |
133
+
134
+
135
+ ### Framework versions
136
+
137
+ - Transformers 4.39.0.dev0
138
+ - Pytorch 2.2.0+cu121
139
+ - Datasets 2.18.0
140
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32001,
3
+ "<|im_start|>": 32000
4
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "N8Programs/llamoe-8x1b",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 1,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "num_local_experts": 8,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.39.0.dev0",
31
+ "use_cache": false,
32
+ "vocab_size": 32032
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67d03410d2d2e9f382f157a7d72d683984c141c7607cd4a9919435a744e9e51
3
+ size 4984765513
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f1d74e57b821aa3a36b41ee70901c0439d9513bf75d5ed7093d820f453a6ef
3
+ size 4991985350
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9babe262a1b1e5ef016e43fc7953855837f15280ac49987c3e5ae932743dacb
3
+ size 2883027970
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,692 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12859527168
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
239
+ "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
240
+ "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
241
+ "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
242
+ "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
243
+ "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
244
+ "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
245
+ "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
246
+ "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
247
+ "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
248
+ "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
249
+ "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
250
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
253
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
259
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
260
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
262
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
263
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
264
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
265
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
266
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
267
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
268
+ "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
269
+ "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
270
+ "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
271
+ "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
272
+ "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
273
+ "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
274
+ "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
275
+ "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
276
+ "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
277
+ "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
278
+ "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
279
+ "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
280
+ "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
281
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
282
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
283
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
284
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
285
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
286
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
287
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
288
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
289
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
290
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
291
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
312
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
315
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
316
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
317
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
318
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00003.bin",
332
+ "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00003.bin",
334
+ "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00003.bin",
337
+ "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00003.bin",
338
+ "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00003.bin",
341
+ "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00003.bin",
342
+ "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
344
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
346
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
347
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
348
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
349
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00003.bin",
350
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00003.bin",
351
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00003.bin",
352
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00003.bin",
353
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00003.bin",
354
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00003.bin",
355
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
356
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
357
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
358
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
359
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
360
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
361
+ "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00003.bin",
362
+ "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00003.bin",
363
+ "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00003.bin",
364
+ "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00003.bin",
365
+ "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00003.bin",
366
+ "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00003.bin",
367
+ "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00003.bin",
368
+ "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00003.bin",
369
+ "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00003.bin",
370
+ "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00003.bin",
371
+ "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00003.bin",
372
+ "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00003.bin",
373
+ "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00003.bin",
374
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
375
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
376
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
377
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
378
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
379
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
380
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
382
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
384
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
386
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
387
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
388
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
390
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
392
+ "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
394
+ "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
396
+ "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
397
+ "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
408
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
409
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
410
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
411
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00003.bin",
414
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00003.bin",
417
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
419
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
421
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
423
+ "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00003.bin",
425
+ "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00003.bin",
427
+ "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00003.bin",
429
+ "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00003.bin",
432
+ "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00003.bin",
433
+ "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00003.bin",
435
+ "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
437
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
439
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
441
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00003.bin",
443
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00003.bin",
445
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00003.bin",
447
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
449
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
451
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
453
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00003.bin",
455
+ "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00003.bin",
457
+ "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00003.bin",
459
+ "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00003.bin",
461
+ "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00003.bin",
463
+ "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00003.bin",
465
+ "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00003.bin",
467
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
469
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
471
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
473
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
474
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
475
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
476
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
477
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
478
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
479
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
480
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
481
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
482
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
483
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
484
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
485
+ "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
486
+ "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
487
+ "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
488
+ "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
489
+ "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
490
+ "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
491
+ "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
492
+ "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
493
+ "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
494
+ "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
495
+ "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
496
+ "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
497
+ "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
498
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
499
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
500
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
501
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
502
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
503
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
504
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
505
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
506
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
507
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
508
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
509
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
510
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
511
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
512
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
513
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
514
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
515
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
516
+ "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
517
+ "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
518
+ "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
519
+ "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
520
+ "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
521
+ "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
522
+ "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
523
+ "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
524
+ "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
525
+ "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
526
+ "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
527
+ "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
528
+ "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
529
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
530
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
531
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
532
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
533
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
534
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
535
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
536
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
537
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
538
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
539
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
540
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
541
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
542
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
543
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
544
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
545
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
546
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
547
+ "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
548
+ "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
549
+ "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
550
+ "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
551
+ "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
552
+ "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
553
+ "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
554
+ "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
555
+ "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
556
+ "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
557
+ "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
558
+ "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
559
+ "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
560
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
561
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
562
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
563
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
564
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
565
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
566
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
567
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
568
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
569
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
570
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
571
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
572
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
573
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
574
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
575
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
576
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
577
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
578
+ "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
579
+ "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
580
+ "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
581
+ "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
582
+ "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
583
+ "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
584
+ "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
585
+ "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
586
+ "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
587
+ "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
588
+ "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
589
+ "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
590
+ "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
591
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
592
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
593
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
594
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
595
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
596
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
597
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
598
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
599
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
600
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
601
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
602
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
603
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
604
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
605
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
606
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
607
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
608
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
609
+ "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00003.bin",
610
+ "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00003.bin",
611
+ "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00003.bin",
612
+ "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00003.bin",
613
+ "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00003.bin",
614
+ "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00003.bin",
615
+ "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00003.bin",
616
+ "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00003.bin",
617
+ "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00003.bin",
618
+ "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00003.bin",
619
+ "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00003.bin",
620
+ "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00003.bin",
621
+ "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
622
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
623
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
624
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
625
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
626
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
627
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
628
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
629
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
630
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
631
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
632
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
633
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
634
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
635
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
636
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
637
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
638
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
639
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
640
+ "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
641
+ "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
642
+ "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
643
+ "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
644
+ "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
645
+ "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
646
+ "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
647
+ "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
648
+ "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
649
+ "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
650
+ "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
651
+ "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
652
+ "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
653
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
654
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
655
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
656
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
657
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
658
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
659
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
660
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
661
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
662
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
663
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
664
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
665
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
666
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
667
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
668
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
669
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
670
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
671
+ "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00003.bin",
672
+ "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00003.bin",
673
+ "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00003.bin",
674
+ "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00003.bin",
675
+ "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00003.bin",
676
+ "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00003.bin",
677
+ "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00003.bin",
678
+ "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00003.bin",
679
+ "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00003.bin",
680
+ "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00003.bin",
681
+ "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00003.bin",
682
+ "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00003.bin",
683
+ "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
684
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
685
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
686
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
687
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
688
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
689
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
690
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
691
+ }
692
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "32001": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ }
46
+ },
47
+ "bos_token": "<s>",
48
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
51
+ "legacy": false,
52
+ "model_max_length": 2048,
53
+ "pad_token": "<s>",
54
+ "padding_side": "left",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": false,
60
+ "use_fast": true
61
+ }