You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Number of experts present in the library: 381

Expert Name Base Model Trained on Adapter Type
51184 meta-llama/Llama-3.1-8B-Instruct /51184 lora
20039 meta-llama/Llama-3.1-8B-Instruct /20039 lora
62212 meta-llama/Llama-3.1-8B-Instruct /62212 lora
61053 meta-llama/Llama-3.1-8B-Instruct /61053 lora
51337 meta-llama/Llama-3.1-8B-Instruct /51337 lora
24966 meta-llama/Llama-3.1-8B-Instruct /24966 lora
61467 meta-llama/Llama-3.1-8B-Instruct /61467 lora
62580 meta-llama/Llama-3.1-8B-Instruct /62580 lora
60412 meta-llama/Llama-3.1-8B-Instruct /60412 lora
51286 meta-llama/Llama-3.1-8B-Instruct /51286 lora
99912 meta-llama/Llama-3.1-8B-Instruct /99912 lora
99902 meta-llama/Llama-3.1-8B-Instruct /99902 lora
20029 meta-llama/Llama-3.1-8B-Instruct /20029 lora
63836 meta-llama/Llama-3.1-8B-Instruct /63836 lora
51433 meta-llama/Llama-3.1-8B-Instruct /51433 lora
61243 meta-llama/Llama-3.1-8B-Instruct /61243 lora
63477 meta-llama/Llama-3.1-8B-Instruct /63477 lora
20064 meta-llama/Llama-3.1-8B-Instruct /20064 lora
51662 meta-llama/Llama-3.1-8B-Instruct /51662 lora
61097 meta-llama/Llama-3.1-8B-Instruct /61097 lora
51413 meta-llama/Llama-3.1-8B-Instruct /51413 lora
99914 meta-llama/Llama-3.1-8B-Instruct /99914 lora
63633 meta-llama/Llama-3.1-8B-Instruct /63633 lora
51534 meta-llama/Llama-3.1-8B-Instruct /51534 lora
24192 meta-llama/Llama-3.1-8B-Instruct /24192 lora
22967 meta-llama/Llama-3.1-8B-Instruct /22967 lora
23588 meta-llama/Llama-3.1-8B-Instruct /23588 lora
51296 meta-llama/Llama-3.1-8B-Instruct /51296 lora
50998 meta-llama/Llama-3.1-8B-Instruct /50998 lora
20045 meta-llama/Llama-3.1-8B-Instruct /20045 lora
62260 meta-llama/Llama-3.1-8B-Instruct /62260 lora
63442 meta-llama/Llama-3.1-8B-Instruct /63442 lora
50449 meta-llama/Llama-3.1-8B-Instruct /50449 lora
51129 meta-llama/Llama-3.1-8B-Instruct /51129 lora
29168 meta-llama/Llama-3.1-8B-Instruct /29168 lora
22073 meta-llama/Llama-3.1-8B-Instruct /22073 lora
20032 meta-llama/Llama-3.1-8B-Instruct /20032 lora
20054 meta-llama/Llama-3.1-8B-Instruct /20054 lora
30029 meta-llama/Llama-3.1-8B-Instruct /30029 lora
50893 meta-llama/Llama-3.1-8B-Instruct /50893 lora
20056 meta-llama/Llama-3.1-8B-Instruct /20056 lora
29193 meta-llama/Llama-3.1-8B-Instruct /29193 lora
62997 meta-llama/Llama-3.1-8B-Instruct /62997 lora
20033 meta-llama/Llama-3.1-8B-Instruct /20033 lora
51688 meta-llama/Llama-3.1-8B-Instruct /51688 lora
20034 meta-llama/Llama-3.1-8B-Instruct /20034 lora
20008 meta-llama/Llama-3.1-8B-Instruct /20008 lora
31736 meta-llama/Llama-3.1-8B-Instruct /31736 lora
51650 meta-llama/Llama-3.1-8B-Instruct /51650 lora
63401 meta-llama/Llama-3.1-8B-Instruct /63401 lora
47989 meta-llama/Llama-3.1-8B-Instruct /47989 lora
99911 meta-llama/Llama-3.1-8B-Instruct /99911 lora
61198 meta-llama/Llama-3.1-8B-Instruct /61198 lora
99920 meta-llama/Llama-3.1-8B-Instruct /99920 lora
62498 meta-llama/Llama-3.1-8B-Instruct /62498 lora
20015 meta-llama/Llama-3.1-8B-Instruct /20015 lora
63527 meta-llama/Llama-3.1-8B-Instruct /63527 lora
20026 meta-llama/Llama-3.1-8B-Instruct /20026 lora
32744 meta-llama/Llama-3.1-8B-Instruct /32744 lora
20058 meta-llama/Llama-3.1-8B-Instruct /20058 lora
20062 meta-llama/Llama-3.1-8B-Instruct /20062 lora
20077 meta-llama/Llama-3.1-8B-Instruct /20077 lora
20060 meta-llama/Llama-3.1-8B-Instruct /20060 lora
62349 meta-llama/Llama-3.1-8B-Instruct /62349 lora
20069 meta-llama/Llama-3.1-8B-Instruct /20069 lora
51231 meta-llama/Llama-3.1-8B-Instruct /51231 lora
50948 meta-llama/Llama-3.1-8B-Instruct /50948 lora
51350 meta-llama/Llama-3.1-8B-Instruct /51350 lora
58733 meta-llama/Llama-3.1-8B-Instruct /58733 lora
63041 meta-llama/Llama-3.1-8B-Instruct /63041 lora
62261 meta-llama/Llama-3.1-8B-Instruct /62261 lora
99915 meta-llama/Llama-3.1-8B-Instruct /99915 lora
62569 meta-llama/Llama-3.1-8B-Instruct /62569 lora
20071 meta-llama/Llama-3.1-8B-Instruct /20071 lora
20048 meta-llama/Llama-3.1-8B-Instruct /20048 lora
49897 meta-llama/Llama-3.1-8B-Instruct /49897 lora
20003 meta-llama/Llama-3.1-8B-Instruct /20003 lora
63645 meta-llama/Llama-3.1-8B-Instruct /63645 lora
20023 meta-llama/Llama-3.1-8B-Instruct /20023 lora
63936 meta-llama/Llama-3.1-8B-Instruct /63936 lora
62619 meta-llama/Llama-3.1-8B-Instruct /62619 lora
23767 meta-llama/Llama-3.1-8B-Instruct /23767 lora
50668 meta-llama/Llama-3.1-8B-Instruct /50668 lora
61481 meta-llama/Llama-3.1-8B-Instruct /61481 lora
50103 meta-llama/Llama-3.1-8B-Instruct /50103 lora
50783 meta-llama/Llama-3.1-8B-Instruct /50783 lora
63605 meta-llama/Llama-3.1-8B-Instruct /63605 lora
23791 meta-llama/Llama-3.1-8B-Instruct /23791 lora
51152 meta-llama/Llama-3.1-8B-Instruct /51152 lora
63097 meta-llama/Llama-3.1-8B-Instruct /63097 lora
99904 meta-llama/Llama-3.1-8B-Instruct /99904 lora
51362 meta-llama/Llama-3.1-8B-Instruct /51362 lora
50571 meta-llama/Llama-3.1-8B-Instruct /50571 lora
63860 meta-llama/Llama-3.1-8B-Instruct /63860 lora
99930 meta-llama/Llama-3.1-8B-Instruct /99930 lora
60747 meta-llama/Llama-3.1-8B-Instruct /60747 lora
25086 meta-llama/Llama-3.1-8B-Instruct /25086 lora
51699 meta-llama/Llama-3.1-8B-Instruct /51699 lora
52326 meta-llama/Llama-3.1-8B-Instruct /52326 lora
22346 meta-llama/Llama-3.1-8B-Instruct /22346 lora
61139 meta-llama/Llama-3.1-8B-Instruct /61139 lora
23563 meta-llama/Llama-3.1-8B-Instruct /23563 lora
61146 meta-llama/Llama-3.1-8B-Instruct /61146 lora
99928 meta-llama/Llama-3.1-8B-Instruct /99928 lora
51395 meta-llama/Llama-3.1-8B-Instruct /51395 lora
50774 meta-llama/Llama-3.1-8B-Instruct /50774 lora
20036 meta-llama/Llama-3.1-8B-Instruct /20036 lora
51407 meta-llama/Llama-3.1-8B-Instruct /51407 lora
40968 meta-llama/Llama-3.1-8B-Instruct /40968 lora
24161 meta-llama/Llama-3.1-8B-Instruct /24161 lora
51201 meta-llama/Llama-3.1-8B-Instruct /51201 lora
51353 meta-llama/Llama-3.1-8B-Instruct /51353 lora
99917 meta-llama/Llama-3.1-8B-Instruct /99917 lora
20013 meta-llama/Llama-3.1-8B-Instruct /20013 lora
99925 meta-llama/Llama-3.1-8B-Instruct /99925 lora
63862 meta-llama/Llama-3.1-8B-Instruct /63862 lora
51330 meta-llama/Llama-3.1-8B-Instruct /51330 lora
51398 meta-llama/Llama-3.1-8B-Instruct /51398 lora
62382 meta-llama/Llama-3.1-8B-Instruct /62382 lora
31355 meta-llama/Llama-3.1-8B-Instruct /31355 lora
50818 meta-llama/Llama-3.1-8B-Instruct /50818 lora
63304 meta-llama/Llama-3.1-8B-Instruct /63304 lora
62476 meta-llama/Llama-3.1-8B-Instruct /62476 lora
63899 meta-llama/Llama-3.1-8B-Instruct /63899 lora
51361 meta-llama/Llama-3.1-8B-Instruct /51361 lora
24247 meta-llama/Llama-3.1-8B-Instruct /24247 lora
24958 meta-llama/Llama-3.1-8B-Instruct /24958 lora
49165 meta-llama/Llama-3.1-8B-Instruct /49165 lora
61228 meta-llama/Llama-3.1-8B-Instruct /61228 lora
55933 meta-llama/Llama-3.1-8B-Instruct /55933 lora
63640 meta-llama/Llama-3.1-8B-Instruct /63640 lora
63473 meta-llama/Llama-3.1-8B-Instruct /63473 lora
20038 meta-llama/Llama-3.1-8B-Instruct /20038 lora
99907 meta-llama/Llama-3.1-8B-Instruct /99907 lora
30062 meta-llama/Llama-3.1-8B-Instruct /30062 lora
50923 meta-llama/Llama-3.1-8B-Instruct /50923 lora
22876 meta-llama/Llama-3.1-8B-Instruct /22876 lora
20027 meta-llama/Llama-3.1-8B-Instruct /20027 lora
50826 meta-llama/Llama-3.1-8B-Instruct /50826 lora
99901 meta-llama/Llama-3.1-8B-Instruct /99901 lora
23592 meta-llama/Llama-3.1-8B-Instruct /23592 lora
27110 meta-llama/Llama-3.1-8B-Instruct /27110 lora
99922 meta-llama/Llama-3.1-8B-Instruct /99922 lora
51170 meta-llama/Llama-3.1-8B-Instruct /51170 lora
60507 meta-llama/Llama-3.1-8B-Instruct /60507 lora
61459 meta-llama/Llama-3.1-8B-Instruct /61459 lora
51267 meta-llama/Llama-3.1-8B-Instruct /51267 lora
26957 meta-llama/Llama-3.1-8B-Instruct /26957 lora
63875 meta-llama/Llama-3.1-8B-Instruct /63875 lora
62198 meta-llama/Llama-3.1-8B-Instruct /62198 lora
63631 meta-llama/Llama-3.1-8B-Instruct /63631 lora
52855 meta-llama/Llama-3.1-8B-Instruct /52855 lora
63919 meta-llama/Llama-3.1-8B-Instruct /63919 lora
32667 meta-llama/Llama-3.1-8B-Instruct /32667 lora
20007 meta-llama/Llama-3.1-8B-Instruct /20007 lora
50766 meta-llama/Llama-3.1-8B-Instruct /50766 lora
20028 meta-llama/Llama-3.1-8B-Instruct /20028 lora
22867 meta-llama/Llama-3.1-8B-Instruct /22867 lora
59368 meta-llama/Llama-3.1-8B-Instruct /59368 lora
99919 meta-llama/Llama-3.1-8B-Instruct /99919 lora
43046 meta-llama/Llama-3.1-8B-Instruct /43046 lora
62324 meta-llama/Llama-3.1-8B-Instruct /62324 lora
51461 meta-llama/Llama-3.1-8B-Instruct /51461 lora
26569 meta-llama/Llama-3.1-8B-Instruct /26569 lora
20063 meta-llama/Llama-3.1-8B-Instruct /20063 lora
24977 meta-llama/Llama-3.1-8B-Instruct /24977 lora
25644 meta-llama/Llama-3.1-8B-Instruct /25644 lora
61171 meta-llama/Llama-3.1-8B-Instruct /61171 lora
51656 meta-llama/Llama-3.1-8B-Instruct /51656 lora
20067 meta-llama/Llama-3.1-8B-Instruct /20067 lora
60515 meta-llama/Llama-3.1-8B-Instruct /60515 lora
22102 meta-llama/Llama-3.1-8B-Instruct /22102 lora
20050 meta-llama/Llama-3.1-8B-Instruct /20050 lora
27588 meta-llama/Llama-3.1-8B-Instruct /27588 lora
29170 meta-llama/Llama-3.1-8B-Instruct /29170 lora
63398 meta-llama/Llama-3.1-8B-Instruct /63398 lora
22875 meta-llama/Llama-3.1-8B-Instruct /22875 lora
61380 meta-llama/Llama-3.1-8B-Instruct /61380 lora
32836 meta-llama/Llama-3.1-8B-Instruct /32836 lora
23104 meta-llama/Llama-3.1-8B-Instruct /23104 lora
99908 meta-llama/Llama-3.1-8B-Instruct /99908 lora
61430 meta-llama/Llama-3.1-8B-Instruct /61430 lora
20075 meta-llama/Llama-3.1-8B-Instruct /20075 lora
59679 meta-llama/Llama-3.1-8B-Instruct /59679 lora
53016 meta-llama/Llama-3.1-8B-Instruct /53016 lora
62244 meta-llama/Llama-3.1-8B-Instruct /62244 lora
50869 meta-llama/Llama-3.1-8B-Instruct /50869 lora
20040 meta-llama/Llama-3.1-8B-Instruct /20040 lora
20055 meta-llama/Llama-3.1-8B-Instruct /20055 lora
50441 meta-llama/Llama-3.1-8B-Instruct /50441 lora
51436 meta-llama/Llama-3.1-8B-Instruct /51436 lora
50868 meta-llama/Llama-3.1-8B-Instruct /50868 lora
50988 meta-llama/Llama-3.1-8B-Instruct /50988 lora
63150 meta-llama/Llama-3.1-8B-Instruct /63150 lora
24290 meta-llama/Llama-3.1-8B-Instruct /24290 lora
60291 meta-llama/Llama-3.1-8B-Instruct /60291 lora
51046 meta-llama/Llama-3.1-8B-Instruct /51046 lora
50827 meta-llama/Llama-3.1-8B-Instruct /50827 lora
61119 meta-llama/Llama-3.1-8B-Instruct /61119 lora
32890 meta-llama/Llama-3.1-8B-Instruct /32890 lora
20012 meta-llama/Llama-3.1-8B-Instruct /20012 lora
51092 meta-llama/Llama-3.1-8B-Instruct /51092 lora
50736 meta-llama/Llama-3.1-8B-Instruct /50736 lora
24275 meta-llama/Llama-3.1-8B-Instruct /24275 lora
60624 meta-llama/Llama-3.1-8B-Instruct /60624 lora
53269 meta-llama/Llama-3.1-8B-Instruct /53269 lora
51210 meta-llama/Llama-3.1-8B-Instruct /51210 lora
61263 meta-llama/Llama-3.1-8B-Instruct /61263 lora
31612 meta-llama/Llama-3.1-8B-Instruct /31612 lora
20017 meta-llama/Llama-3.1-8B-Instruct /20017 lora
61090 meta-llama/Llama-3.1-8B-Instruct /61090 lora
99924 meta-llama/Llama-3.1-8B-Instruct /99924 lora
51344 meta-llama/Llama-3.1-8B-Instruct /51344 lora
25627 meta-llama/Llama-3.1-8B-Instruct /25627 lora
20072 meta-llama/Llama-3.1-8B-Instruct /20072 lora
20035 meta-llama/Llama-3.1-8B-Instruct /20035 lora
63616 meta-llama/Llama-3.1-8B-Instruct /63616 lora
49901 meta-llama/Llama-3.1-8B-Instruct /49901 lora
63833 meta-llama/Llama-3.1-8B-Instruct /63833 lora
20020 meta-llama/Llama-3.1-8B-Instruct /20020 lora
22590 meta-llama/Llama-3.1-8B-Instruct /22590 lora
63916 meta-llama/Llama-3.1-8B-Instruct /63916 lora
40954 meta-llama/Llama-3.1-8B-Instruct /40954 lora
20073 meta-llama/Llama-3.1-8B-Instruct /20073 lora
99906 meta-llama/Llama-3.1-8B-Instruct /99906 lora
61007 meta-llama/Llama-3.1-8B-Instruct /61007 lora
51351 meta-llama/Llama-3.1-8B-Instruct /51351 lora
51295 meta-llama/Llama-3.1-8B-Instruct /51295 lora
60283 meta-llama/Llama-3.1-8B-Instruct /60283 lora
41562 meta-llama/Llama-3.1-8B-Instruct /41562 lora
51310 meta-llama/Llama-3.1-8B-Instruct /51310 lora
63657 meta-llama/Llama-3.1-8B-Instruct /63657 lora
22462 meta-llama/Llama-3.1-8B-Instruct /22462 lora
51241 meta-llama/Llama-3.1-8B-Instruct /51241 lora
51380 meta-llama/Llama-3.1-8B-Instruct /51380 lora
50905 meta-llama/Llama-3.1-8B-Instruct /50905 lora
50928 meta-llama/Llama-3.1-8B-Instruct /50928 lora
63109 meta-llama/Llama-3.1-8B-Instruct /63109 lora
63392 meta-llama/Llama-3.1-8B-Instruct /63392 lora
26066 meta-llama/Llama-3.1-8B-Instruct /26066 lora
59418 meta-llama/Llama-3.1-8B-Instruct /59418 lora
20066 meta-llama/Llama-3.1-8B-Instruct /20066 lora
50847 meta-llama/Llama-3.1-8B-Instruct /50847 lora
63523 meta-llama/Llama-3.1-8B-Instruct /63523 lora
60713 meta-llama/Llama-3.1-8B-Instruct /60713 lora
63130 meta-llama/Llama-3.1-8B-Instruct /63130 lora
51687 meta-llama/Llama-3.1-8B-Instruct /51687 lora
62314 meta-llama/Llama-3.1-8B-Instruct /62314 lora
30035 meta-llama/Llama-3.1-8B-Instruct /30035 lora
61052 meta-llama/Llama-3.1-8B-Instruct /61052 lora
61081 meta-llama/Llama-3.1-8B-Instruct /61081 lora
51075 meta-llama/Llama-3.1-8B-Instruct /51075 lora
99905 meta-llama/Llama-3.1-8B-Instruct /99905 lora
99929 meta-llama/Llama-3.1-8B-Instruct /99929 lora
51305 meta-llama/Llama-3.1-8B-Instruct /51305 lora
61285 meta-llama/Llama-3.1-8B-Instruct /61285 lora
51193 meta-llama/Llama-3.1-8B-Instruct /51193 lora
51609 meta-llama/Llama-3.1-8B-Instruct /51609 lora
99910 meta-llama/Llama-3.1-8B-Instruct /99910 lora
23160 meta-llama/Llama-3.1-8B-Instruct /23160 lora
99923 meta-llama/Llama-3.1-8B-Instruct /99923 lora
51597 meta-llama/Llama-3.1-8B-Instruct /51597 lora
26741 meta-llama/Llama-3.1-8B-Instruct /26741 lora
20041 meta-llama/Llama-3.1-8B-Instruct /20041 lora
62085 meta-llama/Llama-3.1-8B-Instruct /62085 lora
24521 meta-llama/Llama-3.1-8B-Instruct /24521 lora
20047 meta-llama/Llama-3.1-8B-Instruct /20047 lora
24278 meta-llama/Llama-3.1-8B-Instruct /24278 lora
61405 meta-llama/Llama-3.1-8B-Instruct /61405 lora
63867 meta-llama/Llama-3.1-8B-Instruct /63867 lora
22218 meta-llama/Llama-3.1-8B-Instruct /22218 lora
51122 meta-llama/Llama-3.1-8B-Instruct /51122 lora
20002 meta-llama/Llama-3.1-8B-Instruct /20002 lora
27665 meta-llama/Llama-3.1-8B-Instruct /27665 lora
51605 meta-llama/Llama-3.1-8B-Instruct /51605 lora
31599 meta-llama/Llama-3.1-8B-Instruct /31599 lora
99927 meta-llama/Llama-3.1-8B-Instruct /99927 lora
63062 meta-llama/Llama-3.1-8B-Instruct /63062 lora
60995 meta-llama/Llama-3.1-8B-Instruct /60995 lora
42111 meta-llama/Llama-3.1-8B-Instruct /42111 lora
20068 meta-llama/Llama-3.1-8B-Instruct /20068 lora
61434 meta-llama/Llama-3.1-8B-Instruct /61434 lora
51249 meta-llama/Llama-3.1-8B-Instruct /51249 lora
51150 meta-llama/Llama-3.1-8B-Instruct /51150 lora
51445 meta-llama/Llama-3.1-8B-Instruct /51445 lora
20019 meta-llama/Llama-3.1-8B-Instruct /20019 lora
50802 meta-llama/Llama-3.1-8B-Instruct /50802 lora
20001 meta-llama/Llama-3.1-8B-Instruct /20001 lora
20022 meta-llama/Llama-3.1-8B-Instruct /20022 lora
22579 meta-llama/Llama-3.1-8B-Instruct /22579 lora
51167 meta-llama/Llama-3.1-8B-Instruct /51167 lora
50848 meta-llama/Llama-3.1-8B-Instruct /50848 lora
63932 meta-llama/Llama-3.1-8B-Instruct /63932 lora
51449 meta-llama/Llama-3.1-8B-Instruct /51449 lora
26843 meta-llama/Llama-3.1-8B-Instruct /26843 lora
61204 meta-llama/Llama-3.1-8B-Instruct /61204 lora
22966 meta-llama/Llama-3.1-8B-Instruct /22966 lora
51053 meta-llama/Llama-3.1-8B-Instruct /51053 lora
51203 meta-llama/Llama-3.1-8B-Instruct /51203 lora
31282 meta-llama/Llama-3.1-8B-Instruct /31282 lora
22958 meta-llama/Llama-3.1-8B-Instruct /22958 lora
51657 meta-llama/Llama-3.1-8B-Instruct /51657 lora
20053 meta-llama/Llama-3.1-8B-Instruct /20053 lora
31357 meta-llama/Llama-3.1-8B-Instruct /31357 lora
51336 meta-llama/Llama-3.1-8B-Instruct /51336 lora
63855 meta-llama/Llama-3.1-8B-Instruct /63855 lora
23942 meta-llama/Llama-3.1-8B-Instruct /23942 lora
63890 meta-llama/Llama-3.1-8B-Instruct /63890 lora
50566 meta-llama/Llama-3.1-8B-Instruct /50566 lora
61242 meta-llama/Llama-3.1-8B-Instruct /61242 lora
51256 meta-llama/Llama-3.1-8B-Instruct /51256 lora
20046 meta-llama/Llama-3.1-8B-Instruct /20046 lora
20030 meta-llama/Llama-3.1-8B-Instruct /20030 lora
51268 meta-llama/Llama-3.1-8B-Instruct /51268 lora
20049 meta-llama/Llama-3.1-8B-Instruct /20049 lora
20061 meta-llama/Llama-3.1-8B-Instruct /20061 lora
51321 meta-llama/Llama-3.1-8B-Instruct /51321 lora
29159 meta-llama/Llama-3.1-8B-Instruct /29159 lora
99913 meta-llama/Llama-3.1-8B-Instruct /99913 lora
43041 meta-llama/Llama-3.1-8B-Instruct /43041 lora
51320 meta-llama/Llama-3.1-8B-Instruct /51320 lora
20005 meta-llama/Llama-3.1-8B-Instruct /20005 lora
50936 meta-llama/Llama-3.1-8B-Instruct /50936 lora
20042 meta-llama/Llama-3.1-8B-Instruct /20042 lora
99903 meta-llama/Llama-3.1-8B-Instruct /99903 lora
24150 meta-llama/Llama-3.1-8B-Instruct /24150 lora
20057 meta-llama/Llama-3.1-8B-Instruct /20057 lora
47841 meta-llama/Llama-3.1-8B-Instruct /47841 lora
55243 meta-llama/Llama-3.1-8B-Instruct /55243 lora
52995 meta-llama/Llama-3.1-8B-Instruct /52995 lora
52845 meta-llama/Llama-3.1-8B-Instruct /52845 lora
51494 meta-llama/Llama-3.1-8B-Instruct /51494 lora
60897 meta-llama/Llama-3.1-8B-Instruct /60897 lora
61213 meta-llama/Llama-3.1-8B-Instruct /61213 lora
63521 meta-llama/Llama-3.1-8B-Instruct /63521 lora
51194 meta-llama/Llama-3.1-8B-Instruct /51194 lora
51126 meta-llama/Llama-3.1-8B-Instruct /51126 lora
61048 meta-llama/Llama-3.1-8B-Instruct /61048 lora
24949 meta-llama/Llama-3.1-8B-Instruct /24949 lora
51274 meta-llama/Llama-3.1-8B-Instruct /51274 lora
20004 meta-llama/Llama-3.1-8B-Instruct /20004 lora
20011 meta-llama/Llama-3.1-8B-Instruct /20011 lora
99926 meta-llama/Llama-3.1-8B-Instruct /99926 lora
61412 meta-llama/Llama-3.1-8B-Instruct /61412 lora
20014 meta-llama/Llama-3.1-8B-Instruct /20014 lora
22524 meta-llama/Llama-3.1-8B-Instruct /22524 lora
55815 meta-llama/Llama-3.1-8B-Instruct /55815 lora
29196 meta-llama/Llama-3.1-8B-Instruct /29196 lora
20074 meta-llama/Llama-3.1-8B-Instruct /20074 lora
61499 meta-llama/Llama-3.1-8B-Instruct /61499 lora
52844 meta-llama/Llama-3.1-8B-Instruct /52844 lora
60745 meta-llama/Llama-3.1-8B-Instruct /60745 lora
20044 meta-llama/Llama-3.1-8B-Instruct /20044 lora
20051 meta-llama/Llama-3.1-8B-Instruct /20051 lora
50940 meta-llama/Llama-3.1-8B-Instruct /50940 lora
51202 meta-llama/Llama-3.1-8B-Instruct /51202 lora
99909 meta-llama/Llama-3.1-8B-Instruct /99909 lora
24517 meta-llama/Llama-3.1-8B-Instruct /24517 lora
99918 meta-llama/Llama-3.1-8B-Instruct /99918 lora
25629 meta-llama/Llama-3.1-8B-Instruct /25629 lora
62139 meta-llama/Llama-3.1-8B-Instruct /62139 lora
48513 meta-llama/Llama-3.1-8B-Instruct /48513 lora
27492 meta-llama/Llama-3.1-8B-Instruct /27492 lora
20052 meta-llama/Llama-3.1-8B-Instruct /20052 lora
51027 meta-llama/Llama-3.1-8B-Instruct /51027 lora
99921 meta-llama/Llama-3.1-8B-Instruct /99921 lora
20043 meta-llama/Llama-3.1-8B-Instruct /20043 lora
51483 meta-llama/Llama-3.1-8B-Instruct /51483 lora
40965 meta-llama/Llama-3.1-8B-Instruct /40965 lora
20010 meta-llama/Llama-3.1-8B-Instruct /20010 lora
63812 meta-llama/Llama-3.1-8B-Instruct /63812 lora
23960 meta-llama/Llama-3.1-8B-Instruct /23960 lora
32665 meta-llama/Llama-3.1-8B-Instruct /32665 lora
61397 meta-llama/Llama-3.1-8B-Instruct /61397 lora
51651 meta-llama/Llama-3.1-8B-Instruct /51651 lora
20006 meta-llama/Llama-3.1-8B-Instruct /20006 lora
50969 meta-llama/Llama-3.1-8B-Instruct /50969 lora
51072 meta-llama/Llama-3.1-8B-Instruct /51072 lora
99916 meta-llama/Llama-3.1-8B-Instruct /99916 lora
49838 meta-llama/Llama-3.1-8B-Instruct /49838 lora
20031 meta-llama/Llama-3.1-8B-Instruct /20031 lora
Last updated on: 2024-12-28 06:14:03+00:00

Training arguments:

{'max_input_length': 4096, 'class_name': '__main__.KMArguments', 'tokenizer': None, 'model_family': 'gpt', 'modify_modules': '.*', 'modify_layers': 'q_proj|k_proj|v_proj|o_proj', 'tie_params': None, 'lora_rank': 16, 'lora_alpha': 16, 'lora_dropout': 0.05, 'lora_init_b_random': False, 'n_skills': 1, 'n_splits': 1, 'n_embd': 2560, 'n_heads': 8, 'moe_num_experts': 100, 'emb_dim': 128, 'down_proj_layer': 'fc1', 'up_proj_layer': 'fc2', 'model': 'meta-llama/Llama-3.1-8B-Instruct', 'soft_prompt_length': 10, 'n_tasks': None, 'patch_last_k_layers': -1, 'prompt_placement': 'prefix', 'keep_ratio': 1.0, 'block_size': 16, 'sps_type': 'block_sparse', 'use_sparse_bias': True, 'adapter_dtype': None, 'steps_in_mask_selection': 1, 'mask_reselection_interval': 100, 'n_max_mask_reselection': -1, 'mask_updater': None, 'skip_zeros_mask_update': False, 'init_all_ones': False, 'dataset': 'az://mttldata/quality-summaries-qa-llama-8b-instruct', 'data_dir': '/tmp/', 'train_batch_size': 4, 'predict_batch_size': 2, 'max_output_length': 64, 'validation_portion': None, 'padding_side': 'left', 'truncation_side': 'left', 'train_on_inputs': False, 'add_eos_to_targets': True, 'finetune_task_name': 61467, 'subsample_train': None, 'subsample_dev': None, 'subsample_test': None, 'subsample_per_task': False, 'subsample': -1, 'pack_sequences': False, 'pad_to_multiple_of': 8, 'max_seq_per_pack': 4, 'task_id_field': 'task_id', 'task_name_field': 'document_id', 'dataloader_num_workers': 8, 'arc_type': 'ARC-Easy', 'few_shot': True, 'augment_mmlu': False, 'source_template': None, 'augment_few_shot': 0, 'include_template_type': '*', 'include_task_source': 'P3,Flan2021,CoT', 'remove_phi_eval_tasks': False, 'use_only_type': 'summary', 'num_outputs_per_chunk': -1, 'split_train_dev_on': 'output', 'label_frac': 0.23, 'prefix_length': 0, 'prompt': 'Answer the following question. Give only the answer, and no extra commentary, formatting, or chattiness. Question: ', 'include_context': False, 'topk_context': 10, 'subsample_file': None, 'attn_implementation': 'flash_attention_2', 'device_map': 'cpu', 'load_in_4bit': False, 'load_in_8bit': False, 'do_train': True, 'cache_dir': './cache', 'output_dir': '/mnt/output/kms/ql-ll-sum-dcd/61467', 'finetune_task_path': None, 'exp_name': None, 'expert_name': None, 'micro_batch_size': 4, 'compute_strategy': 'auto', 'scheduler': 'linear_decay_with_warmup', 'checkpoint': None, 'checkpoint_step': None, 'backbone_checkpoint': None, 'learning_rate': 0.001, 'warmup_proportion': 0.06, 'trainable_param_names': '.*lora_[ab].*', 'non_trainable_param_names': None, 'weight_decay': 0.0, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.1, 'optimizer': 'adamw', 'adafactor_scale_parameter': True, 'adafactor_warmup_init': False, 'adafactor_relative_step': False, 'num_train_epochs': -1, 'warmup_steps': 90, 'total_steps': 1500, 'num_tasks_per_batch': None, 'save_every': 50, 'save_each_epoch': False, 'eval_every': 50, 'eval_every_n_epoch': -1, 'seed': 42, 'debug': False, 'precision': 'bf16', 'monitor_grad_alignment_on': None, 'wandb_project': None, 'wandb_run_name': 'ql-ll-sum-dcd-61467', 'tensorboard': False, 'remote_token': None, 'library_id': None, 'destination_library_id': None, 'logging_prefix': '', 'router_weight_decay': None, 'router_learning_rate': None, 'module_logits_relaxed_bernoulli': True, 'module_logits_straight_through': False, 'module_logits_learning_rate': 0.1, 'adapters_learning_rate': None, 'adapters_weight_decay': None, 'module_logits_dropout': 0.0, 'module_logits_l2_norm': False, 'eval_mmlu_few_shot': True, 'eval_mmlu_flag': False, 'eval_rouge_flag': False, 'eval_before_training': True, 'create_transfer_matrix': False, 'pipeline_eval_tasks': None, 'save_if_loaded_from_ckpt': True, 'dataset_type': 'dcd_km', 'profile': False, 'model_modifier': 'lora', 'loss_function': 'dcd', 'evaluate_on': 'quality', 'logit_factor': 1.0, 'hidden_factor': 1.0, 'temp': 1.0, 'loss_on_topk': None, 'callback_during_training': False, 'eval_after_training': True, 'patience': None}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.