LoneStriker commited on
Commit
d4f3ecb
1 Parent(s): 7f35b5a

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: athirdpath/Harmonia-20B
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: lora
8
+ results: []
9
+ ---
10
+ This was mostly a test to see what the loss/eval looked like when training on top of Harmonia, and in that sense it was a sterling success, without the "jitter" I experienced training on top of Nethena 20b.
11
+ Quick testing shows a bit of derpiness, but a nice conversational flow. Overall, this will be helpful in developing additional 20b merges.
12
+
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
+ # NOTES
16
+
17
+ This model is a fine-tuned version of [athirdpath/Harmonia-20B](https://huggingface.co/athirdpath/Harmonia-20B) on the HF No Robots dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.4881
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 3.5e-05
39
+ - train_batch_size: 3
40
+ - eval_batch_size: 3
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 3
43
+ - total_train_batch_size: 9
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 10
47
+ - num_epochs: 3
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.5598 | 0.55 | 50 | 1.5816 |
54
+ | 1.5384 | 1.08 | 100 | 1.5146 |
55
+ | 1.5362 | 1.64 | 150 | 1.4972 |
56
+ | 1.4234 | 2.17 | 200 | 1.4902 |
57
+ | 1.4678 | 2.72 | 250 | 1.4881 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.35.2
63
+ - Pytorch 2.0.1+cu118
64
+ - Datasets 2.15.0
65
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "athirdpath/Harmonia-20B",
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": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 62,
18
+ "num_key_value_heads": 40,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.35.2",
27
+ "use_cache": false,
28
+ "vocab_size": 32001,
29
+ "quantization_config": {
30
+ "quant_method": "exl2",
31
+ "version": "0.0.16",
32
+ "bits": 3.0,
33
+ "head_bits": 6,
34
+ "calibration": {
35
+ "rows": 100,
36
+ "length": 2048,
37
+ "dataset": "(default)"
38
+ }
39
+ }
40
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.35.2",
7
+ "use_cache": false
8
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffca95bd8f4e94d89b70183dca1800d5ff862b1b501bfd37a3fcc20eae75b116
3
+ size 7833441212
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,568 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 39988746240
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00009-of-00009.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00009.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
323
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
324
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
325
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
326
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
327
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
328
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
329
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
330
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
331
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
332
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
333
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
334
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
335
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
336
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
337
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
338
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
339
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
340
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
341
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
342
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
343
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
344
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
345
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
346
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
347
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
348
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
349
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
350
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
351
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
352
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
353
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
354
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
355
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
356
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
357
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
358
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
359
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
360
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
361
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
362
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
363
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
364
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
365
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
366
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
367
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
368
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
369
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
370
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
371
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
372
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
373
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
374
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
375
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
376
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
377
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
378
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
379
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
380
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
381
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
382
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
383
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
384
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
385
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
386
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
387
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
388
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
389
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
390
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
391
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
392
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
393
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
394
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
395
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
396
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
397
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
398
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
399
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
400
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
401
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
402
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
403
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
404
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
405
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
406
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
407
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
408
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
409
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
410
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
411
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
412
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
413
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
414
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
415
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
416
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
417
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
418
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
419
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
420
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
421
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
422
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
423
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
424
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
425
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
426
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
427
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
428
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
429
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
430
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
431
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
432
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
433
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
434
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
435
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
436
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
437
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
438
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
439
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
440
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
441
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
442
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
443
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
444
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
445
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
446
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
447
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
448
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
449
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
450
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
451
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
452
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
453
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
454
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
455
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
456
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
457
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
458
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
459
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
460
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
461
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
462
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
463
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
464
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
465
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
466
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
467
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
468
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
469
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
470
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
471
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
472
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
473
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
474
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
475
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
476
+ "model.layers.56.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
477
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
478
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
479
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
480
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
481
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
482
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
483
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
484
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
485
+ "model.layers.57.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
486
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
487
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
488
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
489
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
490
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
491
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
492
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
493
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
494
+ "model.layers.58.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
495
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
496
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
497
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
498
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
499
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
500
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
501
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
502
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
503
+ "model.layers.59.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
504
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
505
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
506
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
507
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
508
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
509
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
510
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
511
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
512
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
513
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
514
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
515
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
516
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
517
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
518
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
519
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
520
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
521
+ "model.layers.60.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
522
+ "model.layers.60.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
523
+ "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
524
+ "model.layers.60.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
525
+ "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
526
+ "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
527
+ "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
528
+ "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
529
+ "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
530
+ "model.layers.61.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
531
+ "model.layers.61.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
532
+ "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
533
+ "model.layers.61.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
534
+ "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
535
+ "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
536
+ "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
537
+ "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
538
+ "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
539
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
540
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
541
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
542
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
543
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
544
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
545
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
546
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
547
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
548
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
549
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
550
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
551
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
552
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
553
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
554
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
555
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
556
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
557
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
558
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
559
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
560
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
561
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
562
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
563
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
564
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
565
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
566
+ "model.norm.weight": "pytorch_model-00008-of-00009.bin"
567
+ }
568
+ }
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
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.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 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": true,
42
+ "model_max_length": 2048,
43
+ "pad_token": "[PAD]",
44
+ "padding_side": "left",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "trust_remote_code": false,
49
+ "unk_token": "<unk>",
50
+ "use_default_system_prompt": false,
51
+ "use_fast": true
52
+ }