★ Best checkpoint | epoch=1 | loss=4.4424
Browse files- .gitattributes +1 -0
- checkpoint-best/added_tokens.json +471 -0
- checkpoint-best/chat_template.jinja +47 -0
- checkpoint-best/config.json +54 -0
- checkpoint-best/generation_config.json +11 -0
- checkpoint-best/model.safetensors +3 -0
- checkpoint-best/special_tokens_map.json +33 -0
- checkpoint-best/tokenizer.json +3 -0
- checkpoint-best/tokenizer.model +3 -0
- checkpoint-best/tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-best/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-best/added_tokens.json
ADDED
|
@@ -0,0 +1,471 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<M0>": 262147,
|
| 3 |
+
"<M100>": 262247,
|
| 4 |
+
"<M101>": 262248,
|
| 5 |
+
"<M102>": 262249,
|
| 6 |
+
"<M103>": 262250,
|
| 7 |
+
"<M104>": 262251,
|
| 8 |
+
"<M105>": 262252,
|
| 9 |
+
"<M106>": 262253,
|
| 10 |
+
"<M107>": 262254,
|
| 11 |
+
"<M108>": 262255,
|
| 12 |
+
"<M109>": 262256,
|
| 13 |
+
"<M10>": 262157,
|
| 14 |
+
"<M110>": 262257,
|
| 15 |
+
"<M111>": 262258,
|
| 16 |
+
"<M112>": 262259,
|
| 17 |
+
"<M113>": 262260,
|
| 18 |
+
"<M114>": 262261,
|
| 19 |
+
"<M115>": 262262,
|
| 20 |
+
"<M116>": 262263,
|
| 21 |
+
"<M117>": 262264,
|
| 22 |
+
"<M118>": 262265,
|
| 23 |
+
"<M119>": 262266,
|
| 24 |
+
"<M11>": 262158,
|
| 25 |
+
"<M120>": 262267,
|
| 26 |
+
"<M121>": 262268,
|
| 27 |
+
"<M122>": 262269,
|
| 28 |
+
"<M123>": 262270,
|
| 29 |
+
"<M124>": 262271,
|
| 30 |
+
"<M125>": 262272,
|
| 31 |
+
"<M126>": 262273,
|
| 32 |
+
"<M127>": 262274,
|
| 33 |
+
"<M128>": 262275,
|
| 34 |
+
"<M129>": 262276,
|
| 35 |
+
"<M12>": 262159,
|
| 36 |
+
"<M130>": 262277,
|
| 37 |
+
"<M131>": 262278,
|
| 38 |
+
"<M132>": 262279,
|
| 39 |
+
"<M133>": 262280,
|
| 40 |
+
"<M134>": 262281,
|
| 41 |
+
"<M135>": 262282,
|
| 42 |
+
"<M136>": 262283,
|
| 43 |
+
"<M137>": 262284,
|
| 44 |
+
"<M138>": 262285,
|
| 45 |
+
"<M139>": 262286,
|
| 46 |
+
"<M13>": 262160,
|
| 47 |
+
"<M140>": 262287,
|
| 48 |
+
"<M141>": 262288,
|
| 49 |
+
"<M142>": 262289,
|
| 50 |
+
"<M143>": 262290,
|
| 51 |
+
"<M144>": 262291,
|
| 52 |
+
"<M145>": 262292,
|
| 53 |
+
"<M146>": 262293,
|
| 54 |
+
"<M147>": 262294,
|
| 55 |
+
"<M148>": 262295,
|
| 56 |
+
"<M149>": 262296,
|
| 57 |
+
"<M14>": 262161,
|
| 58 |
+
"<M150>": 262297,
|
| 59 |
+
"<M151>": 262298,
|
| 60 |
+
"<M152>": 262299,
|
| 61 |
+
"<M153>": 262300,
|
| 62 |
+
"<M154>": 262301,
|
| 63 |
+
"<M155>": 262302,
|
| 64 |
+
"<M156>": 262303,
|
| 65 |
+
"<M157>": 262304,
|
| 66 |
+
"<M158>": 262305,
|
| 67 |
+
"<M159>": 262306,
|
| 68 |
+
"<M15>": 262162,
|
| 69 |
+
"<M160>": 262307,
|
| 70 |
+
"<M161>": 262308,
|
| 71 |
+
"<M162>": 262309,
|
| 72 |
+
"<M163>": 262310,
|
| 73 |
+
"<M164>": 262311,
|
| 74 |
+
"<M165>": 262312,
|
| 75 |
+
"<M166>": 262313,
|
| 76 |
+
"<M167>": 262314,
|
| 77 |
+
"<M168>": 262315,
|
| 78 |
+
"<M169>": 262316,
|
| 79 |
+
"<M16>": 262163,
|
| 80 |
+
"<M170>": 262317,
|
| 81 |
+
"<M171>": 262318,
|
| 82 |
+
"<M172>": 262319,
|
| 83 |
+
"<M173>": 262320,
|
| 84 |
+
"<M174>": 262321,
|
| 85 |
+
"<M175>": 262322,
|
| 86 |
+
"<M176>": 262323,
|
| 87 |
+
"<M177>": 262324,
|
| 88 |
+
"<M178>": 262325,
|
| 89 |
+
"<M179>": 262326,
|
| 90 |
+
"<M17>": 262164,
|
| 91 |
+
"<M180>": 262327,
|
| 92 |
+
"<M181>": 262328,
|
| 93 |
+
"<M182>": 262329,
|
| 94 |
+
"<M183>": 262330,
|
| 95 |
+
"<M184>": 262331,
|
| 96 |
+
"<M185>": 262332,
|
| 97 |
+
"<M186>": 262333,
|
| 98 |
+
"<M187>": 262334,
|
| 99 |
+
"<M188>": 262335,
|
| 100 |
+
"<M18>": 262165,
|
| 101 |
+
"<M190>": 262336,
|
| 102 |
+
"<M191>": 262337,
|
| 103 |
+
"<M192>": 262338,
|
| 104 |
+
"<M194>": 262339,
|
| 105 |
+
"<M196>": 262340,
|
| 106 |
+
"<M197>": 262341,
|
| 107 |
+
"<M198>": 262342,
|
| 108 |
+
"<M199>": 262343,
|
| 109 |
+
"<M19>": 262166,
|
| 110 |
+
"<M1>": 262148,
|
| 111 |
+
"<M200>": 262344,
|
| 112 |
+
"<M205>": 262345,
|
| 113 |
+
"<M206>": 262346,
|
| 114 |
+
"<M207>": 262347,
|
| 115 |
+
"<M208>": 262348,
|
| 116 |
+
"<M209>": 262349,
|
| 117 |
+
"<M20>": 262167,
|
| 118 |
+
"<M210>": 262350,
|
| 119 |
+
"<M211>": 262351,
|
| 120 |
+
"<M212>": 262352,
|
| 121 |
+
"<M213>": 262353,
|
| 122 |
+
"<M214>": 262354,
|
| 123 |
+
"<M215>": 262355,
|
| 124 |
+
"<M216>": 262356,
|
| 125 |
+
"<M217>": 262357,
|
| 126 |
+
"<M218>": 262358,
|
| 127 |
+
"<M219>": 262359,
|
| 128 |
+
"<M21>": 262168,
|
| 129 |
+
"<M220>": 262360,
|
| 130 |
+
"<M221>": 262361,
|
| 131 |
+
"<M222>": 262362,
|
| 132 |
+
"<M223>": 262363,
|
| 133 |
+
"<M224>": 262364,
|
| 134 |
+
"<M225>": 262365,
|
| 135 |
+
"<M226>": 262366,
|
| 136 |
+
"<M227>": 262367,
|
| 137 |
+
"<M228>": 262368,
|
| 138 |
+
"<M229>": 262369,
|
| 139 |
+
"<M22>": 262169,
|
| 140 |
+
"<M230>": 262370,
|
| 141 |
+
"<M231>": 262371,
|
| 142 |
+
"<M232>": 262372,
|
| 143 |
+
"<M233>": 262373,
|
| 144 |
+
"<M234>": 262374,
|
| 145 |
+
"<M235>": 262375,
|
| 146 |
+
"<M236>": 262376,
|
| 147 |
+
"<M238>": 262377,
|
| 148 |
+
"<M239>": 262378,
|
| 149 |
+
"<M23>": 262170,
|
| 150 |
+
"<M240>": 262379,
|
| 151 |
+
"<M241>": 262380,
|
| 152 |
+
"<M242>": 262381,
|
| 153 |
+
"<M243>": 262382,
|
| 154 |
+
"<M244>": 262383,
|
| 155 |
+
"<M245>": 262384,
|
| 156 |
+
"<M246>": 262385,
|
| 157 |
+
"<M247>": 262386,
|
| 158 |
+
"<M248>": 262387,
|
| 159 |
+
"<M24>": 262171,
|
| 160 |
+
"<M250>": 262388,
|
| 161 |
+
"<M252>": 262389,
|
| 162 |
+
"<M254>": 262390,
|
| 163 |
+
"<M256>": 262391,
|
| 164 |
+
"<M257>": 262392,
|
| 165 |
+
"<M258>": 262393,
|
| 166 |
+
"<M259>": 262394,
|
| 167 |
+
"<M25>": 262172,
|
| 168 |
+
"<M260>": 262395,
|
| 169 |
+
"<M261>": 262396,
|
| 170 |
+
"<M262>": 262397,
|
| 171 |
+
"<M263>": 262398,
|
| 172 |
+
"<M264>": 262399,
|
| 173 |
+
"<M265>": 262400,
|
| 174 |
+
"<M266>": 262401,
|
| 175 |
+
"<M267>": 262402,
|
| 176 |
+
"<M268>": 262403,
|
| 177 |
+
"<M269>": 262404,
|
| 178 |
+
"<M26>": 262173,
|
| 179 |
+
"<M270>": 262405,
|
| 180 |
+
"<M271>": 262406,
|
| 181 |
+
"<M272>": 262407,
|
| 182 |
+
"<M273>": 262408,
|
| 183 |
+
"<M274>": 262409,
|
| 184 |
+
"<M275>": 262410,
|
| 185 |
+
"<M276>": 262411,
|
| 186 |
+
"<M277>": 262412,
|
| 187 |
+
"<M278>": 262413,
|
| 188 |
+
"<M27>": 262174,
|
| 189 |
+
"<M280>": 262414,
|
| 190 |
+
"<M282>": 262415,
|
| 191 |
+
"<M283>": 262416,
|
| 192 |
+
"<M284>": 262417,
|
| 193 |
+
"<M285>": 262418,
|
| 194 |
+
"<M286>": 262419,
|
| 195 |
+
"<M287>": 262420,
|
| 196 |
+
"<M289>": 262421,
|
| 197 |
+
"<M28>": 262175,
|
| 198 |
+
"<M290>": 262422,
|
| 199 |
+
"<M291>": 262423,
|
| 200 |
+
"<M292>": 262424,
|
| 201 |
+
"<M293>": 262425,
|
| 202 |
+
"<M295>": 262426,
|
| 203 |
+
"<M296>": 262427,
|
| 204 |
+
"<M297>": 262428,
|
| 205 |
+
"<M298>": 262429,
|
| 206 |
+
"<M29>": 262176,
|
| 207 |
+
"<M2>": 262149,
|
| 208 |
+
"<M300>": 262430,
|
| 209 |
+
"<M303>": 262431,
|
| 210 |
+
"<M304>": 262432,
|
| 211 |
+
"<M306>": 262433,
|
| 212 |
+
"<M307>": 262434,
|
| 213 |
+
"<M308>": 262435,
|
| 214 |
+
"<M309>": 262436,
|
| 215 |
+
"<M30>": 262177,
|
| 216 |
+
"<M310>": 262437,
|
| 217 |
+
"<M311>": 262438,
|
| 218 |
+
"<M312>": 262439,
|
| 219 |
+
"<M313>": 262440,
|
| 220 |
+
"<M315>": 262441,
|
| 221 |
+
"<M316>": 262442,
|
| 222 |
+
"<M317>": 262443,
|
| 223 |
+
"<M318>": 262444,
|
| 224 |
+
"<M319>": 262445,
|
| 225 |
+
"<M31>": 262178,
|
| 226 |
+
"<M320>": 262446,
|
| 227 |
+
"<M321>": 262447,
|
| 228 |
+
"<M322>": 262448,
|
| 229 |
+
"<M323>": 262449,
|
| 230 |
+
"<M324>": 262450,
|
| 231 |
+
"<M325>": 262451,
|
| 232 |
+
"<M326>": 262452,
|
| 233 |
+
"<M327>": 262453,
|
| 234 |
+
"<M328>": 262454,
|
| 235 |
+
"<M329>": 262455,
|
| 236 |
+
"<M32>": 262179,
|
| 237 |
+
"<M330>": 262456,
|
| 238 |
+
"<M332>": 262457,
|
| 239 |
+
"<M333>": 262458,
|
| 240 |
+
"<M334>": 262459,
|
| 241 |
+
"<M335>": 262460,
|
| 242 |
+
"<M336>": 262461,
|
| 243 |
+
"<M337>": 262462,
|
| 244 |
+
"<M338>": 262463,
|
| 245 |
+
"<M33>": 262180,
|
| 246 |
+
"<M342>": 262464,
|
| 247 |
+
"<M343>": 262465,
|
| 248 |
+
"<M345>": 262466,
|
| 249 |
+
"<M346>": 262467,
|
| 250 |
+
"<M347>": 262468,
|
| 251 |
+
"<M348>": 262469,
|
| 252 |
+
"<M349>": 262470,
|
| 253 |
+
"<M34>": 262181,
|
| 254 |
+
"<M350>": 262471,
|
| 255 |
+
"<M351>": 262472,
|
| 256 |
+
"<M352>": 262473,
|
| 257 |
+
"<M353>": 262474,
|
| 258 |
+
"<M354>": 262475,
|
| 259 |
+
"<M355>": 262476,
|
| 260 |
+
"<M356>": 262477,
|
| 261 |
+
"<M357>": 262478,
|
| 262 |
+
"<M359>": 262479,
|
| 263 |
+
"<M35>": 262182,
|
| 264 |
+
"<M360>": 262480,
|
| 265 |
+
"<M362>": 262481,
|
| 266 |
+
"<M363>": 262482,
|
| 267 |
+
"<M364>": 262483,
|
| 268 |
+
"<M365>": 262484,
|
| 269 |
+
"<M366>": 262485,
|
| 270 |
+
"<M367>": 262486,
|
| 271 |
+
"<M368>": 262487,
|
| 272 |
+
"<M369>": 262488,
|
| 273 |
+
"<M36>": 262183,
|
| 274 |
+
"<M370>": 262489,
|
| 275 |
+
"<M371>": 262490,
|
| 276 |
+
"<M372>": 262491,
|
| 277 |
+
"<M373>": 262492,
|
| 278 |
+
"<M374>": 262493,
|
| 279 |
+
"<M375>": 262494,
|
| 280 |
+
"<M376>": 262495,
|
| 281 |
+
"<M378>": 262496,
|
| 282 |
+
"<M379>": 262497,
|
| 283 |
+
"<M37>": 262184,
|
| 284 |
+
"<M380>": 262498,
|
| 285 |
+
"<M381>": 262499,
|
| 286 |
+
"<M382>": 262500,
|
| 287 |
+
"<M383>": 262501,
|
| 288 |
+
"<M384>": 262502,
|
| 289 |
+
"<M385>": 262503,
|
| 290 |
+
"<M386>": 262504,
|
| 291 |
+
"<M387>": 262505,
|
| 292 |
+
"<M388>": 262506,
|
| 293 |
+
"<M389>": 262507,
|
| 294 |
+
"<M38>": 262185,
|
| 295 |
+
"<M390>": 262508,
|
| 296 |
+
"<M391>": 262509,
|
| 297 |
+
"<M392>": 262510,
|
| 298 |
+
"<M393>": 262511,
|
| 299 |
+
"<M395>": 262512,
|
| 300 |
+
"<M396>": 262513,
|
| 301 |
+
"<M398>": 262514,
|
| 302 |
+
"<M39>": 262186,
|
| 303 |
+
"<M3>": 262150,
|
| 304 |
+
"<M402>": 262515,
|
| 305 |
+
"<M403>": 262516,
|
| 306 |
+
"<M404>": 262517,
|
| 307 |
+
"<M405>": 262518,
|
| 308 |
+
"<M406>": 262519,
|
| 309 |
+
"<M408>": 262520,
|
| 310 |
+
"<M409>": 262521,
|
| 311 |
+
"<M40>": 262187,
|
| 312 |
+
"<M410>": 262522,
|
| 313 |
+
"<M411>": 262523,
|
| 314 |
+
"<M412>": 262524,
|
| 315 |
+
"<M413>": 262525,
|
| 316 |
+
"<M414>": 262526,
|
| 317 |
+
"<M416>": 262527,
|
| 318 |
+
"<M418>": 262528,
|
| 319 |
+
"<M419>": 262529,
|
| 320 |
+
"<M41>": 262188,
|
| 321 |
+
"<M421>": 262530,
|
| 322 |
+
"<M422>": 262531,
|
| 323 |
+
"<M423>": 262532,
|
| 324 |
+
"<M424>": 262533,
|
| 325 |
+
"<M426>": 262534,
|
| 326 |
+
"<M427>": 262535,
|
| 327 |
+
"<M428>": 262536,
|
| 328 |
+
"<M429>": 262537,
|
| 329 |
+
"<M42>": 262189,
|
| 330 |
+
"<M430>": 262538,
|
| 331 |
+
"<M431>": 262539,
|
| 332 |
+
"<M432>": 262540,
|
| 333 |
+
"<M433>": 262541,
|
| 334 |
+
"<M434>": 262542,
|
| 335 |
+
"<M435>": 262543,
|
| 336 |
+
"<M436>": 262544,
|
| 337 |
+
"<M437>": 262545,
|
| 338 |
+
"<M438>": 262546,
|
| 339 |
+
"<M439>": 262547,
|
| 340 |
+
"<M43>": 262190,
|
| 341 |
+
"<M440>": 262548,
|
| 342 |
+
"<M441>": 262549,
|
| 343 |
+
"<M442>": 262550,
|
| 344 |
+
"<M443>": 262551,
|
| 345 |
+
"<M444>": 262552,
|
| 346 |
+
"<M445>": 262553,
|
| 347 |
+
"<M446>": 262554,
|
| 348 |
+
"<M447>": 262555,
|
| 349 |
+
"<M448>": 262556,
|
| 350 |
+
"<M449>": 262557,
|
| 351 |
+
"<M44>": 262191,
|
| 352 |
+
"<M450>": 262558,
|
| 353 |
+
"<M451>": 262559,
|
| 354 |
+
"<M452>": 262560,
|
| 355 |
+
"<M454>": 262561,
|
| 356 |
+
"<M455>": 262562,
|
| 357 |
+
"<M456>": 262563,
|
| 358 |
+
"<M457>": 262564,
|
| 359 |
+
"<M458>": 262565,
|
| 360 |
+
"<M459>": 262566,
|
| 361 |
+
"<M45>": 262192,
|
| 362 |
+
"<M460>": 262567,
|
| 363 |
+
"<M461>": 262568,
|
| 364 |
+
"<M462>": 262569,
|
| 365 |
+
"<M463>": 262570,
|
| 366 |
+
"<M464>": 262571,
|
| 367 |
+
"<M465>": 262572,
|
| 368 |
+
"<M466>": 262573,
|
| 369 |
+
"<M467>": 262574,
|
| 370 |
+
"<M468>": 262575,
|
| 371 |
+
"<M469>": 262576,
|
| 372 |
+
"<M46>": 262193,
|
| 373 |
+
"<M470>": 262577,
|
| 374 |
+
"<M471>": 262578,
|
| 375 |
+
"<M472>": 262579,
|
| 376 |
+
"<M473>": 262580,
|
| 377 |
+
"<M474>": 262581,
|
| 378 |
+
"<M475>": 262582,
|
| 379 |
+
"<M477>": 262583,
|
| 380 |
+
"<M479>": 262584,
|
| 381 |
+
"<M47>": 262194,
|
| 382 |
+
"<M481>": 262585,
|
| 383 |
+
"<M483>": 262586,
|
| 384 |
+
"<M484>": 262587,
|
| 385 |
+
"<M485>": 262588,
|
| 386 |
+
"<M487>": 262589,
|
| 387 |
+
"<M489>": 262590,
|
| 388 |
+
"<M48>": 262195,
|
| 389 |
+
"<M490>": 262591,
|
| 390 |
+
"<M491>": 262592,
|
| 391 |
+
"<M492>": 262593,
|
| 392 |
+
"<M493>": 262594,
|
| 393 |
+
"<M494>": 262595,
|
| 394 |
+
"<M495>": 262596,
|
| 395 |
+
"<M496>": 262597,
|
| 396 |
+
"<M497>": 262598,
|
| 397 |
+
"<M498>": 262599,
|
| 398 |
+
"<M499>": 262600,
|
| 399 |
+
"<M49>": 262196,
|
| 400 |
+
"<M4>": 262151,
|
| 401 |
+
"<M500>": 262601,
|
| 402 |
+
"<M501>": 262602,
|
| 403 |
+
"<M502>": 262603,
|
| 404 |
+
"<M503>": 262604,
|
| 405 |
+
"<M504>": 262605,
|
| 406 |
+
"<M505>": 262606,
|
| 407 |
+
"<M506>": 262607,
|
| 408 |
+
"<M507>": 262608,
|
| 409 |
+
"<M508>": 262609,
|
| 410 |
+
"<M509>": 262610,
|
| 411 |
+
"<M50>": 262197,
|
| 412 |
+
"<M510>": 262611,
|
| 413 |
+
"<M511>": 262612,
|
| 414 |
+
"<M51>": 262198,
|
| 415 |
+
"<M52>": 262199,
|
| 416 |
+
"<M53>": 262200,
|
| 417 |
+
"<M54>": 262201,
|
| 418 |
+
"<M55>": 262202,
|
| 419 |
+
"<M56>": 262203,
|
| 420 |
+
"<M57>": 262204,
|
| 421 |
+
"<M58>": 262205,
|
| 422 |
+
"<M59>": 262206,
|
| 423 |
+
"<M5>": 262152,
|
| 424 |
+
"<M60>": 262207,
|
| 425 |
+
"<M61>": 262208,
|
| 426 |
+
"<M62>": 262209,
|
| 427 |
+
"<M63>": 262210,
|
| 428 |
+
"<M64>": 262211,
|
| 429 |
+
"<M65>": 262212,
|
| 430 |
+
"<M66>": 262213,
|
| 431 |
+
"<M67>": 262214,
|
| 432 |
+
"<M68>": 262215,
|
| 433 |
+
"<M69>": 262216,
|
| 434 |
+
"<M6>": 262153,
|
| 435 |
+
"<M70>": 262217,
|
| 436 |
+
"<M71>": 262218,
|
| 437 |
+
"<M72>": 262219,
|
| 438 |
+
"<M73>": 262220,
|
| 439 |
+
"<M74>": 262221,
|
| 440 |
+
"<M75>": 262222,
|
| 441 |
+
"<M76>": 262223,
|
| 442 |
+
"<M77>": 262224,
|
| 443 |
+
"<M78>": 262225,
|
| 444 |
+
"<M79>": 262226,
|
| 445 |
+
"<M7>": 262154,
|
| 446 |
+
"<M80>": 262227,
|
| 447 |
+
"<M81>": 262228,
|
| 448 |
+
"<M82>": 262229,
|
| 449 |
+
"<M83>": 262230,
|
| 450 |
+
"<M84>": 262231,
|
| 451 |
+
"<M85>": 262232,
|
| 452 |
+
"<M86>": 262233,
|
| 453 |
+
"<M87>": 262234,
|
| 454 |
+
"<M88>": 262235,
|
| 455 |
+
"<M89>": 262236,
|
| 456 |
+
"<M8>": 262155,
|
| 457 |
+
"<M90>": 262237,
|
| 458 |
+
"<M91>": 262238,
|
| 459 |
+
"<M92>": 262239,
|
| 460 |
+
"<M93>": 262240,
|
| 461 |
+
"<M94>": 262241,
|
| 462 |
+
"<M95>": 262242,
|
| 463 |
+
"<M96>": 262243,
|
| 464 |
+
"<M97>": 262244,
|
| 465 |
+
"<M98>": 262245,
|
| 466 |
+
"<M99>": 262246,
|
| 467 |
+
"<M9>": 262156,
|
| 468 |
+
"<M_END>": 262146,
|
| 469 |
+
"<M_START>": 262145,
|
| 470 |
+
"<image_soft_token>": 262144
|
| 471 |
+
}
|
checkpoint-best/chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
checkpoint-best/config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 2048,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention"
|
| 37 |
+
],
|
| 38 |
+
"max_position_embeddings": 32768,
|
| 39 |
+
"model_type": "gemma3_text",
|
| 40 |
+
"num_attention_heads": 4,
|
| 41 |
+
"num_hidden_layers": 18,
|
| 42 |
+
"num_key_value_heads": 1,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"query_pre_attn_scalar": 256,
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_local_base_freq": 10000.0,
|
| 47 |
+
"rope_scaling": null,
|
| 48 |
+
"rope_theta": 1000000.0,
|
| 49 |
+
"sliding_window": 512,
|
| 50 |
+
"transformers_version": "4.57.6",
|
| 51 |
+
"use_bidirectional_attention": false,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 262613
|
| 54 |
+
}
|
checkpoint-best/generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_implementation": "hybrid",
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106
|
| 7 |
+
],
|
| 8 |
+
"top_k": 64,
|
| 9 |
+
"top_p": 0.95,
|
| 10 |
+
"transformers_version": "4.57.6"
|
| 11 |
+
}
|
checkpoint-best/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7546287b518c6589b330634007b238a5f4532f8adc69915faaf08ebe0364e2a0
|
| 3 |
+
size 1073619904
|
checkpoint-best/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
checkpoint-best/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4508188ef586fd9b7974e820d55442a0c83a8a1842a23bdfd33407d276be9176
|
| 3 |
+
size 33470204
|
checkpoint-best/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-best/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|