Crystalcareai commited on
Commit
e4b1638
·
1 Parent(s): 9738a0b

Upload 10 files

Browse files
README.md CHANGED
@@ -1,3 +1,146 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ base_model: microsoft/phi-2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: phi-sft-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: `0.3.0`
18
+ ```yaml
19
+ base_model: microsoft/phi-2
20
+ model_type: AutoModelForCausalLM
21
+ tokenizer_type: AutoTokenizer
22
+ trust_remote_code: true
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: tatsu-lab/alpaca
30
+ type: alpaca
31
+
32
+ dataset_prepared_path:
33
+ val_set_size: 0.05
34
+ output_dir: ./phi-sft-out
35
+
36
+ sequence_len: 2048
37
+ sample_packing: false # currently unsupported
38
+ pad_to_sequence_len:
39
+
40
+ adapter:
41
+ lora_model_dir:
42
+ lora_r: 16
43
+ lora_alpha: 32
44
+ lora_dropout: 0.1
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+ lora_modules_to_save:
48
+ - embd
49
+ - lm_head
50
+
51
+ wandb_project: Deepseek Wa
52
+ wandb_entity: lucasatkins81
53
+ wandb_watch:
54
+ wandb_name: Phi2 a6000 FT
55
+ wandb_log_model:
56
+
57
+ gradient_accumulation_steps: 1
58
+ micro_batch_size: 1
59
+ num_epochs: 1.5
60
+ optimizer: paged_adamw_8bit
61
+ adam_beta2: 0.95
62
+ adam_epsilon: 0.00001
63
+ max_grad_norm: 1.0
64
+ lr_scheduler: cosine
65
+ learning_rate: 1e-5
66
+
67
+ train_on_inputs: false
68
+ group_by_length: false
69
+ bf16: true
70
+ fp16: false
71
+ tf32: true
72
+
73
+ gradient_checkpointing: true
74
+ early_stopping_patience:
75
+ resume_from_checkpoint:
76
+ local_rank:
77
+ logging_steps: 1
78
+ xformers_attention:
79
+ flash_attention: true
80
+
81
+ warmup_steps: 100
82
+ evals_per_epoch: 4
83
+ saves_per_epoch: 1
84
+ debug:
85
+ deepspeed:
86
+ weight_decay: 0.1
87
+ fsdp:
88
+ fsdp_config:
89
+ resize_token_embeddings_to_32x: true
90
+ special_tokens:
91
+ pad_token: "<|endoftext|>"
92
+
93
+ ```
94
+
95
+ </details><br>
96
+
97
+ # phi-sft-out
98
+
99
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
100
+ It achieves the following results on the evaluation set:
101
+ - Loss: nan
102
+
103
+ ## Model description
104
+
105
+ More information needed
106
+
107
+ ## Intended uses & limitations
108
+
109
+ More information needed
110
+
111
+ ## Training and evaluation data
112
+
113
+ More information needed
114
+
115
+ ## Training procedure
116
+
117
+ ### Training hyperparameters
118
+
119
+ The following hyperparameters were used during training:
120
+ - learning_rate: 1e-05
121
+ - train_batch_size: 1
122
+ - eval_batch_size: 1
123
+ - seed: 42
124
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
125
+ - lr_scheduler_type: cosine
126
+ - lr_scheduler_warmup_steps: 100
127
+ - num_epochs: 1.5
128
+
129
+ ### Training results
130
+
131
+ | Training Loss | Epoch | Step | Validation Loss |
132
+ |:-------------:|:-----:|:-----:|:---------------:|
133
+ | 1.4382 | 0.0 | 1 | nan |
134
+ | 0.9139 | 0.25 | 12351 | nan |
135
+ | 0.016 | 0.5 | 24702 | nan |
136
+ | 0.0538 | 0.75 | 37053 | nan |
137
+ | 0.6701 | 1.0 | 49404 | nan |
138
+ | 0.0018 | 1.25 | 61755 | nan |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.37.0.dev0
144
+ - Pytorch 2.1.1+cu121
145
+ - Datasets 2.16.1
146
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "PhiForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
10
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
11
+ },
12
+ "embd_pdrop": 0.0,
13
+ "flash_attn": true,
14
+ "flash_rotary": true,
15
+ "fused_dense": true,
16
+ "img_processor": null,
17
+ "initializer_range": 0.02,
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "phi-msft",
20
+ "n_embd": 2560,
21
+ "n_head": 32,
22
+ "n_head_kv": null,
23
+ "n_inner": null,
24
+ "n_layer": 32,
25
+ "n_positions": 2048,
26
+ "resid_pdrop": 0.1,
27
+ "rotary_dim": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.37.0.dev0",
31
+ "use_cache": false,
32
+ "vocab_size": 51200
33
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.0.dev0"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ed2eb29acdd4d92149e484362c47e63aa6a9cfb8d6cb31d303e9236f35697c
3
+ size 4982540319
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e1dde8ac18c8806bbe2c2250ab6037076518faf6a7a0eebb93ec3509b36bbd
3
+ size 839196470
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,332 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5821624320
4
+ },
5
+ "weight_map": {
6
+ "lm_head.linear.bias": "pytorch_model-00002-of-00002.bin",
7
+ "lm_head.linear.weight": "pytorch_model-00002-of-00002.bin",
8
+ "lm_head.ln.bias": "pytorch_model-00002-of-00002.bin",
9
+ "lm_head.ln.weight": "pytorch_model-00002-of-00002.bin",
10
+ "transformer.embd.wte.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.ln.bias": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.ln.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.ln.bias": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.ln.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.1.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.10.ln.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.10.ln.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.10.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.10.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.10.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.10.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.11.ln.bias": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.11.ln.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.11.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.11.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.11.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.11.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.12.ln.bias": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.12.ln.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.12.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.12.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.12.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.12.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.13.ln.bias": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.13.ln.weight": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.13.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.13.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.13.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.13.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.14.ln.bias": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.14.ln.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.14.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.14.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.14.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.14.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.15.ln.bias": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.15.ln.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.15.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.15.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.15.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.15.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.16.ln.bias": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.16.ln.weight": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.16.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.16.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.16.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.16.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.17.ln.bias": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.17.ln.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.17.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.17.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.17.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.17.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.18.ln.bias": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.18.ln.weight": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.18.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.18.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.18.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.18.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.19.ln.bias": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.19.ln.weight": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.19.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.19.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.19.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.19.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.2.ln.bias": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.2.ln.weight": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.2.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.2.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.2.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.2.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.20.ln.bias": "pytorch_model-00001-of-00002.bin",
142
+ "transformer.h.20.ln.weight": "pytorch_model-00001-of-00002.bin",
143
+ "transformer.h.20.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.20.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.20.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.20.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.21.ln.bias": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.21.ln.weight": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.21.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.21.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.21.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.21.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.22.ln.bias": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.22.ln.weight": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.22.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.22.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.22.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.22.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.23.ln.bias": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.23.ln.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.23.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.23.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.23.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.23.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.24.ln.bias": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.24.ln.weight": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.24.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.24.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.24.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.24.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.25.ln.bias": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.25.ln.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.25.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.25.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.25.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.25.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.h.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
200
+ "transformer.h.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
201
+ "transformer.h.26.ln.bias": "pytorch_model-00001-of-00002.bin",
202
+ "transformer.h.26.ln.weight": "pytorch_model-00001-of-00002.bin",
203
+ "transformer.h.26.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
204
+ "transformer.h.26.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
205
+ "transformer.h.26.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
206
+ "transformer.h.26.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "transformer.h.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
208
+ "transformer.h.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
209
+ "transformer.h.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
210
+ "transformer.h.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
211
+ "transformer.h.27.ln.bias": "pytorch_model-00001-of-00002.bin",
212
+ "transformer.h.27.ln.weight": "pytorch_model-00001-of-00002.bin",
213
+ "transformer.h.27.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
214
+ "transformer.h.27.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
215
+ "transformer.h.27.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
216
+ "transformer.h.27.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "transformer.h.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
218
+ "transformer.h.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
219
+ "transformer.h.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
220
+ "transformer.h.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
221
+ "transformer.h.28.ln.bias": "pytorch_model-00001-of-00002.bin",
222
+ "transformer.h.28.ln.weight": "pytorch_model-00001-of-00002.bin",
223
+ "transformer.h.28.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
224
+ "transformer.h.28.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
225
+ "transformer.h.28.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
226
+ "transformer.h.28.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "transformer.h.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
228
+ "transformer.h.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
229
+ "transformer.h.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
230
+ "transformer.h.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
231
+ "transformer.h.29.ln.bias": "pytorch_model-00001-of-00002.bin",
232
+ "transformer.h.29.ln.weight": "pytorch_model-00001-of-00002.bin",
233
+ "transformer.h.29.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
234
+ "transformer.h.29.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
235
+ "transformer.h.29.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
236
+ "transformer.h.29.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
237
+ "transformer.h.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
238
+ "transformer.h.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
239
+ "transformer.h.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
240
+ "transformer.h.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
241
+ "transformer.h.3.ln.bias": "pytorch_model-00001-of-00002.bin",
242
+ "transformer.h.3.ln.weight": "pytorch_model-00001-of-00002.bin",
243
+ "transformer.h.3.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
244
+ "transformer.h.3.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
245
+ "transformer.h.3.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
246
+ "transformer.h.3.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "transformer.h.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
248
+ "transformer.h.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
249
+ "transformer.h.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
250
+ "transformer.h.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
251
+ "transformer.h.30.ln.bias": "pytorch_model-00001-of-00002.bin",
252
+ "transformer.h.30.ln.weight": "pytorch_model-00001-of-00002.bin",
253
+ "transformer.h.30.mixer.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
254
+ "transformer.h.30.mixer.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
255
+ "transformer.h.30.mixer.out_proj.bias": "pytorch_model-00002-of-00002.bin",
256
+ "transformer.h.30.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
257
+ "transformer.h.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
258
+ "transformer.h.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
259
+ "transformer.h.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
260
+ "transformer.h.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
261
+ "transformer.h.31.ln.bias": "pytorch_model-00002-of-00002.bin",
262
+ "transformer.h.31.ln.weight": "pytorch_model-00002-of-00002.bin",
263
+ "transformer.h.31.mixer.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
264
+ "transformer.h.31.mixer.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
265
+ "transformer.h.31.mixer.out_proj.bias": "pytorch_model-00002-of-00002.bin",
266
+ "transformer.h.31.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
267
+ "transformer.h.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
268
+ "transformer.h.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
269
+ "transformer.h.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
270
+ "transformer.h.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
271
+ "transformer.h.4.ln.bias": "pytorch_model-00001-of-00002.bin",
272
+ "transformer.h.4.ln.weight": "pytorch_model-00001-of-00002.bin",
273
+ "transformer.h.4.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
274
+ "transformer.h.4.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
275
+ "transformer.h.4.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
276
+ "transformer.h.4.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "transformer.h.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
278
+ "transformer.h.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
279
+ "transformer.h.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
280
+ "transformer.h.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
281
+ "transformer.h.5.ln.bias": "pytorch_model-00001-of-00002.bin",
282
+ "transformer.h.5.ln.weight": "pytorch_model-00001-of-00002.bin",
283
+ "transformer.h.5.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
284
+ "transformer.h.5.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
285
+ "transformer.h.5.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
286
+ "transformer.h.5.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "transformer.h.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
288
+ "transformer.h.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
289
+ "transformer.h.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
290
+ "transformer.h.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
291
+ "transformer.h.6.ln.bias": "pytorch_model-00001-of-00002.bin",
292
+ "transformer.h.6.ln.weight": "pytorch_model-00001-of-00002.bin",
293
+ "transformer.h.6.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
294
+ "transformer.h.6.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
295
+ "transformer.h.6.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
296
+ "transformer.h.6.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "transformer.h.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
298
+ "transformer.h.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
299
+ "transformer.h.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
300
+ "transformer.h.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
301
+ "transformer.h.7.ln.bias": "pytorch_model-00001-of-00002.bin",
302
+ "transformer.h.7.ln.weight": "pytorch_model-00001-of-00002.bin",
303
+ "transformer.h.7.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
304
+ "transformer.h.7.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
305
+ "transformer.h.7.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
306
+ "transformer.h.7.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
307
+ "transformer.h.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
308
+ "transformer.h.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
309
+ "transformer.h.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
310
+ "transformer.h.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
311
+ "transformer.h.8.ln.bias": "pytorch_model-00001-of-00002.bin",
312
+ "transformer.h.8.ln.weight": "pytorch_model-00001-of-00002.bin",
313
+ "transformer.h.8.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
314
+ "transformer.h.8.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
315
+ "transformer.h.8.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
316
+ "transformer.h.8.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "transformer.h.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
318
+ "transformer.h.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
319
+ "transformer.h.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
320
+ "transformer.h.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
321
+ "transformer.h.9.ln.bias": "pytorch_model-00001-of-00002.bin",
322
+ "transformer.h.9.ln.weight": "pytorch_model-00001-of-00002.bin",
323
+ "transformer.h.9.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
324
+ "transformer.h.9.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
325
+ "transformer.h.9.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
326
+ "transformer.h.9.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
327
+ "transformer.h.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
328
+ "transformer.h.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
329
+ "transformer.h.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
330
+ "transformer.h.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin"
331
+ }
332
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "tokenizer_class": "CodeGenTokenizer",
323
+ "unk_token": "<|endoftext|>"
324
+ }