·
AI & ML interests
None yet
Organizations
morizon/llm-jp-3-13b-instruct2-grpo-MATH-lighteval_step1000
Text Generation
• 14B • Updated • 1
morizon/llm-jp-3-13b-instruct2-grpo-0215_lora
Updated
morizon/llm-jp-3-13b-instruct2-grpo_0215
Text Generation
• 14B • Updated • 2
morizon/llm-jp-3-13b-instruct2-grpo-0219_lora
Updated
morizon/llm-jp-3-13b-instruct2-grpo-0219
Text Generation
• 14B • Updated • 1
morizon/qwen2.5-3b-instruct-unsloth-grpo_rev1
Text Generation
• 3B • Updated • 2
morizon/qwen2.5-3b-instruct-unsloth-grpo
Text Generation
• 3B • Updated • 1
morizon/llm-jp-3-13b_mix_50000_1216
Updated
morizon/llm-jp-3-13b_mix_30000_1209
Text Generation
• Updated morizon/llm-jp-3-13b_packing_rev2_1215
Updated
morizon/llm-jp-3-13b_mix_40000_1215
Updated
morizon/llm-jp-3-13b_packing_1215
Updated
morizon/llm-jp-3-3b_mix_20000_epoch2_1213
Updated
morizon/llm-jp-3-13b-unsloth_13b_mix._lora
Updated
morizon/llm-jp-3-13b_mix_100000_5e-5_add_epo
Updated
morizon/llm-jp-3-13b_mix_more_1211
Updated
morizon/llm-jp-3-13b_mix_30000_DPO
Updated
morizon/llm-jp-finetune3_peft_ichi_4bit_1208
Text Generation
• 2B • Updated • 1
morizon/llm-jp-finetune3_peft_merge_1207
Text Generation
• 14B • Updated morizon/llm-jp-finetune3_peft_merge
Text Generation
• 14B • Updated • 4
morizon/llm-jp-finetune-3_aya-DPO
Text Generation
• 14B • Updated • 1
morizon/llm-jp-finetune3_peft
Text Generation
• 14B • Updated • 1
morizon/llm-jp-3-13b-finetune-3_1
Text Generation
• 14B • Updated • 1
morizon/dpo_idefics_rlaif-v-50
Updated
morizon/idefics2-8b-dpo-rlaif-v
morizon/llava-jp_norprompt
Text Generation
• 0.5B • Updated • 4
morizon/dpo_visual_llavajp_refmodel
Text Generation
• 0.5B • Updated • 2