Vocabulary Expansion for Low-resource Cross-lingual Transfer
Paper
•
2406.11477
•
Published
Low-resource Vocabulary Expansion
Collection of models for "How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?"
-
-
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-rand
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-1000-rand-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-focus
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2stage-mtp-512
Text Generation • 7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-mean
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2stage-mtp-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-de-30K-rand
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage-mtp-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-512
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-merge
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-rand
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2stage-mtp-512
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2x2ls-mtp
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-1000-mean-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-5000-mean-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2stage-mtp
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-5000-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-5000-mean-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-mtp-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-50-align-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-50-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2x2ls
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-focus
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-mean
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-mean-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-rand-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-th-30K-mean
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-de-30K-align
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2stage-mtp
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-512
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2stage
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2stage-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2stage-mtp-512
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2x2ls
Text Generation • 7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2x2ls-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2x2ls-mtp
7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-mtp
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align-mtp-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-focus
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-merge
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-rand
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-de-30K-focus
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-de-30K-merge
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-de-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-de-30K-mean
Text Generation • 7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2stage-mtp
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2x2ls
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2x2ls-mtp
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2x2ls-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-mtp
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-align-mtp-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-focus
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-el-30K-mean
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2stage
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2stage-512
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2stage-mtp
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2x2ls
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-2x2ls-512
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-mtp
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-align-mtp-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-focus
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-mean
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-merge
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-hi-30K-rand
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-ja-30K-align
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-ja-30K-focus
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-ja-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-ja-30K-mean
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-ja-30K-merge
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-ja-30K-rand
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-1000-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-1000-rand-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-5000-align-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-5000-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-500-align-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-500-mean-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-500-rand-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-50-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-50-mean-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-50-rand-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align
Text Generation • 7B • Updated • 2 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2stage
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2stage-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2x2ls
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2x2ls-512
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2x2ls-mtp
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-mtp-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-align-mtp
Text Generation • 7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-focus
Text Generation • 7B • Updated • 2 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-mean
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-mean-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-rand-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-merge
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-my-30K-rand
Text Generation • 7B • Updated • 2 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-1000-align-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-1000-mean-2x2ls-mtp-512
7B • Updated • 1 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-1000-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-5000-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-500-align-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-500-mean-2x2ls-mtp-512
7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-500-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-50-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2stage
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-50-mean-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-50-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2stage-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2stage-mtp
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2x2ls
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2x2ls-512
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2x2ls-mtp
7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-512
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-align-mtp
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-mean-2x2ls-mtp-512
7B • Updated • 7 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-mean
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-merge
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-si-30K-rand
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-align
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-focus
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-mean
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-sw-30K-merge
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-1000-align-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-1000-mean-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-5000-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-5000-mean-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-5000-rand-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-500-align-2x2ls-mtp-512
7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-500-mean-2x2ls-mtp-512
7B • Updated • 4 -
atsuki-yamaguchi/Llama-3-8B-my-30K-50-align
9B • Updated • 9 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-500-rand-2x2ls-mtp-512
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-50-mean-2x2ls-mtp-512
7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2stage
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2stage-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2stage-mtp
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2stage-mtp-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2x2ls-512
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-2x2ls-mtp
7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-mtp
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-align-mtp-512
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-merge
Text Generation • 7B • Updated • 2 -
atsuki-yamaguchi/Llama-2-7b-hf-te-30K-rand
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-th-30K-align
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-2-7b-hf-th-30K-focus
Text Generation • 7B • Updated • 4 -
atsuki-yamaguchi/Llama-2-7b-hf-th-30K-lapt
Updated -
atsuki-yamaguchi/Llama-2-7b-hf-ar-30K-align
Text Generation • 7B • Updated • 6 -
atsuki-yamaguchi/Llama-2-7b-hf-th-30K-merge
Text Generation • 7B • Updated • 3 -
atsuki-yamaguchi/Llama-2-7b-hf-th-30K-rand
Text Generation • 7B • Updated • 5 -
atsuki-yamaguchi/Llama-3-8B-si-30K-100-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-si-30K-1000-align
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-te-30K-5000-mean
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-5000-rand
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-500-align
9B • Updated • 24 -
atsuki-yamaguchi/Llama-3-8B-si-30K-1000-mean
9B • Updated • 5 -
atsuki-yamaguchi/Llama-3-8B-si-30K-1000-rand
9B • Updated • 5 -
atsuki-yamaguchi/Llama-3-8B-si-30K-100-mean
9B • Updated • 3 -
atsuki-yamaguchi/Llama-3-8B-si-30K-5000-align
9B • Updated • 8 -
atsuki-yamaguchi/Llama-3-8B-si-30K-5000-mean
9B • Updated • 8 -
atsuki-yamaguchi/Llama-3-8B-si-30K-5000-rand
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-si-30K-500-align
9B • Updated • 9 -
atsuki-yamaguchi/Llama-3-8B-si-30K-500-rand
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-te-30K-1000-align
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-te-30K-1000-rand
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-te-30K-500-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-te-30K-50-mean
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-my-30K-5000-align
9B • Updated • 4 -
atsuki-yamaguchi/Llama-3-8B-my-30K-1000-mean
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-my-30K-100-mean
9B • Updated • 4 -
atsuki-yamaguchi/Llama-3-8B-my-30K-1000-rand
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-100-align
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-my-30K-100-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-my-30K-5000-mean
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-500-mean
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-my-30K-500-rand
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-50-mean
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-50-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-my-30K-lapt
Updated -
atsuki-yamaguchi/Llama-3-8B-si-30K-100-align
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-si-30K-500-mean
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-si-30K-50-align
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-si-30K-50-mean
9B • Updated • 5 -
atsuki-yamaguchi/Llama-3-8B-si-30K-50-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-si-30K-lapt
Updated -
atsuki-yamaguchi/Llama-3-8B-te-30K-1000-mean
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-te-30K-100-align
9B • Updated • 4 -
atsuki-yamaguchi/Llama-3-8B-te-30K-100-mean
9B • Updated • 8 -
atsuki-yamaguchi/Llama-3-8B-te-30K-100-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-te-30K-5000-align
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-te-30K-5000-rand
9B • Updated • 7 -
atsuki-yamaguchi/Llama-3-8B-te-30K-500-align
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-te-30K-500-mean
9B • Updated • 8 -
atsuki-yamaguchi/Llama-3-8B-te-30K-50-align
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-my-30K-1000-align
9B • Updated • 6 -
atsuki-yamaguchi/Llama-3-8B-te-30K-50-rand
9B • Updated • 5 -
atsuki-yamaguchi/Llama-3-8B-te-30K-lapt
Updated -
atsuki-yamaguchi/gemma-2-9b-my-30K-1000-rand
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-te-30K-5000-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-5000-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-my-30K-5000-mean
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-my-30K-align
10B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-te-30K-1000-mean
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-my-30K-5000-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-1000-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-50-mean
10B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-te-30K-align
10B • Updated • 5 • 1 -
atsuki-yamaguchi/gemma-2-9b-si-30K-50-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-500-mean
10B • Updated • 7 -
atsuki-yamaguchi/gemma-2-9b-my-30K-mean
10B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-my-30K-1000-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-5000-mean
10B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-my-30K-50-rand
10B • Updated • 7 -
atsuki-yamaguchi/gemma-2-9b-si-30K-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-my-30K-500-rand
10B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-si-30K-1000-rand
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-mean
10B • Updated • 7 -
atsuki-yamaguchi/gemma-2-9b-my-30K-5000-rand
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-te-30K-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-500-mean
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-my-30K-500-align
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-my-30K-1000-mean
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-si-30K-5000-rand
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-500-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-5000-mean
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-50-align
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-500-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-500-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-1000-mean
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-my-30K-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-mean
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-5000-align
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-my-30K-50-mean
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-te-30K-50-mean
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-my-30K-50-align
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-1000-align
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-rand
10B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-te-30K-500-rand
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-te-30K-50-rand
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-my-30K-500-mean
10B • Updated • 6 -
atsuki-yamaguchi/gemma-2-9b-te-30K-1000-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-lapt
Updated -
atsuki-yamaguchi/gemma-2-9b-te-30K-50-align
10B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-lapt
Updated -
atsuki-yamaguchi/gemma-2-9b-my-30K-lapt
Updated -
atsuki-yamaguchi/gemma-2-9b-si-30K-align-merge
9B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-my-30K-align-merge
9B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-te-30K-align-merge
9B • Updated • 3 -
atsuki-yamaguchi/gemma-2-9b-te-30K-vr-focus
9B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-vr-random
9B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-te-30K-vr-random
9B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-my-30K-vr-mean
9B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-si-30K-vr-mean
9B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-te-30K-vr-mean
9B • Updated • 5 -
atsuki-yamaguchi/gemma-2-9b-my-30K-vr-random
9B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-my-30K-vr-focus
9B • Updated • 4 -
atsuki-yamaguchi/gemma-2-9b-si-30K-vr-focus
9B • Updated • 2