dpo-qwen3-4b-loraby meti94π₯οΈ GPUFP16~10 GB4B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
NeoHorse-1-9Bby liskasYRπ₯οΈ GPUFP16~22 GB9B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0reasoningconversationallicense:apache-2.0View on Hugging Face
augmented-83bbf8f015eeb6ecby gradients-io-tournamentsπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
MiniCPM5-2B-Baseby liskasYRπ₯οΈ GPUFP16~5 GB2B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationaldataset:openbmb/ultra-finewebdataset:openbmb/ultrax-previewdataset:openbmb/ultra-fineweb-l3View on Hugging Face
tydiqa_en_and_telugu_3000_percentage_1_120_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_telugu_3000_percentage_1_42_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_telugu_3000_percentage_1_40_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_bengali_3000_percentage_1_120_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_bengali_3000_percentage_1_42_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_bengali_3000_percentage_1_40_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_swahili_3000_percentage_1_120_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_swahili_3000_percentage_1_42_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
tydiqa_en_and_swahili_3000_percentage_1_40_LoRAby WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
DeltaP2S-Llama2-13B-P2S-curio7B-ptbr-S13-a025by g-assismoraesπ₯οΈ GPUFP16~32 GB13B paramsβ¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_hi_5000_percentage_1_120_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_hi_5000_percentage_1_42_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_hi_5000_percentage_1_40_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_sw_5000_percentage_1_120_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_sw_5000_percentage_1_42_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_sw_5000_percentage_1_40_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_ur_5000_percentage_1_42_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_ur_5000_percentage_1_120_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
xnli_en_and_ur_5000_percentage_1_40_PiSSA_rank_4by WijewardhanaNTπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageView on Hugging Face
qwen306b-rl-exp2by DQN-Labsπ₯οΈ GPUFP16~735 GB306B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationallicense:apache-2.0View on Hugging Face