Hugging Face's logo

Lambent
/
CosMoEAlpacaLisa-4x1b

Text Generation
Transformers
PyTorch
mixtral
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
3v324v23 commited on
Commit
403b4e5
·
1 Parent(s): 0f653ec

lisa model

Browse files
Files changed (10) hide show
  1. README.md +140 -0
  2. config.json +34 -0
  3. generation_config.json +7 -0
  4. pytorch_model-00001-of-00003.bin +3 -0
  5. pytorch_model-00002-of-00003.bin +3 -0
  6. pytorch_model-00003-of-00003.bin +3 -0
  7. pytorch_model.bin.index.json +466 -0
  8. special_tokens_map.json +30 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +44 -0
README.md CHANGED
@@ -1,3 +1,143 @@
1
  ---
2
  license: cc
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc
3
+ base_model: Lambent/cosmoem-4x1b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: lisa-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: Lambent/cosmoem-4x1b
20
+ model_type: AutoModelForCausalLM
21
+ tokenizer_type: LlamaTokenizer
22
+ trust_remote_code: true
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: vicgalle/alpaca-gpt4
30
+ type: alpaca
31
+ dataset_prepared_path: prepared-alpaca
32
+ val_set_size: 0.05
33
+ output_dir: ./lisa-out
34
+
35
+ sequence_len: 2048
36
+ sample_packing: true
37
+ eval_sample_packing: false
38
+ pad_to_sequence_len: true
39
+
40
+ lisa_n_layers: 4
41
+ lisa_step_interval: 10
42
+ lisa_layers_attribute: model.layers
43
+
44
+ adapter:
45
+ lora_model_dir:
46
+ lora_r:
47
+ lora_alpha:
48
+ lora_dropout:
49
+ lora_target_linear:
50
+ lora_fan_in_fan_out:
51
+
52
+ wandb_project: CosMoE-AlpacaLisa
53
+ wandb_entity:
54
+ wandb_watch:
55
+ wandb_name:
56
+ wandb_log_model:
57
+
58
+ gradient_accumulation_steps: 1
59
+ micro_batch_size: 1
60
+ num_epochs: 1
61
+ optimizer: adamw_bnb_8bit
62
+ lr_scheduler: cosine
63
+ learning_rate: 0.0005
64
+
65
+ train_on_inputs: false
66
+ group_by_length: false
67
+ bf16: auto
68
+ fp16:
69
+ tf32: false
70
+
71
+ gradient_checkpointing: true
72
+ early_stopping_patience:
73
+ resume_from_checkpoint:
74
+ local_rank:
75
+ logging_steps: 1
76
+ xformers_attention:
77
+ flash_attention: true
78
+
79
+ loss_watchdog_threshold: 3.0
80
+ loss_watchdog_patience: 3
81
+
82
+ warmup_steps: 20
83
+ evals_per_epoch: 4
84
+ saves_per_epoch: 1
85
+ debug:
86
+ deepspeed:
87
+ weight_decay: 0.002
88
+ fsdp:
89
+ fsdp_config:
90
+ special_tokens:
91
+
92
+ ```
93
+
94
+ </details><br>
95
+
96
+ # lisa-out
97
+
98
+ This model is a fine-tuned version of [Lambent/cosmoem-4x1b](https://huggingface.co/Lambent/cosmoem-4x1b) on the None dataset.
99
+ It achieves the following results on the evaluation set:
100
+ - Loss: 1.2588
101
+
102
+ ## Model description
103
+
104
+ More information needed
105
+
106
+ ## Intended uses & limitations
107
+
108
+ More information needed
109
+
110
+ ## Training and evaluation data
111
+
112
+ More information needed
113
+
114
+ ## Training procedure
115
+
116
+ ### Training hyperparameters
117
+
118
+ The following hyperparameters were used during training:
119
+ - learning_rate: 0.0005
120
+ - train_batch_size: 1
121
+ - eval_batch_size: 1
122
+ - seed: 42
123
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
124
+ - lr_scheduler_type: cosine
125
+ - lr_scheduler_warmup_steps: 20
126
+ - num_epochs: 1
127
+
128
+ ### Training results
129
+
130
+ | Training Loss | Epoch | Step | Validation Loss |
131
+ |:-------------:|:-----:|:----:|:---------------:|
132
+ | 1.197 | 0.0 | 1 | 1.5990 |
133
+ | 1.4959 | 0.25 | 1383 | 1.4359 |
134
+ | 1.6549 | 0.5 | 2766 | 1.3353 |
135
+ | 1.3571 | 0.75 | 4149 | 1.2588 |
136
+
137
+
138
+ ### Framework versions
139
+
140
+ - Transformers 4.40.0.dev0
141
+ - Pytorch 2.1.2+cu118
142
+ - Datasets 2.18.0
143
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Lambent/cosmoem-4x1b",
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": 8192,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 16,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "num_local_experts": 4,
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
+ "router_jitter_noise": 0.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.40.0.dev0",
32
+ "use_cache": false,
33
+ "vocab_size": 32000
34
+ }
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": "4.40.0.dev0"
7
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3782553ce10995f4872b7d3224c44fdb8f67c4b604f781cab9ac38864e2e8906
3
+ size 4997026850
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ada71881c8cfc6ed0001b483ce6ae4d18c980ccdee75a955e47fc87eed5873
3
+ size 4966584896
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934f6eb9612521ed1cb8a30d110e470866569b1e704f877a6e91ab3dc46c833e
3
+ size 768670260
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,466 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10732113920
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.gate.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
78
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
81
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
82
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
83
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
84
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
237
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
238
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
249
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
250
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
251
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
252
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
253
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
254
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
255
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
259
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
260
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
262
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
263
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
264
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
265
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
266
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
267
+ "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
268
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
269
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
270
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
271
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
272
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
273
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
274
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
275
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
276
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
277
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
278
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
279
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
280
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00003.bin",
281
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00003.bin",
282
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00003.bin",
283
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00003.bin",
284
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00003.bin",
285
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00003.bin",
286
+ "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
287
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
288
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
289
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
290
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
291
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
292
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
293
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00003.bin",
294
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00003.bin",
295
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00003.bin",
296
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00003.bin",
297
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00003.bin",
298
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00003.bin",
299
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00003.bin",
306
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
309
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
310
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
311
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
312
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00003.bin",
315
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00003.bin",
316
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00003.bin",
317
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00003.bin",
318
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
332
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
333
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
334
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
335
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
336
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
337
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
338
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
339
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
340
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
341
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
342
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
343
+ "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
344
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
345
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
346
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
347
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
348
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
349
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
350
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
351
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
352
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
353
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
354
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
355
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
356
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
357
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
358
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
359
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
360
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
361
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
362
+ "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
363
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
365
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
366
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
367
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
368
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
369
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
370
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
371
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
372
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
373
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
374
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
375
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
376
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
377
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
378
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
379
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
380
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
382
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
384
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
386
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
387
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
390
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
392
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
394
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
396
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
397
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
408
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
409
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
410
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
411
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
412
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
413
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
414
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
415
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
416
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
417
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
418
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
419
+ "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
420
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
421
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
422
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
423
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
424
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
425
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
426
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
427
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
428
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
429
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
430
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
431
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
432
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
433
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
434
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
435
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
436
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
437
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
438
+ "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
439
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
440
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
441
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
442
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
443
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
444
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
445
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00003.bin",
446
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00003.bin",
447
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00003.bin",
448
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00003.bin",
449
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00003.bin",
450
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00003.bin",
451
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00003.bin",
452
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00003.bin",
453
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00003.bin",
454
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00003.bin",
455
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00003.bin",
456
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00003.bin",
457
+ "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00003.bin",
458
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
459
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
460
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
461
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
462
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
463
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
464
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
465
+ }
466
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }