ping98k commited on
Commit
1885b87
1 Parent(s): fe78392

Upload 11 files

Browse files
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: scb10x/typhoon-7b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: 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: scb10x/typhoon-7b
20
+ model_type: MistralForCausalLM
21
+ tokenizer_type: LlamaTokenizer
22
+ is_mistral_derived_model: true
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: finetune-data.jsonl
30
+ type: alpaca
31
+ dataset_prepared_path: last_run_prepared
32
+ val_set_size: 0.05
33
+ output_dir: ./out
34
+
35
+ sequence_len: 8192
36
+ sample_packing: false
37
+ pad_to_sequence_len: true
38
+ eval_sample_packing: false
39
+
40
+ wandb_project: typhoon-7b
41
+ wandb_entity:
42
+ wandb_watch:
43
+ wandb_name:
44
+ wandb_log_model:
45
+
46
+ gradient_accumulation_steps: 8
47
+ micro_batch_size: 1
48
+ num_epochs: 4
49
+ optimizer: adamw_bnb_8bit
50
+ lr_scheduler: cosine
51
+ learning_rate: 0.000005
52
+
53
+ train_on_inputs: false
54
+ group_by_length: false
55
+ bf16: true
56
+ fp16: false
57
+ tf32: false
58
+
59
+ gradient_checkpointing: true
60
+ early_stopping_patience:
61
+ resume_from_checkpoint:
62
+ local_rank:
63
+ logging_steps: 1
64
+ xformers_attention:
65
+ flash_attention: true
66
+
67
+ warmup_ratio: 0.05
68
+ evals_per_epoch: 5
69
+ eval_table_size:
70
+ eval_table_max_new_tokens: 128
71
+ saves_per_epoch: 5
72
+ save_total_limit: 10
73
+ debug:
74
+ deepspeed:
75
+ weight_decay: 0.0
76
+ fsdp:
77
+ fsdp_config:
78
+ special_tokens:
79
+ bos_token: "<s>"
80
+ eos_token: "</s>"
81
+ unk_token: "<unk>"
82
+
83
+ ```
84
+
85
+ </details><br>
86
+
87
+ # out
88
+
89
+ This model is a fine-tuned version of [scb10x/typhoon-7b](https://huggingface.co/scb10x/typhoon-7b) on the None dataset.
90
+ It achieves the following results on the evaluation set:
91
+ - Loss: 0.7682
92
+
93
+ ## Model description
94
+
95
+ More information needed
96
+
97
+ ## Intended uses & limitations
98
+
99
+ More information needed
100
+
101
+ ## Training and evaluation data
102
+
103
+ More information needed
104
+
105
+ ## Training procedure
106
+
107
+ ### Training hyperparameters
108
+
109
+ The following hyperparameters were used during training:
110
+ - learning_rate: 5e-06
111
+ - train_batch_size: 1
112
+ - eval_batch_size: 1
113
+ - seed: 42
114
+ - distributed_type: multi-GPU
115
+ - num_devices: 2
116
+ - gradient_accumulation_steps: 8
117
+ - total_train_batch_size: 16
118
+ - total_eval_batch_size: 2
119
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
120
+ - lr_scheduler_type: cosine
121
+ - lr_scheduler_warmup_steps: 23
122
+ - num_epochs: 4
123
+
124
+ ### Training results
125
+
126
+ | Training Loss | Epoch | Step | Validation Loss |
127
+ |:-------------:|:-----:|:----:|:---------------:|
128
+ | 3.4821 | 0.0 | 1 | 4.2554 |
129
+ | 0.7752 | 0.2 | 48 | 0.7134 |
130
+ | 0.7287 | 0.41 | 96 | 0.6403 |
131
+ | 0.6135 | 0.61 | 144 | 0.6305 |
132
+ | 0.7828 | 0.81 | 192 | 0.6020 |
133
+ | 0.3375 | 1.02 | 240 | 0.5951 |
134
+ | 0.471 | 1.22 | 288 | 0.6191 |
135
+ | 0.2798 | 1.42 | 336 | 0.6249 |
136
+ | 0.5071 | 1.63 | 384 | 0.6213 |
137
+ | 0.2792 | 1.83 | 432 | 0.6176 |
138
+ | 0.069 | 2.03 | 480 | 0.6393 |
139
+ | 0.0742 | 2.23 | 528 | 0.6877 |
140
+ | 0.1309 | 2.44 | 576 | 0.6892 |
141
+ | 0.0349 | 2.64 | 624 | 0.6701 |
142
+ | 0.0639 | 2.84 | 672 | 0.6657 |
143
+ | 0.0273 | 3.05 | 720 | 0.6895 |
144
+ | 0.0311 | 3.25 | 768 | 0.7606 |
145
+ | 0.0307 | 3.45 | 816 | 0.7636 |
146
+ | 0.0791 | 3.66 | 864 | 0.7664 |
147
+ | 0.0747 | 3.86 | 912 | 0.7682 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.37.0.dev0
153
+ - Pytorch 2.0.1+cu118
154
+ - Datasets 2.16.1
155
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "scb10x/typhoon-7b",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.37.0.dev0",
24
+ "use_cache": false,
25
+ "vocab_size": 35219
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0.dev0"
6
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e267af4e4cccd3b5fbd33376bc3d94eb02e7ed5a073c4ff1082e19f931b8a81
3
+ size 4801743249
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:471451b514abdf82dbc6fef3a5cac90730bdc7d62737667e91ed42ee9b563d5b
3
+ size 4983009101
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a023e4beccb0f2b397c05aecb04c6d45ef1d66f4946802a4c8599a59bbac57
3
+ size 4983009101
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3777787dcef723157cb237ae48ed9880fc0c6e9270b38230e3c6393676b71e5b
3
+ size 3526641335
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18294300672
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
296
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0260fe22b9efe79df479f2619890767ab9c44912142f21648f1980c32297ed
3
+ size 562945
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "trust_remote_code": false,
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true,
43
+ "use_fast": true
44
+ }