TrandeLik/czech_gpt_vocab_64_embed384_muon120k_no_tying
Updated
Dmitrii Feoktistov
TrandeLik
AI & ML interests
Graph ML, Optimization, Efficiency
Recent Activity
upvoted a paper about 2 months ago
Reasoning Shift: How Context Silently Shortens LLM Reasoning updated a model 7 months ago
TrandeLik/czech_gpt_vocab_64_embed384_muon120k_no_tying published a model 7 months ago
TrandeLik/czech_gpt_vocab_64_embed384_muon120k_no_tyingOrganizations
None yet
models 21
TrandeLik/czech_gpt_vocab_64_embed384_muon100k
Updated • 1
TrandeLik/czech_gpt_vocab_64_embed64_layers4_muon50k
Updated • 1
TrandeLik/czech_gpt_vocab_64_embed64_muon20k
Updated • 5
TrandeLik/czech_gpt_vocab_64_embed384_adamw50k
Updated
TrandeLik/czech_gpt_vocab_64_embed384_muon50k
Updated • 1
TrandeLik/czech_gpt_vocab_64_embed384_muon20k
Updated • 1
TrandeLik/czech_gpt_vocab_64_embed768_muon20k
Updated
TrandeLik/czech_gpt_vocab_64_embed768_muon10k
Updated
TrandeLik/aug_rt-qwen-qwen2.5-7b-instruct-trl-lib-tldr-preference-n_epochs1-bs16-rsreduced_weight
Updated