Mark-Arcee commited on
Commit
3b29058
1 Parent(s): 5d66738

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
7
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
8
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
9
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
10
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
11
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
12
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
13
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
14
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
15
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
16
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
17
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
18
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
19
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
20
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
21
+ - MaziyarPanahi/Calme-7B-Instruct-v0.1.1
22
+ ---
23
+
24
+ # Calme-Instruct-Extended
25
+
26
+ Calme-Instruct-Extended is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
27
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
28
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
29
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
30
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
31
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
32
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
33
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
34
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
35
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
36
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
37
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
38
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
39
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
40
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
41
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
42
+ * [MaziyarPanahi/Calme-7B-Instruct-v0.1.1](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.1.1)
43
+
44
+ ## 🧩 Configuration
45
+
46
+ ```yaml
47
+ slices:
48
+ - sources:
49
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
50
+ layer_range:
51
+ - 0
52
+ - 4
53
+ - sources:
54
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
55
+ layer_range:
56
+ - 3
57
+ - 4
58
+ parameters:
59
+ scale:
60
+ - filter: o_proj
61
+ value: 0
62
+ - filter: down_proj
63
+ value: 0
64
+ - value: 1
65
+ - sources:
66
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
67
+ layer_range:
68
+ - 4
69
+ - 8
70
+ - sources:
71
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
72
+ layer_range:
73
+ - 7
74
+ - 8
75
+ parameters:
76
+ scale:
77
+ - filter: o_proj
78
+ value: 0
79
+ - filter: down_proj
80
+ value: 0
81
+ - value: 1
82
+ - sources:
83
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
84
+ layer_range:
85
+ - 8
86
+ - 12
87
+ - sources:
88
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
89
+ layer_range:
90
+ - 11
91
+ - 12
92
+ parameters:
93
+ scale:
94
+ - filter: o_proj
95
+ value: 0
96
+ - filter: down_proj
97
+ value: 0
98
+ - value: 1
99
+ - sources:
100
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
101
+ layer_range:
102
+ - 12
103
+ - 16
104
+ - sources:
105
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
106
+ layer_range:
107
+ - 15
108
+ - 16
109
+ parameters:
110
+ scale:
111
+ - filter: o_proj
112
+ value: 0
113
+ - filter: down_proj
114
+ value: 0
115
+ - value: 1
116
+ - sources:
117
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
118
+ layer_range:
119
+ - 16
120
+ - 20
121
+ - sources:
122
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
123
+ layer_range:
124
+ - 19
125
+ - 20
126
+ parameters:
127
+ scale:
128
+ - filter: o_proj
129
+ value: 0
130
+ - filter: down_proj
131
+ value: 0
132
+ - value: 1
133
+ - sources:
134
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
135
+ layer_range:
136
+ - 20
137
+ - 24
138
+ - sources:
139
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
140
+ layer_range:
141
+ - 23
142
+ - 24
143
+ parameters:
144
+ scale:
145
+ - filter: o_proj
146
+ value: 0
147
+ - filter: down_proj
148
+ value: 0
149
+ - value: 1
150
+ - sources:
151
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
152
+ layer_range:
153
+ - 24
154
+ - 28
155
+ - sources:
156
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
157
+ layer_range:
158
+ - 27
159
+ - 28
160
+ parameters:
161
+ scale:
162
+ - filter: o_proj
163
+ value: 0
164
+ - filter: down_proj
165
+ value: 0
166
+ - value: 1
167
+ - sources:
168
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
169
+ layer_range:
170
+ - 28
171
+ - 32
172
+ - sources:
173
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
174
+ layer_range:
175
+ - 31
176
+ - 32
177
+ parameters:
178
+ scale:
179
+ - filter: o_proj
180
+ value: 0
181
+ - filter: down_proj
182
+ value: 0
183
+ - value: 1
184
+ merge_method: passthrough
185
+ dtype: bfloat16
186
+
187
+
188
+
189
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MaziyarPanahi/Calme-7B-Instruct-v0.1.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
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": false,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
5
+ layer_range:
6
+ - 0
7
+ - 4
8
+ - sources:
9
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
10
+ layer_range:
11
+ - 3
12
+ - 4
13
+ parameters:
14
+ scale:
15
+ - filter: o_proj
16
+ value: 0
17
+ - filter: down_proj
18
+ value: 0
19
+ - value: 1
20
+ - sources:
21
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
22
+ layer_range:
23
+ - 4
24
+ - 8
25
+ - sources:
26
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
27
+ layer_range:
28
+ - 7
29
+ - 8
30
+ parameters:
31
+ scale:
32
+ - filter: o_proj
33
+ value: 0
34
+ - filter: down_proj
35
+ value: 0
36
+ - value: 1
37
+ - sources:
38
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
39
+ layer_range:
40
+ - 8
41
+ - 12
42
+ - sources:
43
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
44
+ layer_range:
45
+ - 11
46
+ - 12
47
+ parameters:
48
+ scale:
49
+ - filter: o_proj
50
+ value: 0
51
+ - filter: down_proj
52
+ value: 0
53
+ - value: 1
54
+ - sources:
55
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
56
+ layer_range:
57
+ - 12
58
+ - 16
59
+ - sources:
60
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
61
+ layer_range:
62
+ - 15
63
+ - 16
64
+ parameters:
65
+ scale:
66
+ - filter: o_proj
67
+ value: 0
68
+ - filter: down_proj
69
+ value: 0
70
+ - value: 1
71
+ - sources:
72
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
73
+ layer_range:
74
+ - 16
75
+ - 20
76
+ - sources:
77
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
78
+ layer_range:
79
+ - 19
80
+ - 20
81
+ parameters:
82
+ scale:
83
+ - filter: o_proj
84
+ value: 0
85
+ - filter: down_proj
86
+ value: 0
87
+ - value: 1
88
+ - sources:
89
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
90
+ layer_range:
91
+ - 20
92
+ - 24
93
+ - sources:
94
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
95
+ layer_range:
96
+ - 23
97
+ - 24
98
+ parameters:
99
+ scale:
100
+ - filter: o_proj
101
+ value: 0
102
+ - filter: down_proj
103
+ value: 0
104
+ - value: 1
105
+ - sources:
106
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
107
+ layer_range:
108
+ - 24
109
+ - 28
110
+ - sources:
111
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
112
+ layer_range:
113
+ - 27
114
+ - 28
115
+ parameters:
116
+ scale:
117
+ - filter: o_proj
118
+ value: 0
119
+ - filter: down_proj
120
+ value: 0
121
+ - value: 1
122
+ - sources:
123
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
124
+ layer_range:
125
+ - 28
126
+ - 32
127
+ - sources:
128
+ - model: MaziyarPanahi/Calme-7B-Instruct-v0.1.1
129
+ layer_range:
130
+ - 31
131
+ - 32
132
+ parameters:
133
+ scale:
134
+ - filter: o_proj
135
+ value: 0
136
+ - filter: down_proj
137
+ value: 0
138
+ - value: 1
139
+ merge_method: passthrough
140
+ dtype: bfloat16
141
+
142
+
143
+
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d010c40690e3376e27a65568a4529622d1e00ca278349e7fa284fa892e16886
3
+ size 1996542272
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1abc5445e1992ff0899cdd36aa91aacabda04277c97672b3011ce1e7ec8cc9ed
3
+ size 1963003976
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea01f2c80dcc95558771622d0d5e3d4782829a083325cc451236cf2a2660daa6
3
+ size 1939952744
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7273b56929c1ca027b2d75b67b12682c402d8b617b3cc068a4b146eb5457e4
3
+ size 1979781464
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdee5c310ccc02a994101140391188d3d3849c9f3da7a233ff2ca84e01db9c9d
3
+ size 1946243984
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc0fa844edcf1615d48e03618b5560d1911b1cdfabd653111d07e774e0601d6
3
+ size 1895878304
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5135ba6925385812637f832cba04ca54f65a031ffb2d31dfd90814595e575923
3
+ size 1973531736
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2915a9b4f00bc4cde9c21301d4be1974e3390de054da263a70eb4aa4e62e7350
3
+ size 1979781464
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c172543bec78071369a1ad5539e378ce04d756c6de227ee6ada45d9f1c8270bf
3
+ size 1946243984
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0177b0fe2d7adc655b15868da1451e9d3168b8e2edc1beec72da1f33014baaf
3
+ size 352338512
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.embed_tokens.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00010.safetensors", "lm_head.weight": "model-00007-of-00010.safetensors", "model.norm.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
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": "<unk>",
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.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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 32768,
38
+ "pad_token": "<unk>",
39
+ "padding_side": "right",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false,
45
+ "use_fast": true
46
+ }