Create README
Browse files
README
ADDED
@@ -0,0 +1,518 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
weight state dict:
|
2 |
+
|
3 |
+
tok_embeddings.weight
|
4 |
+
layers.0.attention.wqkv.q.weight
|
5 |
+
layers.0.attention.wqkv.q.scales_and_zeros
|
6 |
+
layers.0.attention.wqkv.k.weight
|
7 |
+
layers.0.attention.wqkv.k.scales_and_zeros
|
8 |
+
layers.0.attention.wqkv.v.weight
|
9 |
+
layers.0.attention.wqkv.v.scales_and_zeros
|
10 |
+
layers.0.attention.wo.weight
|
11 |
+
layers.0.attention.wo.scales_and_zeros
|
12 |
+
layers.0.feed_forward.w1.weight
|
13 |
+
layers.0.feed_forward.w1.scales_and_zeros
|
14 |
+
layers.0.feed_forward.w3.weight
|
15 |
+
layers.0.feed_forward.w3.scales_and_zeros
|
16 |
+
layers.0.feed_forward.w2.weight
|
17 |
+
layers.0.feed_forward.w2.scales_and_zeros
|
18 |
+
layers.0.ffn_norm.weight
|
19 |
+
layers.0.attention_norm.weight
|
20 |
+
layers.1.attention.wqkv.q.weight
|
21 |
+
layers.1.attention.wqkv.q.scales_and_zeros
|
22 |
+
layers.1.attention.wqkv.k.weight
|
23 |
+
layers.1.attention.wqkv.k.scales_and_zeros
|
24 |
+
layers.1.attention.wqkv.v.weight
|
25 |
+
layers.1.attention.wqkv.v.scales_and_zeros
|
26 |
+
layers.1.attention.wo.weight
|
27 |
+
layers.1.attention.wo.scales_and_zeros
|
28 |
+
layers.1.feed_forward.w1.weight
|
29 |
+
layers.1.feed_forward.w1.scales_and_zeros
|
30 |
+
layers.1.feed_forward.w3.weight
|
31 |
+
layers.1.feed_forward.w3.scales_and_zeros
|
32 |
+
layers.1.feed_forward.w2.weight
|
33 |
+
layers.1.feed_forward.w2.scales_and_zeros
|
34 |
+
layers.1.ffn_norm.weight
|
35 |
+
layers.1.attention_norm.weight
|
36 |
+
layers.2.attention.wqkv.q.weight
|
37 |
+
layers.2.attention.wqkv.q.scales_and_zeros
|
38 |
+
layers.2.attention.wqkv.k.weight
|
39 |
+
layers.2.attention.wqkv.k.scales_and_zeros
|
40 |
+
layers.2.attention.wqkv.v.weight
|
41 |
+
layers.2.attention.wqkv.v.scales_and_zeros
|
42 |
+
layers.2.attention.wo.weight
|
43 |
+
layers.2.attention.wo.scales_and_zeros
|
44 |
+
layers.2.feed_forward.w1.weight
|
45 |
+
layers.2.feed_forward.w1.scales_and_zeros
|
46 |
+
layers.2.feed_forward.w3.weight
|
47 |
+
layers.2.feed_forward.w3.scales_and_zeros
|
48 |
+
layers.2.feed_forward.w2.weight
|
49 |
+
layers.2.feed_forward.w2.scales_and_zeros
|
50 |
+
layers.2.ffn_norm.weight
|
51 |
+
layers.2.attention_norm.weight
|
52 |
+
layers.3.attention.wqkv.q.weight
|
53 |
+
layers.3.attention.wqkv.q.scales_and_zeros
|
54 |
+
layers.3.attention.wqkv.k.weight
|
55 |
+
layers.3.attention.wqkv.k.scales_and_zeros
|
56 |
+
layers.3.attention.wqkv.v.weight
|
57 |
+
layers.3.attention.wqkv.v.scales_and_zeros
|
58 |
+
layers.3.attention.wo.weight
|
59 |
+
layers.3.attention.wo.scales_and_zeros
|
60 |
+
layers.3.feed_forward.w1.weight
|
61 |
+
layers.3.feed_forward.w1.scales_and_zeros
|
62 |
+
layers.3.feed_forward.w3.weight
|
63 |
+
layers.3.feed_forward.w3.scales_and_zeros
|
64 |
+
layers.3.feed_forward.w2.weight
|
65 |
+
layers.3.feed_forward.w2.scales_and_zeros
|
66 |
+
layers.3.ffn_norm.weight
|
67 |
+
layers.3.attention_norm.weight
|
68 |
+
layers.4.attention.wqkv.q.weight
|
69 |
+
layers.4.attention.wqkv.q.scales_and_zeros
|
70 |
+
layers.4.attention.wqkv.k.weight
|
71 |
+
layers.4.attention.wqkv.k.scales_and_zeros
|
72 |
+
layers.4.attention.wqkv.v.weight
|
73 |
+
layers.4.attention.wqkv.v.scales_and_zeros
|
74 |
+
layers.4.attention.wo.weight
|
75 |
+
layers.4.attention.wo.scales_and_zeros
|
76 |
+
layers.4.feed_forward.w1.weight
|
77 |
+
layers.4.feed_forward.w1.scales_and_zeros
|
78 |
+
layers.4.feed_forward.w3.weight
|
79 |
+
layers.4.feed_forward.w3.scales_and_zeros
|
80 |
+
layers.4.feed_forward.w2.weight
|
81 |
+
layers.4.feed_forward.w2.scales_and_zeros
|
82 |
+
layers.4.ffn_norm.weight
|
83 |
+
layers.4.attention_norm.weight
|
84 |
+
layers.5.attention.wqkv.q.weight
|
85 |
+
layers.5.attention.wqkv.q.scales_and_zeros
|
86 |
+
layers.5.attention.wqkv.k.weight
|
87 |
+
layers.5.attention.wqkv.k.scales_and_zeros
|
88 |
+
layers.5.attention.wqkv.v.weight
|
89 |
+
layers.5.attention.wqkv.v.scales_and_zeros
|
90 |
+
layers.5.attention.wo.weight
|
91 |
+
layers.5.attention.wo.scales_and_zeros
|
92 |
+
layers.5.feed_forward.w1.weight
|
93 |
+
layers.5.feed_forward.w1.scales_and_zeros
|
94 |
+
layers.5.feed_forward.w3.weight
|
95 |
+
layers.5.feed_forward.w3.scales_and_zeros
|
96 |
+
layers.5.feed_forward.w2.weight
|
97 |
+
layers.5.feed_forward.w2.scales_and_zeros
|
98 |
+
layers.5.ffn_norm.weight
|
99 |
+
layers.5.attention_norm.weight
|
100 |
+
layers.6.attention.wqkv.q.weight
|
101 |
+
layers.6.attention.wqkv.q.scales_and_zeros
|
102 |
+
layers.6.attention.wqkv.k.weight
|
103 |
+
layers.6.attention.wqkv.k.scales_and_zeros
|
104 |
+
layers.6.attention.wqkv.v.weight
|
105 |
+
layers.6.attention.wqkv.v.scales_and_zeros
|
106 |
+
layers.6.attention.wo.weight
|
107 |
+
layers.6.attention.wo.scales_and_zeros
|
108 |
+
layers.6.feed_forward.w1.weight
|
109 |
+
layers.6.feed_forward.w1.scales_and_zeros
|
110 |
+
layers.6.feed_forward.w3.weight
|
111 |
+
layers.6.feed_forward.w3.scales_and_zeros
|
112 |
+
layers.6.feed_forward.w2.weight
|
113 |
+
layers.6.feed_forward.w2.scales_and_zeros
|
114 |
+
layers.6.ffn_norm.weight
|
115 |
+
layers.6.attention_norm.weight
|
116 |
+
layers.7.attention.wqkv.q.weight
|
117 |
+
layers.7.attention.wqkv.q.scales_and_zeros
|
118 |
+
layers.7.attention.wqkv.k.weight
|
119 |
+
layers.7.attention.wqkv.k.scales_and_zeros
|
120 |
+
layers.7.attention.wqkv.v.weight
|
121 |
+
layers.7.attention.wqkv.v.scales_and_zeros
|
122 |
+
layers.7.attention.wo.weight
|
123 |
+
layers.7.attention.wo.scales_and_zeros
|
124 |
+
layers.7.feed_forward.w1.weight
|
125 |
+
layers.7.feed_forward.w1.scales_and_zeros
|
126 |
+
layers.7.feed_forward.w3.weight
|
127 |
+
layers.7.feed_forward.w3.scales_and_zeros
|
128 |
+
layers.7.feed_forward.w2.weight
|
129 |
+
layers.7.feed_forward.w2.scales_and_zeros
|
130 |
+
layers.7.ffn_norm.weight
|
131 |
+
layers.7.attention_norm.weight
|
132 |
+
layers.8.attention.wqkv.q.weight
|
133 |
+
layers.8.attention.wqkv.q.scales_and_zeros
|
134 |
+
layers.8.attention.wqkv.k.weight
|
135 |
+
layers.8.attention.wqkv.k.scales_and_zeros
|
136 |
+
layers.8.attention.wqkv.v.weight
|
137 |
+
layers.8.attention.wqkv.v.scales_and_zeros
|
138 |
+
layers.8.attention.wo.weight
|
139 |
+
layers.8.attention.wo.scales_and_zeros
|
140 |
+
layers.8.feed_forward.w1.weight
|
141 |
+
layers.8.feed_forward.w1.scales_and_zeros
|
142 |
+
layers.8.feed_forward.w3.weight
|
143 |
+
layers.8.feed_forward.w3.scales_and_zeros
|
144 |
+
layers.8.feed_forward.w2.weight
|
145 |
+
layers.8.feed_forward.w2.scales_and_zeros
|
146 |
+
layers.8.ffn_norm.weight
|
147 |
+
layers.8.attention_norm.weight
|
148 |
+
layers.9.attention.wqkv.q.weight
|
149 |
+
layers.9.attention.wqkv.q.scales_and_zeros
|
150 |
+
layers.9.attention.wqkv.k.weight
|
151 |
+
layers.9.attention.wqkv.k.scales_and_zeros
|
152 |
+
layers.9.attention.wqkv.v.weight
|
153 |
+
layers.9.attention.wqkv.v.scales_and_zeros
|
154 |
+
layers.9.attention.wo.weight
|
155 |
+
layers.9.attention.wo.scales_and_zeros
|
156 |
+
layers.9.feed_forward.w1.weight
|
157 |
+
layers.9.feed_forward.w1.scales_and_zeros
|
158 |
+
layers.9.feed_forward.w3.weight
|
159 |
+
layers.9.feed_forward.w3.scales_and_zeros
|
160 |
+
layers.9.feed_forward.w2.weight
|
161 |
+
layers.9.feed_forward.w2.scales_and_zeros
|
162 |
+
layers.9.ffn_norm.weight
|
163 |
+
layers.9.attention_norm.weight
|
164 |
+
layers.10.attention.wqkv.q.weight
|
165 |
+
layers.10.attention.wqkv.q.scales_and_zeros
|
166 |
+
layers.10.attention.wqkv.k.weight
|
167 |
+
layers.10.attention.wqkv.k.scales_and_zeros
|
168 |
+
layers.10.attention.wqkv.v.weight
|
169 |
+
layers.10.attention.wqkv.v.scales_and_zeros
|
170 |
+
layers.10.attention.wo.weight
|
171 |
+
layers.10.attention.wo.scales_and_zeros
|
172 |
+
layers.10.feed_forward.w1.weight
|
173 |
+
layers.10.feed_forward.w1.scales_and_zeros
|
174 |
+
layers.10.feed_forward.w3.weight
|
175 |
+
layers.10.feed_forward.w3.scales_and_zeros
|
176 |
+
layers.10.feed_forward.w2.weight
|
177 |
+
layers.10.feed_forward.w2.scales_and_zeros
|
178 |
+
layers.10.ffn_norm.weight
|
179 |
+
layers.10.attention_norm.weight
|
180 |
+
layers.11.attention.wqkv.q.weight
|
181 |
+
layers.11.attention.wqkv.q.scales_and_zeros
|
182 |
+
layers.11.attention.wqkv.k.weight
|
183 |
+
layers.11.attention.wqkv.k.scales_and_zeros
|
184 |
+
layers.11.attention.wqkv.v.weight
|
185 |
+
layers.11.attention.wqkv.v.scales_and_zeros
|
186 |
+
layers.11.attention.wo.weight
|
187 |
+
layers.11.attention.wo.scales_and_zeros
|
188 |
+
layers.11.feed_forward.w1.weight
|
189 |
+
layers.11.feed_forward.w1.scales_and_zeros
|
190 |
+
layers.11.feed_forward.w3.weight
|
191 |
+
layers.11.feed_forward.w3.scales_and_zeros
|
192 |
+
layers.11.feed_forward.w2.weight
|
193 |
+
layers.11.feed_forward.w2.scales_and_zeros
|
194 |
+
layers.11.ffn_norm.weight
|
195 |
+
layers.11.attention_norm.weight
|
196 |
+
layers.12.attention.wqkv.q.weight
|
197 |
+
layers.12.attention.wqkv.q.scales_and_zeros
|
198 |
+
layers.12.attention.wqkv.k.weight
|
199 |
+
layers.12.attention.wqkv.k.scales_and_zeros
|
200 |
+
layers.12.attention.wqkv.v.weight
|
201 |
+
layers.12.attention.wqkv.v.scales_and_zeros
|
202 |
+
layers.12.attention.wo.weight
|
203 |
+
layers.12.attention.wo.scales_and_zeros
|
204 |
+
layers.12.feed_forward.w1.weight
|
205 |
+
layers.12.feed_forward.w1.scales_and_zeros
|
206 |
+
layers.12.feed_forward.w3.weight
|
207 |
+
layers.12.feed_forward.w3.scales_and_zeros
|
208 |
+
layers.12.feed_forward.w2.weight
|
209 |
+
layers.12.feed_forward.w2.scales_and_zeros
|
210 |
+
layers.12.ffn_norm.weight
|
211 |
+
layers.12.attention_norm.weight
|
212 |
+
layers.13.attention.wqkv.q.weight
|
213 |
+
layers.13.attention.wqkv.q.scales_and_zeros
|
214 |
+
layers.13.attention.wqkv.k.weight
|
215 |
+
layers.13.attention.wqkv.k.scales_and_zeros
|
216 |
+
layers.13.attention.wqkv.v.weight
|
217 |
+
layers.13.attention.wqkv.v.scales_and_zeros
|
218 |
+
layers.13.attention.wo.weight
|
219 |
+
layers.13.attention.wo.scales_and_zeros
|
220 |
+
layers.13.feed_forward.w1.weight
|
221 |
+
layers.13.feed_forward.w1.scales_and_zeros
|
222 |
+
layers.13.feed_forward.w3.weight
|
223 |
+
layers.13.feed_forward.w3.scales_and_zeros
|
224 |
+
layers.13.feed_forward.w2.weight
|
225 |
+
layers.13.feed_forward.w2.scales_and_zeros
|
226 |
+
layers.13.ffn_norm.weight
|
227 |
+
layers.13.attention_norm.weight
|
228 |
+
layers.14.attention.wqkv.q.weight
|
229 |
+
layers.14.attention.wqkv.q.scales_and_zeros
|
230 |
+
layers.14.attention.wqkv.k.weight
|
231 |
+
layers.14.attention.wqkv.k.scales_and_zeros
|
232 |
+
layers.14.attention.wqkv.v.weight
|
233 |
+
layers.14.attention.wqkv.v.scales_and_zeros
|
234 |
+
layers.14.attention.wo.weight
|
235 |
+
layers.14.attention.wo.scales_and_zeros
|
236 |
+
layers.14.feed_forward.w1.weight
|
237 |
+
layers.14.feed_forward.w1.scales_and_zeros
|
238 |
+
layers.14.feed_forward.w3.weight
|
239 |
+
layers.14.feed_forward.w3.scales_and_zeros
|
240 |
+
layers.14.feed_forward.w2.weight
|
241 |
+
layers.14.feed_forward.w2.scales_and_zeros
|
242 |
+
layers.14.ffn_norm.weight
|
243 |
+
layers.14.attention_norm.weight
|
244 |
+
layers.15.attention.wqkv.q.weight
|
245 |
+
layers.15.attention.wqkv.q.scales_and_zeros
|
246 |
+
layers.15.attention.wqkv.k.weight
|
247 |
+
layers.15.attention.wqkv.k.scales_and_zeros
|
248 |
+
layers.15.attention.wqkv.v.weight
|
249 |
+
layers.15.attention.wqkv.v.scales_and_zeros
|
250 |
+
layers.15.attention.wo.weight
|
251 |
+
layers.15.attention.wo.scales_and_zeros
|
252 |
+
layers.15.feed_forward.w1.weight
|
253 |
+
layers.15.feed_forward.w1.scales_and_zeros
|
254 |
+
layers.15.feed_forward.w3.weight
|
255 |
+
layers.15.feed_forward.w3.scales_and_zeros
|
256 |
+
layers.15.feed_forward.w2.weight
|
257 |
+
layers.15.feed_forward.w2.scales_and_zeros
|
258 |
+
layers.15.ffn_norm.weight
|
259 |
+
layers.15.attention_norm.weight
|
260 |
+
layers.16.attention.wqkv.q.weight
|
261 |
+
layers.16.attention.wqkv.q.scales_and_zeros
|
262 |
+
layers.16.attention.wqkv.k.weight
|
263 |
+
layers.16.attention.wqkv.k.scales_and_zeros
|
264 |
+
layers.16.attention.wqkv.v.weight
|
265 |
+
layers.16.attention.wqkv.v.scales_and_zeros
|
266 |
+
layers.16.attention.wo.weight
|
267 |
+
layers.16.attention.wo.scales_and_zeros
|
268 |
+
layers.16.feed_forward.w1.weight
|
269 |
+
layers.16.feed_forward.w1.scales_and_zeros
|
270 |
+
layers.16.feed_forward.w3.weight
|
271 |
+
layers.16.feed_forward.w3.scales_and_zeros
|
272 |
+
layers.16.feed_forward.w2.weight
|
273 |
+
layers.16.feed_forward.w2.scales_and_zeros
|
274 |
+
layers.16.ffn_norm.weight
|
275 |
+
layers.16.attention_norm.weight
|
276 |
+
layers.17.attention.wqkv.q.weight
|
277 |
+
layers.17.attention.wqkv.q.scales_and_zeros
|
278 |
+
layers.17.attention.wqkv.k.weight
|
279 |
+
layers.17.attention.wqkv.k.scales_and_zeros
|
280 |
+
layers.17.attention.wqkv.v.weight
|
281 |
+
layers.17.attention.wqkv.v.scales_and_zeros
|
282 |
+
layers.17.attention.wo.weight
|
283 |
+
layers.17.attention.wo.scales_and_zeros
|
284 |
+
layers.17.feed_forward.w1.weight
|
285 |
+
layers.17.feed_forward.w1.scales_and_zeros
|
286 |
+
layers.17.feed_forward.w3.weight
|
287 |
+
layers.17.feed_forward.w3.scales_and_zeros
|
288 |
+
layers.17.feed_forward.w2.weight
|
289 |
+
layers.17.feed_forward.w2.scales_and_zeros
|
290 |
+
layers.17.ffn_norm.weight
|
291 |
+
layers.17.attention_norm.weight
|
292 |
+
layers.18.attention.wqkv.q.weight
|
293 |
+
layers.18.attention.wqkv.q.scales_and_zeros
|
294 |
+
layers.18.attention.wqkv.k.weight
|
295 |
+
layers.18.attention.wqkv.k.scales_and_zeros
|
296 |
+
layers.18.attention.wqkv.v.weight
|
297 |
+
layers.18.attention.wqkv.v.scales_and_zeros
|
298 |
+
layers.18.attention.wo.weight
|
299 |
+
layers.18.attention.wo.scales_and_zeros
|
300 |
+
layers.18.feed_forward.w1.weight
|
301 |
+
layers.18.feed_forward.w1.scales_and_zeros
|
302 |
+
layers.18.feed_forward.w3.weight
|
303 |
+
layers.18.feed_forward.w3.scales_and_zeros
|
304 |
+
layers.18.feed_forward.w2.weight
|
305 |
+
layers.18.feed_forward.w2.scales_and_zeros
|
306 |
+
layers.18.ffn_norm.weight
|
307 |
+
layers.18.attention_norm.weight
|
308 |
+
layers.19.attention.wqkv.q.weight
|
309 |
+
layers.19.attention.wqkv.q.scales_and_zeros
|
310 |
+
layers.19.attention.wqkv.k.weight
|
311 |
+
layers.19.attention.wqkv.k.scales_and_zeros
|
312 |
+
layers.19.attention.wqkv.v.weight
|
313 |
+
layers.19.attention.wqkv.v.scales_and_zeros
|
314 |
+
layers.19.attention.wo.weight
|
315 |
+
layers.19.attention.wo.scales_and_zeros
|
316 |
+
layers.19.feed_forward.w1.weight
|
317 |
+
layers.19.feed_forward.w1.scales_and_zeros
|
318 |
+
layers.19.feed_forward.w3.weight
|
319 |
+
layers.19.feed_forward.w3.scales_and_zeros
|
320 |
+
layers.19.feed_forward.w2.weight
|
321 |
+
layers.19.feed_forward.w2.scales_and_zeros
|
322 |
+
layers.19.ffn_norm.weight
|
323 |
+
layers.19.attention_norm.weight
|
324 |
+
layers.20.attention.wqkv.q.weight
|
325 |
+
layers.20.attention.wqkv.q.scales_and_zeros
|
326 |
+
layers.20.attention.wqkv.k.weight
|
327 |
+
layers.20.attention.wqkv.k.scales_and_zeros
|
328 |
+
layers.20.attention.wqkv.v.weight
|
329 |
+
layers.20.attention.wqkv.v.scales_and_zeros
|
330 |
+
layers.20.attention.wo.weight
|
331 |
+
layers.20.attention.wo.scales_and_zeros
|
332 |
+
layers.20.feed_forward.w1.weight
|
333 |
+
layers.20.feed_forward.w1.scales_and_zeros
|
334 |
+
layers.20.feed_forward.w3.weight
|
335 |
+
layers.20.feed_forward.w3.scales_and_zeros
|
336 |
+
layers.20.feed_forward.w2.weight
|
337 |
+
layers.20.feed_forward.w2.scales_and_zeros
|
338 |
+
layers.20.ffn_norm.weight
|
339 |
+
layers.20.attention_norm.weight
|
340 |
+
layers.21.attention.wqkv.q.weight
|
341 |
+
layers.21.attention.wqkv.q.scales_and_zeros
|
342 |
+
layers.21.attention.wqkv.k.weight
|
343 |
+
layers.21.attention.wqkv.k.scales_and_zeros
|
344 |
+
layers.21.attention.wqkv.v.weight
|
345 |
+
layers.21.attention.wqkv.v.scales_and_zeros
|
346 |
+
layers.21.attention.wo.weight
|
347 |
+
layers.21.attention.wo.scales_and_zeros
|
348 |
+
layers.21.feed_forward.w1.weight
|
349 |
+
layers.21.feed_forward.w1.scales_and_zeros
|
350 |
+
layers.21.feed_forward.w3.weight
|
351 |
+
layers.21.feed_forward.w3.scales_and_zeros
|
352 |
+
layers.21.feed_forward.w2.weight
|
353 |
+
layers.21.feed_forward.w2.scales_and_zeros
|
354 |
+
layers.21.ffn_norm.weight
|
355 |
+
layers.21.attention_norm.weight
|
356 |
+
layers.22.attention.wqkv.q.weight
|
357 |
+
layers.22.attention.wqkv.q.scales_and_zeros
|
358 |
+
layers.22.attention.wqkv.k.weight
|
359 |
+
layers.22.attention.wqkv.k.scales_and_zeros
|
360 |
+
layers.22.attention.wqkv.v.weight
|
361 |
+
layers.22.attention.wqkv.v.scales_and_zeros
|
362 |
+
layers.22.attention.wo.weight
|
363 |
+
layers.22.attention.wo.scales_and_zeros
|
364 |
+
layers.22.feed_forward.w1.weight
|
365 |
+
layers.22.feed_forward.w1.scales_and_zeros
|
366 |
+
layers.22.feed_forward.w3.weight
|
367 |
+
layers.22.feed_forward.w3.scales_and_zeros
|
368 |
+
layers.22.feed_forward.w2.weight
|
369 |
+
layers.22.feed_forward.w2.scales_and_zeros
|
370 |
+
layers.22.ffn_norm.weight
|
371 |
+
layers.22.attention_norm.weight
|
372 |
+
layers.23.attention.wqkv.q.weight
|
373 |
+
layers.23.attention.wqkv.q.scales_and_zeros
|
374 |
+
layers.23.attention.wqkv.k.weight
|
375 |
+
layers.23.attention.wqkv.k.scales_and_zeros
|
376 |
+
layers.23.attention.wqkv.v.weight
|
377 |
+
layers.23.attention.wqkv.v.scales_and_zeros
|
378 |
+
layers.23.attention.wo.weight
|
379 |
+
layers.23.attention.wo.scales_and_zeros
|
380 |
+
layers.23.feed_forward.w1.weight
|
381 |
+
layers.23.feed_forward.w1.scales_and_zeros
|
382 |
+
layers.23.feed_forward.w3.weight
|
383 |
+
layers.23.feed_forward.w3.scales_and_zeros
|
384 |
+
layers.23.feed_forward.w2.weight
|
385 |
+
layers.23.feed_forward.w2.scales_and_zeros
|
386 |
+
layers.23.ffn_norm.weight
|
387 |
+
layers.23.attention_norm.weight
|
388 |
+
layers.24.attention.wqkv.q.weight
|
389 |
+
layers.24.attention.wqkv.q.scales_and_zeros
|
390 |
+
layers.24.attention.wqkv.k.weight
|
391 |
+
layers.24.attention.wqkv.k.scales_and_zeros
|
392 |
+
layers.24.attention.wqkv.v.weight
|
393 |
+
layers.24.attention.wqkv.v.scales_and_zeros
|
394 |
+
layers.24.attention.wo.weight
|
395 |
+
layers.24.attention.wo.scales_and_zeros
|
396 |
+
layers.24.feed_forward.w1.weight
|
397 |
+
layers.24.feed_forward.w1.scales_and_zeros
|
398 |
+
layers.24.feed_forward.w3.weight
|
399 |
+
layers.24.feed_forward.w3.scales_and_zeros
|
400 |
+
layers.24.feed_forward.w2.weight
|
401 |
+
layers.24.feed_forward.w2.scales_and_zeros
|
402 |
+
layers.24.ffn_norm.weight
|
403 |
+
layers.24.attention_norm.weight
|
404 |
+
layers.25.attention.wqkv.q.weight
|
405 |
+
layers.25.attention.wqkv.q.scales_and_zeros
|
406 |
+
layers.25.attention.wqkv.k.weight
|
407 |
+
layers.25.attention.wqkv.k.scales_and_zeros
|
408 |
+
layers.25.attention.wqkv.v.weight
|
409 |
+
layers.25.attention.wqkv.v.scales_and_zeros
|
410 |
+
layers.25.attention.wo.weight
|
411 |
+
layers.25.attention.wo.scales_and_zeros
|
412 |
+
layers.25.feed_forward.w1.weight
|
413 |
+
layers.25.feed_forward.w1.scales_and_zeros
|
414 |
+
layers.25.feed_forward.w3.weight
|
415 |
+
layers.25.feed_forward.w3.scales_and_zeros
|
416 |
+
layers.25.feed_forward.w2.weight
|
417 |
+
layers.25.feed_forward.w2.scales_and_zeros
|
418 |
+
layers.25.ffn_norm.weight
|
419 |
+
layers.25.attention_norm.weight
|
420 |
+
layers.26.attention.wqkv.q.weight
|
421 |
+
layers.26.attention.wqkv.q.scales_and_zeros
|
422 |
+
layers.26.attention.wqkv.k.weight
|
423 |
+
layers.26.attention.wqkv.k.scales_and_zeros
|
424 |
+
layers.26.attention.wqkv.v.weight
|
425 |
+
layers.26.attention.wqkv.v.scales_and_zeros
|
426 |
+
layers.26.attention.wo.weight
|
427 |
+
layers.26.attention.wo.scales_and_zeros
|
428 |
+
layers.26.feed_forward.w1.weight
|
429 |
+
layers.26.feed_forward.w1.scales_and_zeros
|
430 |
+
layers.26.feed_forward.w3.weight
|
431 |
+
layers.26.feed_forward.w3.scales_and_zeros
|
432 |
+
layers.26.feed_forward.w2.weight
|
433 |
+
layers.26.feed_forward.w2.scales_and_zeros
|
434 |
+
layers.26.ffn_norm.weight
|
435 |
+
layers.26.attention_norm.weight
|
436 |
+
layers.27.attention.wqkv.q.weight
|
437 |
+
layers.27.attention.wqkv.q.scales_and_zeros
|
438 |
+
layers.27.attention.wqkv.k.weight
|
439 |
+
layers.27.attention.wqkv.k.scales_and_zeros
|
440 |
+
layers.27.attention.wqkv.v.weight
|
441 |
+
layers.27.attention.wqkv.v.scales_and_zeros
|
442 |
+
layers.27.attention.wo.weight
|
443 |
+
layers.27.attention.wo.scales_and_zeros
|
444 |
+
layers.27.feed_forward.w1.weight
|
445 |
+
layers.27.feed_forward.w1.scales_and_zeros
|
446 |
+
layers.27.feed_forward.w3.weight
|
447 |
+
layers.27.feed_forward.w3.scales_and_zeros
|
448 |
+
layers.27.feed_forward.w2.weight
|
449 |
+
layers.27.feed_forward.w2.scales_and_zeros
|
450 |
+
layers.27.ffn_norm.weight
|
451 |
+
layers.27.attention_norm.weight
|
452 |
+
layers.28.attention.wqkv.q.weight
|
453 |
+
layers.28.attention.wqkv.q.scales_and_zeros
|
454 |
+
layers.28.attention.wqkv.k.weight
|
455 |
+
layers.28.attention.wqkv.k.scales_and_zeros
|
456 |
+
layers.28.attention.wqkv.v.weight
|
457 |
+
layers.28.attention.wqkv.v.scales_and_zeros
|
458 |
+
layers.28.attention.wo.weight
|
459 |
+
layers.28.attention.wo.scales_and_zeros
|
460 |
+
layers.28.feed_forward.w1.weight
|
461 |
+
layers.28.feed_forward.w1.scales_and_zeros
|
462 |
+
layers.28.feed_forward.w3.weight
|
463 |
+
layers.28.feed_forward.w3.scales_and_zeros
|
464 |
+
layers.28.feed_forward.w2.weight
|
465 |
+
layers.28.feed_forward.w2.scales_and_zeros
|
466 |
+
layers.28.ffn_norm.weight
|
467 |
+
layers.28.attention_norm.weight
|
468 |
+
layers.29.attention.wqkv.q.weight
|
469 |
+
layers.29.attention.wqkv.q.scales_and_zeros
|
470 |
+
layers.29.attention.wqkv.k.weight
|
471 |
+
layers.29.attention.wqkv.k.scales_and_zeros
|
472 |
+
layers.29.attention.wqkv.v.weight
|
473 |
+
layers.29.attention.wqkv.v.scales_and_zeros
|
474 |
+
layers.29.attention.wo.weight
|
475 |
+
layers.29.attention.wo.scales_and_zeros
|
476 |
+
layers.29.feed_forward.w1.weight
|
477 |
+
layers.29.feed_forward.w1.scales_and_zeros
|
478 |
+
layers.29.feed_forward.w3.weight
|
479 |
+
layers.29.feed_forward.w3.scales_and_zeros
|
480 |
+
layers.29.feed_forward.w2.weight
|
481 |
+
layers.29.feed_forward.w2.scales_and_zeros
|
482 |
+
layers.29.ffn_norm.weight
|
483 |
+
layers.29.attention_norm.weight
|
484 |
+
layers.30.attention.wqkv.q.weight
|
485 |
+
layers.30.attention.wqkv.q.scales_and_zeros
|
486 |
+
layers.30.attention.wqkv.k.weight
|
487 |
+
layers.30.attention.wqkv.k.scales_and_zeros
|
488 |
+
layers.30.attention.wqkv.v.weight
|
489 |
+
layers.30.attention.wqkv.v.scales_and_zeros
|
490 |
+
layers.30.attention.wo.weight
|
491 |
+
layers.30.attention.wo.scales_and_zeros
|
492 |
+
layers.30.feed_forward.w1.weight
|
493 |
+
layers.30.feed_forward.w1.scales_and_zeros
|
494 |
+
layers.30.feed_forward.w3.weight
|
495 |
+
layers.30.feed_forward.w3.scales_and_zeros
|
496 |
+
layers.30.feed_forward.w2.weight
|
497 |
+
layers.30.feed_forward.w2.scales_and_zeros
|
498 |
+
layers.30.ffn_norm.weight
|
499 |
+
layers.30.attention_norm.weight
|
500 |
+
layers.31.attention.wqkv.q.weight
|
501 |
+
layers.31.attention.wqkv.q.scales_and_zeros
|
502 |
+
layers.31.attention.wqkv.k.weight
|
503 |
+
layers.31.attention.wqkv.k.scales_and_zeros
|
504 |
+
layers.31.attention.wqkv.v.weight
|
505 |
+
layers.31.attention.wqkv.v.scales_and_zeros
|
506 |
+
layers.31.attention.wo.weight
|
507 |
+
layers.31.attention.wo.scales_and_zeros
|
508 |
+
layers.31.feed_forward.w1.weight
|
509 |
+
layers.31.feed_forward.w1.scales_and_zeros
|
510 |
+
layers.31.feed_forward.w3.weight
|
511 |
+
layers.31.feed_forward.w3.scales_and_zeros
|
512 |
+
layers.31.feed_forward.w2.weight
|
513 |
+
layers.31.feed_forward.w2.scales_and_zeros
|
514 |
+
layers.31.ffn_norm.weight
|
515 |
+
layers.31.attention_norm.weight
|
516 |
+
norm.weight
|
517 |
+
output.weight
|
518 |
+
output.scales_and_zeros
|