AALF commited on
Commit
8cf599b
1 Parent(s): 778a558

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # FuseChat-7B-Ties-VaRM-comb1-top0.1
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the ties_varm merge method using /data/wanfq/fusechat/models/openchat_3.5 as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Mixtral
22
+ * /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-NHSolar
23
+ * /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Qwen
24
+ * /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-internlm
25
+ * /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Starling
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+ models:
33
+ - model: /data/wanfq/fusechat/models/openchat_3.5
34
+ # no parameters necessary for base model
35
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-internlm
36
+ parameters:
37
+ density: 0.1 # density gradient
38
+ weight: 0.2
39
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Qwen
40
+ parameters:
41
+ density: 0.5
42
+ weight: 0.2 # weight gradient
43
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Mixtral
44
+ parameters:
45
+ density: 0.5
46
+ weight: 0.2 # weight gradient
47
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Starling
48
+ parameters:
49
+ density: 0.5
50
+ weight: 0.2 # weight gradient
51
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-NHSolar
52
+ parameters:
53
+ density: 0.5
54
+ weight: 0.2 # weight gradient
55
+ merge_method: ties_varm
56
+ base_model: /data/wanfq/fusechat/models/openchat_3.5
57
+ parameters:
58
+ normalize: true
59
+ dtype: bfloat16
60
+
61
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/wanfq/fusechat/models/openchat_3.5",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32002
26
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "transformers_version": "4.39.1",
6
+ "use_cache": false
7
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: /data/wanfq/fusechat/models/openchat_3.5
3
+ # no parameters necessary for base model
4
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-internlm
5
+ parameters:
6
+ density: 0.1 # density gradient
7
+ weight: 0.2
8
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Qwen
9
+ parameters:
10
+ density: 0.5
11
+ weight: 0.2 # weight gradient
12
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Mixtral
13
+ parameters:
14
+ density: 0.5
15
+ weight: 0.2 # weight gradient
16
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Starling
17
+ parameters:
18
+ density: 0.5
19
+ weight: 0.2 # weight gradient
20
+ - model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-NHSolar
21
+ parameters:
22
+ density: 0.5
23
+ weight: 0.2 # weight gradient
24
+ merge_method: ties_varm
25
+ base_model: /data/wanfq/fusechat/models/openchat_3.5
26
+ parameters:
27
+ normalize: true
28
+ dtype: bfloat16
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c49d2b7308b408d8ed817127afe189238471f22bb0d1215ee1e10f3b46149d
3
+ size 9942998080
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a031d4a873de47a4781064896c1fc6beb693eb4d66bc54e637497682c9b806
3
+ size 4540532728
model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "mergekit_version": "0.0.4.2",
4
+ "total_size": 14483496960
5
+ },
6
+ "weight_map": {
7
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "lm_head.weight": "model-00002-of-00002.safetensors",
211
+ "model.norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors"
298
+ }
299
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|end_of_turn|>",
48
+ "<|pad_0|>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|end_of_turn|>",
54
+ "legacy": true,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": null,
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "unk_token": "<unk>",
61
+ "use_default_system_prompt": true
62
+ }