TroyDoesAI
commited on
Commit
•
b6ee697
1
Parent(s):
325b93e
Really interesting Personality that seems to scale as the model gets larger really strangely
Browse files- config.json +27 -0
- mergekit_config.yml +254 -0
- model-00001-of-00012.safetensors +3 -0
- model-00002-of-00012.safetensors +3 -0
- model-00003-of-00012.safetensors +3 -0
- model-00004-of-00012.safetensors +3 -0
- model-00005-of-00012.safetensors +3 -0
- model-00006-of-00012.safetensors +3 -0
- model-00007-of-00012.safetensors +3 -0
- model-00008-of-00012.safetensors +3 -0
- model-00009-of-00012.safetensors +3 -0
- model-00010-of-00012.safetensors +3 -0
- model-00011-of-00012.safetensors +3 -0
- model-00012-of-00012.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DigitalSouls/BlackSheep-DigitalSoul",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 6144,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 16384,
|
14 |
+
"max_position_embeddings": 131072,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 48,
|
17 |
+
"num_hidden_layers": 70,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.40.2",
|
25 |
+
"use_cache": false,
|
26 |
+
"vocab_size": 32768
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,254 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# slices:
|
2 |
+
# - sources:
|
3 |
+
# - model: failspy/kappa-3-phi-abliterated
|
4 |
+
# layer_range: [0, 1]
|
5 |
+
# - sources:
|
6 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
7 |
+
# layer_range: [0, 1]
|
8 |
+
|
9 |
+
# - sources:
|
10 |
+
# - model: failspy/kappa-3-phi-abliterated
|
11 |
+
# layer_range: [1, 2]
|
12 |
+
# - sources:
|
13 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
14 |
+
# layer_range: [1, 2]
|
15 |
+
|
16 |
+
# - sources:
|
17 |
+
# - model: failspy/kappa-3-phi-abliterated
|
18 |
+
# layer_range: [2, 3]
|
19 |
+
# - sources:
|
20 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
21 |
+
# layer_range: [2, 3]
|
22 |
+
|
23 |
+
# - sources:
|
24 |
+
# - model: failspy/kappa-3-phi-abliterated
|
25 |
+
# layer_range: [3, 4]
|
26 |
+
# - sources:
|
27 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
28 |
+
# layer_range: [3, 4]
|
29 |
+
|
30 |
+
# - sources:
|
31 |
+
# - model: failspy/kappa-3-phi-abliterated
|
32 |
+
# layer_range: [4, 5]
|
33 |
+
# - sources:
|
34 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
35 |
+
# layer_range: [4, 5]
|
36 |
+
|
37 |
+
# - sources:
|
38 |
+
# - model: failspy/kappa-3-phi-abliterated
|
39 |
+
# layer_range: [5, 6]
|
40 |
+
# - sources:
|
41 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
42 |
+
# layer_range: [5, 6]
|
43 |
+
|
44 |
+
# - sources:
|
45 |
+
# - model: failspy/kappa-3-phi-abliterated
|
46 |
+
# layer_range: [6, 7]
|
47 |
+
# - sources:
|
48 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
49 |
+
# layer_range: [6, 7]
|
50 |
+
|
51 |
+
# - sources:
|
52 |
+
# - model: failspy/kappa-3-phi-abliterated
|
53 |
+
# layer_range: [7, 8]
|
54 |
+
# - sources:
|
55 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
56 |
+
# layer_range: [7, 8]
|
57 |
+
|
58 |
+
# - sources:
|
59 |
+
# - model: failspy/kappa-3-phi-abliterated
|
60 |
+
# layer_range: [8, 9]
|
61 |
+
# - sources:
|
62 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
63 |
+
# layer_range: [8, 9]
|
64 |
+
|
65 |
+
# - sources:
|
66 |
+
# - model: failspy/kappa-3-phi-abliterated
|
67 |
+
# layer_range: [9, 10]
|
68 |
+
# - sources:
|
69 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
70 |
+
# layer_range: [9, 10]
|
71 |
+
|
72 |
+
# - sources:
|
73 |
+
# - model: failspy/kappa-3-phi-abliterated
|
74 |
+
# layer_range: [10, 11]
|
75 |
+
# - sources:
|
76 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
77 |
+
# layer_range: [10, 11]
|
78 |
+
|
79 |
+
# - sources:
|
80 |
+
# - model: failspy/kappa-3-phi-abliterated
|
81 |
+
# layer_range: [11, 12]
|
82 |
+
# - sources:
|
83 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
84 |
+
# layer_range: [11, 12]
|
85 |
+
|
86 |
+
# - sources:
|
87 |
+
# - model: failspy/kappa-3-phi-abliterated
|
88 |
+
# layer_range: [12, 13]
|
89 |
+
# - sources:
|
90 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
91 |
+
# layer_range: [12, 13]
|
92 |
+
|
93 |
+
# - sources:
|
94 |
+
# - model: failspy/kappa-3-phi-abliterated
|
95 |
+
# layer_range: [13, 14]
|
96 |
+
# - sources:
|
97 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
98 |
+
# layer_range: [13, 14]
|
99 |
+
|
100 |
+
# - sources:
|
101 |
+
# - model: failspy/kappa-3-phi-abliterated
|
102 |
+
# layer_range: [14, 15]
|
103 |
+
# - sources:
|
104 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
105 |
+
# layer_range: [14, 15]
|
106 |
+
|
107 |
+
# - sources:
|
108 |
+
# - model: failspy/kappa-3-phi-abliterated
|
109 |
+
# layer_range: [15, 16]
|
110 |
+
# - sources:
|
111 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
112 |
+
# layer_range: [15, 16]
|
113 |
+
|
114 |
+
# - sources:
|
115 |
+
# - model: failspy/kappa-3-phi-abliterated
|
116 |
+
# layer_range: [16, 17]
|
117 |
+
# - sources:
|
118 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
119 |
+
# layer_range: [16, 17]
|
120 |
+
|
121 |
+
# - sources:
|
122 |
+
# - model: failspy/kappa-3-phi-abliterated
|
123 |
+
# layer_range: [17, 18]
|
124 |
+
# - sources:
|
125 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
126 |
+
# layer_range: [17, 18]
|
127 |
+
|
128 |
+
# - sources:
|
129 |
+
# - model: failspy/kappa-3-phi-abliterated
|
130 |
+
# layer_range: [18, 19]
|
131 |
+
# - sources:
|
132 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
133 |
+
# layer_range: [18, 19]
|
134 |
+
|
135 |
+
# - sources:
|
136 |
+
# - model: failspy/kappa-3-phi-abliterated
|
137 |
+
# layer_range: [19, 20]
|
138 |
+
# - sources:
|
139 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
140 |
+
# layer_range: [19, 20]
|
141 |
+
|
142 |
+
# - sources:
|
143 |
+
# - model: failspy/kappa-3-phi-abliterated
|
144 |
+
# layer_range: [20, 21]
|
145 |
+
# - sources:
|
146 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
147 |
+
# layer_range: [20, 21]
|
148 |
+
|
149 |
+
# - sources:
|
150 |
+
# - model: failspy/kappa-3-phi-abliterated
|
151 |
+
# layer_range: [21, 22]
|
152 |
+
# - sources:
|
153 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
154 |
+
# layer_range: [21, 22]
|
155 |
+
|
156 |
+
# - sources:
|
157 |
+
# - model: failspy/kappa-3-phi-abliterated
|
158 |
+
# layer_range: [22, 23]
|
159 |
+
# - sources:
|
160 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
161 |
+
# layer_range: [22, 23]
|
162 |
+
|
163 |
+
# - sources:
|
164 |
+
# - model: failspy/kappa-3-phi-abliterated
|
165 |
+
# layer_range: [23, 24]
|
166 |
+
# - sources:
|
167 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
168 |
+
# layer_range: [23, 24]
|
169 |
+
|
170 |
+
# - sources:
|
171 |
+
# - model: failspy/kappa-3-phi-abliterated
|
172 |
+
# layer_range: [24, 25]
|
173 |
+
# - sources:
|
174 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
175 |
+
# layer_range: [24, 25]
|
176 |
+
|
177 |
+
# - sources:
|
178 |
+
# - model: failspy/kappa-3-phi-abliterated
|
179 |
+
# layer_range: [25, 26]
|
180 |
+
# - sources:
|
181 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
182 |
+
# layer_range: [25, 26]
|
183 |
+
|
184 |
+
# - sources:
|
185 |
+
# - model: failspy/kappa-3-phi-abliterated
|
186 |
+
# layer_range: [26, 27]
|
187 |
+
# - sources:
|
188 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
189 |
+
# layer_range: [26, 27]
|
190 |
+
|
191 |
+
# - sources:
|
192 |
+
# - model: failspy/kappa-3-phi-abliterated
|
193 |
+
# layer_range: [27, 28]
|
194 |
+
# - sources:
|
195 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
196 |
+
# layer_range: [27, 28]
|
197 |
+
|
198 |
+
# - sources:
|
199 |
+
# - model: failspy/kappa-3-phi-abliterated
|
200 |
+
# layer_range: [28, 29]
|
201 |
+
# - sources:
|
202 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
203 |
+
# layer_range: [28, 29]
|
204 |
+
|
205 |
+
# - sources:
|
206 |
+
# - model: failspy/kappa-3-phi-abliterated
|
207 |
+
# layer_range: [29, 30]
|
208 |
+
# - sources:
|
209 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
210 |
+
# layer_range: [29, 30]
|
211 |
+
|
212 |
+
# - sources:
|
213 |
+
# - model: failspy/kappa-3-phi-abliterated
|
214 |
+
# layer_range: [30, 31]
|
215 |
+
# - sources:
|
216 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
217 |
+
# layer_range: [30, 31]
|
218 |
+
|
219 |
+
# - sources:
|
220 |
+
# - model: failspy/kappa-3-phi-abliterated
|
221 |
+
# layer_range: [31, 32]
|
222 |
+
# - sources:
|
223 |
+
# - model: TroyDoesAI/Phi-3-Context-Obedient-RAG
|
224 |
+
# layer_range: [31, 32]
|
225 |
+
|
226 |
+
|
227 |
+
|
228 |
+
|
229 |
+
|
230 |
+
|
231 |
+
|
232 |
+
|
233 |
+
|
234 |
+
|
235 |
+
|
236 |
+
|
237 |
+
|
238 |
+
|
239 |
+
|
240 |
+
|
241 |
+
|
242 |
+
slices:
|
243 |
+
- sources:
|
244 |
+
- model: DigitalSouls/BlackSheep-DigitalSoul
|
245 |
+
layer_range: [0, 32]
|
246 |
+
- sources:
|
247 |
+
- model: TroyDoesAI/BlackSheep-MermaidMistral-22B
|
248 |
+
layer_range: [24, 42]
|
249 |
+
- sources:
|
250 |
+
- model: DigitalSouls/BlackSheep-DigitalSoul
|
251 |
+
layer_range: [32, 56]
|
252 |
+
|
253 |
+
merge_method: passthrough
|
254 |
+
dtype: bfloat16
|
model-00001-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0280fc856fd8aeddd7b769900cf904dc50b14ae21b47c3045df7a1e002318d3
|
3 |
+
size 4907476544
|
model-00002-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c084c8c971ba45cedc9d3c16d91500bc4e474d208983502b1fb74b10b1d41fb
|
3 |
+
size 4882323752
|
model-00003-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b69c9584183ec944ea03f46556379bb9e979dcb558dffcd053499a6cc6d60a1
|
3 |
+
size 4970416760
|
model-00004-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edce3204e5ace361b95787ab0edf468fab63ce85d8fd6413d22a2606d448dae9
|
3 |
+
size 4995569816
|
model-00005-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57f809776e64426998e3227cc084f136357be234f31606f92fd7fd5aa35d6a4a
|
3 |
+
size 4857183080
|
model-00006-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dca7c03a6e395d862d7e9bf0ce85d5325b1283a386b87940c0ba20a445a52849
|
3 |
+
size 4882323752
|
model-00007-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68264ef0e715451fe7176313ea1042ec1fa3ef669c88d90e98e59b74fdf95709
|
3 |
+
size 4882323752
|
model-00008-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:105f12bd51688db3bde86284db93564c1c17ad8e1934c9d72fa7ee12fc277260
|
3 |
+
size 4857183064
|
model-00009-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3044086425dbfaca1b77f4a19d99c9e5adebfabf1320e722a05495096669d678
|
3 |
+
size 4882311352
|
model-00010-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f042f9895009ee9e94ac037bd9d3ab9b4b1ea668c1a908191efa7238bd37839
|
3 |
+
size 4970416752
|
model-00011-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e1a564c52767764b92d0b42243f8596e04824de6f8afd9b4894fe915da11de5
|
3 |
+
size 4970416736
|
model-00012-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a99fa77340b53a55ef55094fc13b4818cec1b5b70003c2828d681a41ed4ae25c
|
3 |
+
size 1359005608
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 55416877056}, "weight_map": {"lm_head.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.60.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.65.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.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": "</s>",
|
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 sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
|
3 |
+
size 587583
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|