sosoai commited on
Commit
98c37b1
1 Parent(s): acb1a41

Upload 11 files

Browse files
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/Phi-3-mini-128k-instruct
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: phi3-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: `0.4.0`
18
+ ```yaml
19
+ base_model: microsoft/Phi-3-mini-128k-instruct
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: sosoai/mixed_dataset
30
+ type: alpaca
31
+
32
+ dataset_prepared_path:
33
+ val_set_size: 0.05
34
+ output_dir: ./phi3-sft-out
35
+
36
+ sequence_len: 2048
37
+ sample_packing: true
38
+ pad_to_sequence_len: true
39
+
40
+ adapter:
41
+ lora_model_dir:
42
+ lora_r:
43
+ lora_alpha:
44
+ lora_dropout:
45
+ lora_target_linear:
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project:
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 1
55
+ micro_batch_size: 2
56
+ num_epochs: 5
57
+ optimizer: adamw_torch
58
+ adam_beta2: 0.95
59
+ adam_epsilon: 0.00001
60
+ max_grad_norm: 1.0
61
+ lr_scheduler: cosine
62
+ learning_rate: 0.000003
63
+
64
+ train_on_inputs: false
65
+ group_by_length: false
66
+ bf16: auto
67
+ fp16:
68
+ tf32: true
69
+
70
+ gradient_checkpointing: true
71
+ gradient_checkpointing_kwargs:
72
+ use_reentrant: True
73
+ early_stopping_patience:
74
+ resume_from_checkpoint:
75
+ local_rank:
76
+ logging_steps: 1
77
+ xformers_attention:
78
+ flash_attention: true
79
+
80
+ warmup_steps: 100
81
+ eval_sample_packing: False
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
+ # phi3-sft-out
98
+
99
+ This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the None dataset.
100
+ It achieves the following results on the evaluation set:
101
+ - Loss: 1.2406
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: 3e-06
121
+ - train_batch_size: 2
122
+ - eval_batch_size: 2
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: 5
128
+
129
+ ### Training results
130
+
131
+ | Training Loss | Epoch | Step | Validation Loss |
132
+ |:-------------:|:-----:|:----:|:---------------:|
133
+ | 4.6772 | 0.0 | 1 | 1.3794 |
134
+ | 3.1471 | 0.25 | 175 | 1.2942 |
135
+ | 3.0306 | 0.5 | 350 | 1.2572 |
136
+ | 2.7486 | 0.75 | 525 | 1.2491 |
137
+ | 2.7702 | 1.0 | 700 | 1.2467 |
138
+ | 2.6302 | 1.24 | 875 | 1.2458 |
139
+ | 2.8356 | 1.49 | 1050 | 1.2436 |
140
+ | 2.7697 | 1.74 | 1225 | 1.2418 |
141
+ | 2.7226 | 2.0 | 1400 | 1.2415 |
142
+ | 2.7363 | 2.23 | 1575 | 1.2411 |
143
+ | 2.6754 | 2.48 | 1750 | 1.2407 |
144
+ | 2.9697 | 2.73 | 1925 | 1.2407 |
145
+ | 2.6213 | 2.99 | 2100 | 1.2406 |
146
+ | 2.6752 | 3.23 | 2275 | 1.2407 |
147
+ | 2.7226 | 3.48 | 2450 | 1.2404 |
148
+ | 2.6131 | 3.73 | 2625 | 1.2405 |
149
+ | 2.7255 | 3.98 | 2800 | 1.2404 |
150
+ | 2.7335 | 4.21 | 2975 | 1.2404 |
151
+ | 2.7924 | 4.46 | 3150 | 1.2406 |
152
+ | 2.6851 | 4.71 | 3325 | 1.2406 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.40.0.dev0
158
+ - Pytorch 2.1.1
159
+ - Datasets 2.15.0
160
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/code|>": 32014,
3
+ "<|/data|>": 32033,
4
+ "<|/inst|>": 32037,
5
+ "<|/query|>": 32031,
6
+ "<|/sys|>": 32035,
7
+ "<|assistant_mask|>": 32017,
8
+ "<|assistant|>": 32001,
9
+ "<|calc|>": 32012,
10
+ "<|code|>": 32013,
11
+ "<|continue|>": 32009,
12
+ "<|data|>": 32032,
13
+ "<|diff_marker|>": 32025,
14
+ "<|disc_sep|>": 32029,
15
+ "<|disc_start|>": 32028,
16
+ "<|disc_thread|><|query|>": 32030,
17
+ "<|endoftext|>": 32000,
18
+ "<|end|>": 32007,
19
+ "<|fim_middle|>": 32021,
20
+ "<|fim_prefix|>": 32020,
21
+ "<|fim_suffix|>": 32022,
22
+ "<|function_call|>": 32005,
23
+ "<|function_list|>": 32011,
24
+ "<|function_output|>": 32003,
25
+ "<|ghissue|>": 32026,
26
+ "<|ghreview|>": 32027,
27
+ "<|inst|>": 32036,
28
+ "<|ipynb_marker|>": 32024,
29
+ "<|message|>": 32019,
30
+ "<|meta_start|>": 32023,
31
+ "<|raw|>": 32008,
32
+ "<|resource|>": 32016,
33
+ "<|start|>": 32018,
34
+ "<|step|>": 32002,
35
+ "<|summary|>": 32015,
36
+ "<|system|>": 32006,
37
+ "<|sys|>": 32034,
38
+ "<|tag|>": 32004,
39
+ "<|user|>": 32010
40
+ }
config.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "resid_pdrop": 0.0,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "long_factor": [
29
+ 1.0299999713897705,
30
+ 1.0499999523162842,
31
+ 1.0499999523162842,
32
+ 1.0799999237060547,
33
+ 1.2299998998641968,
34
+ 1.2299998998641968,
35
+ 1.2999999523162842,
36
+ 1.4499999284744263,
37
+ 1.5999999046325684,
38
+ 1.6499998569488525,
39
+ 1.8999998569488525,
40
+ 2.859999895095825,
41
+ 3.68999981880188,
42
+ 5.419999599456787,
43
+ 5.489999771118164,
44
+ 5.489999771118164,
45
+ 9.09000015258789,
46
+ 11.579999923706055,
47
+ 15.65999984741211,
48
+ 15.769999504089355,
49
+ 15.789999961853027,
50
+ 18.360000610351562,
51
+ 21.989999771118164,
52
+ 23.079999923706055,
53
+ 30.009998321533203,
54
+ 32.35000228881836,
55
+ 32.590003967285156,
56
+ 35.56000518798828,
57
+ 39.95000457763672,
58
+ 53.840003967285156,
59
+ 56.20000457763672,
60
+ 57.95000457763672,
61
+ 59.29000473022461,
62
+ 59.77000427246094,
63
+ 59.920005798339844,
64
+ 61.190006256103516,
65
+ 61.96000671386719,
66
+ 62.50000762939453,
67
+ 63.3700065612793,
68
+ 63.48000717163086,
69
+ 63.48000717163086,
70
+ 63.66000747680664,
71
+ 63.850006103515625,
72
+ 64.08000946044922,
73
+ 64.760009765625,
74
+ 64.80001068115234,
75
+ 64.81001281738281,
76
+ 64.81001281738281
77
+ ],
78
+ "short_factor": [
79
+ 1.05,
80
+ 1.05,
81
+ 1.05,
82
+ 1.1,
83
+ 1.1,
84
+ 1.1500000000000001,
85
+ 1.2000000000000002,
86
+ 1.2500000000000002,
87
+ 1.3000000000000003,
88
+ 1.3500000000000003,
89
+ 1.5000000000000004,
90
+ 2.000000000000001,
91
+ 2.000000000000001,
92
+ 2.000000000000001,
93
+ 2.000000000000001,
94
+ 2.000000000000001,
95
+ 2.000000000000001,
96
+ 2.000000000000001,
97
+ 2.000000000000001,
98
+ 2.000000000000001,
99
+ 2.000000000000001,
100
+ 2.000000000000001,
101
+ 2.000000000000001,
102
+ 2.000000000000001,
103
+ 2.000000000000001,
104
+ 2.000000000000001,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.0500000000000007,
112
+ 2.0500000000000007,
113
+ 2.0500000000000007,
114
+ 2.1000000000000005,
115
+ 2.1000000000000005,
116
+ 2.1000000000000005,
117
+ 2.1500000000000004,
118
+ 2.1500000000000004,
119
+ 2.3499999999999996,
120
+ 2.549999999999999,
121
+ 2.5999999999999988,
122
+ 2.5999999999999988,
123
+ 2.7499999999999982,
124
+ 2.849999999999998,
125
+ 2.849999999999998,
126
+ 2.9499999999999975
127
+ ],
128
+ "type": "su"
129
+ },
130
+ "rope_theta": 10000.0,
131
+ "sliding_window": 262144,
132
+ "tie_word_embeddings": false,
133
+ "torch_dtype": "bfloat16",
134
+ "transformers_version": "4.40.0.dev0",
135
+ "use_cache": false,
136
+ "vocab_size": 32064
137
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 32000,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.40.0.dev0"
11
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d812ca95e19dcb5990fa030c0c54d60b92dacc76c1c53fd4c1a3c0e686bc8dae
3
+ size 4972520014
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e82727707345582ec74bb710d5bcc3b4a4d29b103259e94c46191b55816c978
3
+ size 2669708640
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7642159104
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
95
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
96
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
98
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
99
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
102
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
104
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
108
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
111
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
113
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
114
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
116
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
119
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
120
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
122
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
123
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
132
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
140
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.4.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.4.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.5.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.5.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.6.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
180
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
181
+ "model.layers.6.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "model.layers.7.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
185
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
186
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
187
+ "model.layers.7.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
188
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
189
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
190
+ "model.layers.8.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
192
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.layers.8.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "model.layers.9.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.9.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
201
+ }
202
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,349 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|step|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|function_output|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|tag|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|function_call|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|raw|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|continue|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|function_list|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|calc|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|code|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|/code|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|summary|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|resource|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|assistant_mask|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|start|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|message|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|fim_prefix|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|fim_middle|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|fim_suffix|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|meta_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|ipynb_marker|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|diff_marker|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|ghissue|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|ghreview|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|disc_start|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|disc_sep|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|disc_thread|><|query|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|/query|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|data|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|/data|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|sys|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|/sys|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|inst|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|/inst|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ }
333
+ },
334
+ "additional_special_tokens": [
335
+ "<|/inst|>"
336
+ ],
337
+ "bos_token": "<s>",
338
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
+ "clean_up_tokenization_spaces": false,
340
+ "eos_token": "<|endoftext|>",
341
+ "legacy": false,
342
+ "model_max_length": 131072,
343
+ "pad_token": "<|endoftext|>",
344
+ "padding_side": "left",
345
+ "sp_model_kwargs": {},
346
+ "tokenizer_class": "LlamaTokenizer",
347
+ "unk_token": "<unk>",
348
+ "use_default_system_prompt": false
349
+ }