QMB15 commited on
Commit
e20a7e7
1 Parent(s): 8ef301c

Upload 9 files

Browse files
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ language:
4
+ - en
5
+ ---
6
+ An improved, potentially even perfected variant of MythoMix, my [MythoLogic-L2](https://huggingface.co/Gryphe/MythoLogic-L2-13b) and [Huginn](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model, resulting in increased coherency across the entire structure.
7
+
8
+ The script and the acccompanying templates I used to produce both can [be found here](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML).
9
+
10
+ This model is proficient at both roleplaying and storywriting due to its unique nature.
11
+
12
+ Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoMax-L2-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ) (You're the best!)
13
+
14
+ ## Model details
15
+
16
+ The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time)
17
+
18
+ This type of merge is incapable of being illustrated, as each of its 363 tensors had an unique ratio applied to it. As with my prior merges, gradients were part of these ratios to further finetune its behaviour.
19
+
20
+ ## Prompt Format
21
+
22
+ This model primarily uses Alpaca formatting, so for optimal model performance, use:
23
+ ```
24
+ <System prompt/Character Card>
25
+
26
+ ### Instruction:
27
+ Your instruction or question here.
28
+ For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
29
+
30
+ ### Response:
31
+ ```
32
+
33
+ ---
34
+ license: other
35
+ ---
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mythomax-L2-13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.32.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.32.0.dev0"
10
+ }
measurement.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26031728640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00013-of-00013.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
323
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
324
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
325
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
326
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
327
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
328
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
329
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
330
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
331
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
332
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
333
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
334
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
335
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
336
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
337
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
338
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
339
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
340
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
341
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
342
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
343
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
344
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
345
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
346
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
347
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
348
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
349
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
350
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
351
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
352
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
353
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
354
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
355
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
356
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
357
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
358
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
359
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
360
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
361
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
362
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
363
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
364
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
365
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
366
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
367
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
368
+ "model.norm.weight": "pytorch_model-00013-of-00013.bin"
369
+ }
370
+ }
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": "<unk>",
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 4096,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }