ehartford commited on
Commit
13e0f8a
1 Parent(s): 59a0553

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "01-ai/Yi-34B-200K",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 7,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 7168,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "max_position_embeddings": 200000,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 56,
16
+ "num_hidden_layers": 60,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 5000000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.35.2",
26
+ "use_cache": true,
27
+ "vocab_size": 64000
28
+ }
configs/dolphin-yi-34b.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: /workspace/models/Yi-34B-200K
2
+ model_type: LlamaForCausalLM
3
+ tokenizer_type: AutoTokenizer
4
+ is_llama_derived_model: true
5
+
6
+ load_in_8bit: false
7
+ load_in_4bit: true
8
+ strict: false
9
+
10
+ datasets:
11
+ - path: /workspace/datasets/dolphin/dolphin201.jsonl
12
+ type: alpaca_w_system.load_open_orca_chatml
13
+ - path: /workspace/datasets/Synthia-converted.jsonl
14
+ type: alpaca_w_system.load_open_orca_chatml
15
+ - path: /workspace/datasets/WizardLM_evol_instruct_cleaned.jsonl
16
+ type: sharegpt
17
+ conversation: chatml
18
+ - path: /workspace/datasets/not_samantha_norefusals.jsonl
19
+ type: sharegpt
20
+ conversation: chatml
21
+
22
+ dataset_prepared_path:
23
+ val_set_size: 0.01
24
+ output_dir: /workspace/dolphin-2.2-yi-34b-200k
25
+
26
+ adapter: qlora
27
+ lora_model_dir:
28
+
29
+ sequence_len: 4096
30
+ sample_packing: true
31
+ pad_to_sequence_len: true
32
+
33
+ lora_r: 32
34
+ lora_alpha: 16
35
+ lora_dropout: 0.05
36
+ lora_target_modules:
37
+ lora_target_linear: true
38
+ lora_fan_in_fan_out:
39
+
40
+ lora_modules_to_save:
41
+ - embed_tokens
42
+ - lm_head
43
+
44
+ wandb_project: dolphin
45
+ wandb_entity:
46
+ wandb_watch:
47
+ wandb_run_id:
48
+ wandb_log_model:
49
+
50
+ gradient_accumulation_steps: 4
51
+ micro_batch_size: 3
52
+ num_epochs: 4
53
+ optimizer: paged_adamw_32bit
54
+ lr_scheduler: cosine
55
+ learning_rate: 0.0003
56
+
57
+ train_on_inputs: false
58
+ group_by_length: false
59
+ bf16: true
60
+ fp16: false
61
+ tf32: false
62
+
63
+ gradient_checkpointing: true
64
+ early_stopping_patience:
65
+ resume_from_checkpoint:
66
+ local_rank:
67
+ logging_steps: 1
68
+ xformers_attention:
69
+ flash_attention: true
70
+
71
+ warmup_steps: 100
72
+ eval_steps:
73
+ save_steps: 0.01
74
+ debug:
75
+ deepspeed: deepspeed/zero3.json
76
+ weight_decay: 0.01
77
+ fsdp:
78
+ fsdp_config:
79
+ special_tokens:
80
+ eos_token: "<|im_end|>"
81
+ tokens:
82
+ - "<|im_start|>"
83
+ - "<|im_end|>"
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 7,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.35.2"
7
+ }
pytorch_model-00001-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc7093c5da6565784626fbca2ccfe948ced7a8e0d5d70fe1cf7c0349c68efb1
3
+ size 4793137945
pytorch_model-00002-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649c352eb9ec90e855d501ac9fb339350172cbd23f676edc580c3671d55ac1a6
3
+ size 4756467785
pytorch_model-00003-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfb7e7bfd2893f6205ae13de39ccc61656bfba16b4dab99e238d9a959ce352f
3
+ size 4991379521
pytorch_model-00004-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd69e7c8b00d855be8a2e501110f580ab38eead8f15ee2739f8928ed3769d2d0
3
+ size 4756467885
pytorch_model-00005-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57d1c51fe84745aba0931d4c71bc593689a3b3ed5268158f026879beaf613f0
3
+ size 4756467785
pytorch_model-00006-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6b15278215da0497e8829c8e0754766379f7916dc1cd1e999af7917c97b99f
3
+ size 4991379585
pytorch_model-00007-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd10d8bee8108741560da270cc6137282fdad121bf7d1d9e0bd6853c5a2107bd
3
+ size 4756467885
pytorch_model-00008-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c35cac05eee5788a4db48c0845c0cbc334999fefcfc1621546d7dfe698548dc
3
+ size 4756467785
pytorch_model-00009-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602df47ab9870a3809aeec07358922b89426e8bf67fe0cf5b6248dfe4ec8df0f
3
+ size 4991379585
pytorch_model-00010-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b4186e03b34b01b03024db50e754218d6e1f5cf679af0d45ae987aab791b38
3
+ size 4756467885
pytorch_model-00011-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfc9514a6e034545082ac8d57f0699e6b8f3afbda66a6787867ed1c3827c753
3
+ size 4756467785
pytorch_model-00012-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaed476486471ace3e04211de8f538f384aa9e4f8d0587e0440cd3607125ee5d
3
+ size 4991379585
pytorch_model-00013-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a287ece124e6c9d4996ccc9af36f3b756b93284b5ee8a671b36c61f73fa91cd1
3
+ size 4756467885
pytorch_model-00014-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dc8e548e1e5721b3188d35cb99b686b935b374da0abf796872ddb475eefeb5f
3
+ size 4756467785
pytorch_model-00015-of-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510178f69465fae45c0bfc5c0765c1e79be42c25de8cd3b415088dd686e67d39
3
+ size 1211150446
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,550 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 68777834496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00015-of-00015.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
323
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
324
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
325
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
326
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
327
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
328
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
329
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
330
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
331
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
332
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
333
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
334
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
335
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
336
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
337
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
338
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
339
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
340
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
341
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
342
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
343
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
344
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
345
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
346
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
347
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
348
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
349
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
350
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
351
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
352
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
353
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
354
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
355
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
356
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
357
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
358
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
359
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
360
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
361
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
362
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
363
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
364
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
365
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
366
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
367
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
368
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
369
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
370
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
371
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
372
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
373
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
374
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
375
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
376
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
377
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
378
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
379
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
380
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
381
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
382
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
383
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
384
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
385
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
386
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
387
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
388
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
389
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
390
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
391
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
392
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
393
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
394
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
395
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
396
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
397
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
398
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
399
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
400
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
401
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
402
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
403
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
404
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
405
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
406
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
407
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
408
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
409
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
410
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
411
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
412
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
413
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
414
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
415
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
416
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
417
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
418
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
419
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
420
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
421
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
422
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
423
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
424
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
425
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
426
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
427
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
428
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
429
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
430
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
431
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
432
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
433
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
434
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
435
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
436
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
437
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
438
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
439
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
440
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
441
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
442
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
443
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
444
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
445
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
446
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
447
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
448
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
449
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
450
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
451
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
452
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
453
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
454
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
455
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
456
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
457
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
458
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
459
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
460
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
461
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
462
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
463
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
464
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
465
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
466
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
467
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
468
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
469
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
470
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
471
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
472
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
473
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
474
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
475
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
476
+ "model.layers.56.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
477
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
478
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
479
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
480
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
481
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
482
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
483
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
484
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
485
+ "model.layers.57.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
486
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
487
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
488
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
489
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
490
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
491
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
492
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
493
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
494
+ "model.layers.58.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
495
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
496
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
497
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
498
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
499
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
500
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
501
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
502
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
503
+ "model.layers.59.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
504
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
505
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
506
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
507
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
508
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
509
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
510
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
511
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
512
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
513
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
514
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
515
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
516
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
517
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
518
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
519
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
520
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
521
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
522
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
523
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
524
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
525
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
526
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
527
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
528
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
529
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
530
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
531
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
532
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
533
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
534
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
535
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
536
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
537
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
538
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
539
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
540
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
541
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
542
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
543
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
544
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
545
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
546
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
547
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
548
+ "model.norm.weight": "pytorch_model-00015-of-00015.bin"
549
+ }
550
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": {
4
+ "content": "<|im_end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "pad_token": "<unk>",
11
+ "unk_token": "<unk>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|startoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "6": {
28
+ "content": "<|im_start|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "7": {
36
+ "content": "<|im_end|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ }
43
+ },
44
+ "bos_token": "<|startoftext|>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "<|im_end|>",
47
+ "legacy": true,
48
+ "model_max_length": 200000,
49
+ "pad_token": "<unk>",
50
+ "sp_model_kwargs": {},
51
+ "tokenizer_class": "LlamaTokenizer",
52
+ "unk_token": "<unk>",
53
+ "use_default_system_prompt": false
54
+ }