kumapo/qwen3-0.6b-sft-lora-rank256-1phase-assistant-only-loss
Text Generation • 0.6B • Updated
kumapo
kumapo
AI & ML interests
None yet
Recent Activity
updated a model about 2 hours ago
kumapo/qwen3-0.6b-sft-lora-rank256-1phase-assistant-only-loss published a model about 2 hours ago
kumapo/qwen3-0.6b-sft-lora-rank256-1phase-assistant-only-loss updated a model about 2 hours ago
kumapo/qwen3-0.6b-sft-lora-rank128-1phase-assistant-only-lossOrganizations
kumapo/qwen3-0.6b-sft-lora-rank128-1phase-assistant-only-loss
Text Generation • 0.6B • Updated
kumapo/qwen3-0.6b-sft-lora-rank512-1phase-assistant-only-loss
Text Generation • 0.6B • Updated
kumapo/qwen3-0.6b-sft-lora-rank2048-1phase-assistant-only-loss
Text Generation • 0.6B • Updated
kumapo/qwen3-0.6b-sft-lora-rank2048-2phase-assisistant-only-loss
Text Generation • 0.6B • Updated • 2
kumapo/qwen3-0.6b-sft-lora-rank2048
Text Generation • 0.6B • Updated • 3
kumapo/qwen3-0.6b-sft-lora-rank2048-2phase
Text Generation • 0.6B • Updated • 1
kumapo/lfm2-350m-sft-lora-rank2048-2phase
Text Generation • 0.4B • Updated • 3
kumapo/lfm2-350m-sft-lora-rank2048
Text Generation • 0.4B • Updated • 4
kumapo/modernbert-ja-130m-jsquad
Question Answering • 0.1B • Updated • 3
kumapo/llm-jp-modernbert-base-jsquad
Question Answering • 0.2B • Updated • 5 • 1
kumapo/modernbert-ja-310m-jsquad
Question Answering • 0.3B • Updated • 4 • 1
kumapo/modernbert-ja-310m-sft
Text Classification • 0.3B • Updated • 3
kumapo/Phi-4-multimodal-instruct
Automatic Speech Recognition • 6B • Updated • 4
kumapo/qwen3-4b-sft-lora
4B • Updated • 4
kumapo/qwen3_235b_a22b_thinking_textbookreasoning_ugphysics_aops_mini
235B • Updated • 2
kumapo/qwen3_235b_a22b_thinking_tbrminifiltered01_ugpfiltered01_olymomniliveumathreasoning
235B • Updated • 2
kumapo/qwen3_235b_a22b_thinking_tbrminifiltered01nomath_olymomniliveumathreasoning
235B • Updated • 1
kumapo/qwen3_235b_a22b_thinking_tbrnomathphysics_olymomniiisliveumathreasoning_ugphysics
235B • Updated • 1
kumapo/qwen3_235b_a22b_thinking_tbrnomath_olymliveumathreasoning
235B • Updated • 1
kumapo/qwen3_235b_a22b_thinking_tbrbalancedminifiltered01_ugpfiltered01_olymomniliveumathreasoning
235B • Updated • 1
kumapo/qwen3_235b_a22b_thinking_tbrnomath_olymomni2liveumathreasoning
235B • Updated • 1
kumapo/modernbert-ja-130m-sft
Text Classification • 0.1B • Updated • 2
kumapo/Qwen3-32B-omr-genselect-100k-peft
33B • Updated • 1
kumapo/llm-jp-3-1.8b-jaster-dev-2634-ichikara-003-001-1
Text Generation • 2B • Updated • 5
kumapo/llm-jp-3-1.8b-ichikara-003-001-1-jaster-dev-first100
Text Generation • 2B • Updated • 4
kumapo/llm-jp-3-1.8b-jaster-dev-first100
Text Generation • 2B • Updated • 6
kumapo/qwen3-4b-sft
Text Generation • 4B • Updated • 1
kumapo/swin-gpt2-ja-image-captioning
Image-Text-to-Text • 0.6B • Updated • 4
kumapo/qwen3-14b-reasoning-conversational
Text Generation • 15B • Updated • 3