Lukas Kuhn commited on
Commit
055df35
1 Parent(s): f81e924

release 0.1

Browse files
README.md ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ base_model: codellama/CodeLlama-7b-hf
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: `0.4.0`
18
+ ```yaml
19
+ base_model: codellama/CodeLlama-7b-hf
20
+ tokenizer_type: LlamaTokenizer
21
+ is_llama_derived_model: true
22
+
23
+ load_in_8bit: false
24
+ load_in_4bit: false
25
+ strict: false
26
+
27
+ datasets:
28
+ - path: wndknd/stata
29
+ type: completion
30
+ dataset_prepared_path: last_run_prepared
31
+ val_set_size: 0.05
32
+ output_dir: ./out
33
+
34
+ sequence_len: 4096
35
+ sample_packing: true
36
+ pad_to_sequence_len: true
37
+
38
+ adapter:
39
+ lora_model_dir:
40
+ lora_r:
41
+ lora_alpha:
42
+ lora_dropout:
43
+ lora_target_linear:
44
+ lora_fan_in_fan_out:
45
+
46
+ wandb_project:
47
+ wandb_entity:
48
+ wandb_watch:
49
+ wandb_name:
50
+ wandb_log_model:
51
+
52
+ gradient_accumulation_steps: 1
53
+ micro_batch_size: 1
54
+ num_epochs: 1
55
+ optimizer: adamw_bnb_8bit
56
+ lr_scheduler: cosine
57
+ learning_rate: 0.0002
58
+
59
+ train_on_inputs: false
60
+ group_by_length: false
61
+ bf16: auto
62
+ fp16:
63
+ tf32: false
64
+
65
+ gradient_checkpointing: true
66
+ early_stopping_patience:
67
+ resume_from_checkpoint:
68
+ local_rank:
69
+ logging_steps: 1
70
+ xformers_attention:
71
+ flash_attention: true
72
+ flash_attn_cross_entropy: false
73
+ flash_attn_rms_norm: true
74
+ flash_attn_fuse_qkv: false
75
+ flash_attn_fuse_mlp: true
76
+
77
+ warmup_steps: 100
78
+ evals_per_epoch: 4
79
+ eval_table_size:
80
+ saves_per_epoch: 1
81
+ debug:
82
+ deepspeed: #deepspeed_configs/zero2.json # multi-gpu only
83
+ weight_decay: 0.1
84
+ fsdp:
85
+ fsdp_config:
86
+ special_tokens:
87
+
88
+ ```
89
+
90
+ </details><br>
91
+
92
+ # out
93
+
94
+ This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
95
+ It achieves the following results on the evaluation set:
96
+ - Loss: 1.0146
97
+
98
+ ## Model description
99
+
100
+ More information needed
101
+
102
+ ## Intended uses & limitations
103
+
104
+ More information needed
105
+
106
+ ## Training and evaluation data
107
+
108
+ More information needed
109
+
110
+ ## Training procedure
111
+
112
+ ### Training hyperparameters
113
+
114
+ The following hyperparameters were used during training:
115
+ - learning_rate: 0.0002
116
+ - train_batch_size: 1
117
+ - eval_batch_size: 1
118
+ - seed: 42
119
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
120
+ - lr_scheduler_type: cosine
121
+ - lr_scheduler_warmup_steps: 100
122
+ - num_epochs: 1
123
+
124
+ ### Training results
125
+
126
+ | Training Loss | Epoch | Step | Validation Loss |
127
+ |:-------------:|:-----:|:----:|:---------------:|
128
+ | 0.4999 | 0.0 | 1 | 1.0117 |
129
+ | 2.6581 | 0.25 | 129 | 1.6428 |
130
+ | 1.4897 | 0.5 | 258 | 1.3088 |
131
+ | 0.0849 | 0.75 | 387 | 1.0146 |
132
+
133
+
134
+ ### Framework versions
135
+
136
+ - Transformers 4.37.0
137
+ - Pytorch 2.1.1+cu121
138
+ - Datasets 2.16.1
139
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codellama/CodeLlama-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.37.0",
26
+ "use_cache": false,
27
+ "vocab_size": 32016
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.37.0"
7
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d7580cbaa31e0dd9a32fbf09e89d5673786b52194c7d54dfdf56702f02ed13
3
+ size 6333821273
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00783c986131b0920b6fe94440ed75e2c4278d39cf5668a8a2989bd843cbd9c7
3
+ size 6386120701
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3e2062a0a33526314194d93d672faa20d3a38be9e73dd60d785610c4051d86
3
+ size 757249236
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10591412224
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.norm.weight": "pytorch_model-00003-of-00003.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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "trust_remote_code": false,
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": true
43
+ }