Zoyd commited on
Commit
dc450df
1 Parent(s): 8497968

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/Phi-3-medium-128k-instruct
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: outputs/phi3-medium-128k-14b.8e6
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-medium-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
+ use_wandb: true
29
+ wandb_project: shisa-v2
30
+ wandb_entity: augmxnt
31
+ wandb_name: shisa-llama3-70b-v1.8e6
32
+
33
+ chat_template: chatml
34
+ datasets:
35
+ - path: augmxnt/ultra-orca-boros-en-ja-v1
36
+ type: sharegpt
37
+ dataset_prepared_path: last_run_prepared
38
+ val_set_size: 0.05
39
+ output_dir: ./outputs/phi3-medium-128k-14b.8e6
40
+
41
+ sequence_len: 4096
42
+ sample_packing: true
43
+ pad_to_sequence_len: true
44
+ neftune_noise_alpha: 5
45
+
46
+ gradient_accumulation_steps: 4
47
+ micro_batch_size: 2
48
+ num_epochs: 3
49
+ optimizer: paged_adamw_8bit
50
+ adam_beta2: 0.95
51
+ adam_epsilon: 0.00001
52
+ max_grad_norm: 1.0
53
+ lr_scheduler: linear
54
+ learning_rate: 0.000008
55
+
56
+ train_on_inputs: false
57
+ group_by_length: false
58
+ bf16: auto
59
+ fp16:
60
+ tf32: true
61
+
62
+ gradient_checkpointing: true
63
+ gradient_checkpointing_kwargs:
64
+ use_reentrant: True
65
+ early_stopping_patience:
66
+ resume_from_checkpoint:
67
+ local_rank:
68
+ logging_steps: 1
69
+ xformers_attention:
70
+ flash_attention: true
71
+
72
+ warmup_steps: 100
73
+ evals_per_epoch: 4
74
+ saves_per_epoch: 1
75
+ debug:
76
+ deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
77
+ weight_decay: 0.1
78
+ fsdp:
79
+ fsdp_config:
80
+ resize_token_embeddings_to_32x: true
81
+ special_tokens:
82
+ pad_token: "<|endoftext|>"
83
+
84
+ ```
85
+
86
+ </details><br>
87
+
88
+ # outputs/phi3-medium-128k-14b.8e6
89
+
90
+ This model is a fine-tuned version of [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) on the None dataset.
91
+ It achieves the following results on the evaluation set:
92
+ - Loss: 0.3339
93
+
94
+ ## Model description
95
+
96
+ More information needed
97
+
98
+ ## Intended uses & limitations
99
+
100
+ More information needed
101
+
102
+ ## Training and evaluation data
103
+
104
+ More information needed
105
+
106
+ ## Training procedure
107
+
108
+ ### Training hyperparameters
109
+
110
+ The following hyperparameters were used during training:
111
+ - learning_rate: 8e-06
112
+ - train_batch_size: 2
113
+ - eval_batch_size: 2
114
+ - seed: 42
115
+ - distributed_type: multi-GPU
116
+ - num_devices: 8
117
+ - gradient_accumulation_steps: 4
118
+ - total_train_batch_size: 64
119
+ - total_eval_batch_size: 16
120
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
121
+ - lr_scheduler_type: linear
122
+ - lr_scheduler_warmup_steps: 100
123
+ - num_epochs: 3
124
+
125
+ ### Training results
126
+
127
+ | Training Loss | Epoch | Step | Validation Loss |
128
+ |:-------------:|:------:|:----:|:---------------:|
129
+ | 2.8309 | 0.0021 | 1 | 2.3406 |
130
+ | 0.7688 | 0.2513 | 121 | 0.4958 |
131
+ | 0.6435 | 0.5026 | 242 | 0.3830 |
132
+ | 0.5286 | 0.7539 | 363 | 0.3626 |
133
+ | 0.5559 | 1.0052 | 484 | 0.3549 |
134
+ | 0.4651 | 1.2425 | 605 | 0.3486 |
135
+ | 0.5294 | 1.4938 | 726 | 0.3432 |
136
+ | 0.5453 | 1.7451 | 847 | 0.3392 |
137
+ | 0.5258 | 1.9964 | 968 | 0.3376 |
138
+ | 0.4805 | 2.2331 | 1089 | 0.3357 |
139
+ | 0.4552 | 2.4844 | 1210 | 0.3352 |
140
+ | 0.5358 | 2.7357 | 1331 | 0.3339 |
141
+
142
+
143
+ ### Framework versions
144
+
145
+ - Transformers 4.40.2
146
+ - Pytorch 2.3.0+cu121
147
+ - Datasets 2.19.1
148
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-medium-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-medium-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": 5120,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 17920,
18
+ "max_position_embeddings": 131072,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 40,
21
+ "num_hidden_layers": 40,
22
+ "num_key_value_heads": 10,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": null,
25
+ "resid_pdrop": 0.0,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "long_factor": [
29
+ 1.0,
30
+ 1.0,
31
+ 1.0,
32
+ 1.0,
33
+ 1.0,
34
+ 1.0,
35
+ 1.0,
36
+ 1.0,
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.25,
43
+ 1.25,
44
+ 1.5,
45
+ 2.0,
46
+ 2.75,
47
+ 5.75,
48
+ 5.75,
49
+ 6.5,
50
+ 9.25,
51
+ 11.0,
52
+ 13.25,
53
+ 19.25,
54
+ 19.75,
55
+ 19.75,
56
+ 21.25,
57
+ 21.5,
58
+ 26.5,
59
+ 30.0,
60
+ 33.75,
61
+ 35.25,
62
+ 38.5,
63
+ 42.0,
64
+ 42.25,
65
+ 46.0,
66
+ 47.0,
67
+ 50.0,
68
+ 50.5,
69
+ 51.0,
70
+ 52.0,
71
+ 52.75,
72
+ 53.75,
73
+ 54.75,
74
+ 57.0,
75
+ 57.25,
76
+ 58.5,
77
+ 59.25,
78
+ 59.5,
79
+ 62.0,
80
+ 62.5,
81
+ 62.75,
82
+ 63.25,
83
+ 63.25,
84
+ 63.25,
85
+ 63.75,
86
+ 64.0,
87
+ 64.0,
88
+ 64.25,
89
+ 64.5,
90
+ 64.5,
91
+ 65.0,
92
+ 65.0
93
+ ],
94
+ "short_factor": [
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.01,
102
+ 1.02,
103
+ 1.02,
104
+ 1.04,
105
+ 1.04,
106
+ 1.07,
107
+ 1.07,
108
+ 1.1,
109
+ 1.3000000000000003,
110
+ 1.3000000000000003,
111
+ 1.5000000000000004,
112
+ 1.5700000000000005,
113
+ 1.9000000000000008,
114
+ 2.3100000000000014,
115
+ 2.759999999999992,
116
+ 3.3899999999999784,
117
+ 3.9399999999999666,
118
+ 4.009999999999965,
119
+ 4.289999999999959,
120
+ 4.349999999999958,
121
+ 5.349999999999937,
122
+ 6.659999999999909,
123
+ 7.029999999999901,
124
+ 7.51999999999989,
125
+ 8.00999999999988,
126
+ 8.249999999999876,
127
+ 8.279999999999875,
128
+ 9.629999999999846,
129
+ 9.89999999999984,
130
+ 10.589999999999826,
131
+ 11.049999999999816,
132
+ 11.7899999999998,
133
+ 12.189999999999792,
134
+ 12.889999999999777,
135
+ 13.129999999999772,
136
+ 13.16999999999977,
137
+ 13.20999999999977,
138
+ 13.479999999999764,
139
+ 13.539999999999763,
140
+ 13.779999999999758,
141
+ 13.929999999999755,
142
+ 14.429999999999744,
143
+ 14.759999999999737,
144
+ 15.149999999999729,
145
+ 15.419999999999723,
146
+ 15.53999999999972,
147
+ 15.659999999999718,
148
+ 15.749999999999716,
149
+ 15.759999999999716,
150
+ 15.799999999999715,
151
+ 16.05999999999971,
152
+ 16.079999999999714,
153
+ 16.11999999999972,
154
+ 16.11999999999972,
155
+ 16.18999999999973,
156
+ 16.31999999999975,
157
+ 16.539999999999786,
158
+ 16.799999999999827
159
+ ],
160
+ "type": "su"
161
+ },
162
+ "rope_theta": 10000.0,
163
+ "sliding_window": 131072,
164
+ "tie_word_embeddings": false,
165
+ "torch_dtype": "bfloat16",
166
+ "transformers_version": "4.40.2",
167
+ "use_cache": false,
168
+ "vocab_size": 32064,
169
+ "quantization_config": {
170
+ "quant_method": "exl2",
171
+ "version": "0.0.21",
172
+ "bits": 5.0,
173
+ "head_bits": 6,
174
+ "calibration": {
175
+ "rows": 100,
176
+ "length": 2048,
177
+ "dataset": "(default)"
178
+ }
179
+ }
180
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 32000,
7
+ 32001,
8
+ 32007
9
+ ],
10
+ "pad_token_id": 32000,
11
+ "transformers_version": "4.40.2"
12
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27920476160
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.32.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.33.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.34.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
183
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
184
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
185
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
186
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.35.self_attn.qkv_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
191
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
192
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
193
+ "model.layers.36.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
194
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
195
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
196
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
197
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
198
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.37.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
200
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
201
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.38.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
206
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.39.self_attn.qkv_proj.weight": "model-00006-of-00006.safetensors",
212
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
213
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
214
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
215
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
226
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00006.safetensors",
227
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
228
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
229
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00006.safetensors",
230
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
231
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
232
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
233
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
234
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
235
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
236
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
237
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
238
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
239
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
240
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
241
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
242
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
243
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
244
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00006.safetensors",
245
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
246
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
247
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00006.safetensors",
248
+ "model.norm.weight": "model-00006-of-00006.safetensors"
249
+ }
250
+ }
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fdd11d96a65ca4abbf067d9407c7c9d335ef8895087144e4320c5f59e8ec49
3
+ size 8541490752
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c301e446170ae7bc8552006e365f5c4151940e4decf5bd57f8d1f0eb965c18
3
+ size 428692056
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|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": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
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": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
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
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 131072,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }