yoheikobashi/ptcg-qwen3-4b-dpo-loras
Updated
Yohei Kobashi
yoheikobashi
AI & ML interests
Development of a language model that generates humor.
Recent Activity
updated a model about 12 hours ago
yoheikobashi/ptcg-qwen3-4b-dpo-loras published a model about 12 hours ago
yoheikobashi/ptcg-qwen3-4b-dpo-loras updated a model about 12 hours ago
yoheikobashi/ptcg-qwen3-4b-cardfirst-v40Organizations
models 9
yoheikobashi/ptcg-qwen3-4b-cardfirst-v40
Text Generation • Updated • 8
yoheikobashi/ptcg-dusknoir-deberta-reranker
Reinforcement Learning • 0.2B • Updated • 7
yoheikobashi/SAEs-OLMo-2-0425-1B-dolma
Updated • 1
yoheikobashi/SAEs-LLM-jp-3-1.8B-dolma
Updated
yoheikobashi/fineweb-edu-10BT-suffix-array
Updated
yoheikobashi/fineweb_edu_10B_for_crypto-LLM
Updated
yoheikobashi/suffix_array_fineweb-edu-10BT-0.1
Updated
yoheikobashi/encrypted_tokenizers
Updated
datasets 6
yoheikobashi/dummy_karte
Viewer • Updated • 194 • 288 • 1
yoheikobashi/SAE_activations_modal_sentences
Viewer • Updated • 203k • 2k
yoheikobashi/fineweb_edu_10BT_scrabbing
Viewer • Updated • 3.65M • 61
yoheikobashi/fineweb_edu_masked_10BT
Viewer • Updated • 9.67M • 274
yoheikobashi/fineweb-edu-100BT-samples-not-in-10BT
Viewer • Updated • 876k • 934
yoheikobashi/fineweb_edu_10B_for_crypto-LLM
Viewer • Updated • 30.8M • 1.04k