Article
37
Kyle Richardson
yakazimir
AI & ML interests
NLP, ML
Recent Activity
authored a paper about 7 hours ago
Operads for compositional reasoning in LLMs authored a paper about 7 hours ago
From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models authored a paper about 7 hours ago
Operadic consistency: a label-free signal for compositional reasoning failures in LLMsOrganizations
models 10
yakazimir/simpo-exps_qwen05b
Text Generation • 0.5B • Updated • 29
yakazimir/smollm_1_7B_ultrachat_v2_pack_nocolat
Text Generation • 2B • Updated • 16
yakazimir/smollm_1_7B_ultrachat_v2_pack
Text Generation • 2B • Updated • 9
yakazimir/smollm_1_7B_ultrachat_v2_coll
Text Generation • 2B • Updated • 20
yakazimir/smollm_1_7B_ultrachat_v2
Text Generation • 2B • Updated • 10
yakazimir/llama_3_2_3B_tulu3
Text Generation • 3B • Updated • 10
yakazimir/smollm_1_7B_tulu3
Text Generation • 2B • Updated • 18
yakazimir/smollm_test
Text Generation • 2B • Updated • 16
yakazimir/smollm_1B_ultrachat
Text Generation • 2B • Updated • 8
yakazimir/simpo-exps
Text Generation • 8B • Updated • 25
datasets 14
yakazimir/on_policy_human_ai
Viewer • Updated • 92.5k • 81
yakazimir/preference_mixture
Viewer • Updated • 81.8k • 38
yakazimir/ultrafeedback_olmo1b_ref
Viewer • Updated • 62.5k • 45
yakazimir/mistral-instruct-ultrafeedback
Viewer • Updated • 62.7k • 19
yakazimir/ultrafeedback_binarized
Viewer • Updated • 63.1k • 15 • 1
yakazimir/llama3-ultrafeedback-armorm
Viewer • Updated • 61.8k • 35
yakazimir/preference_mix
Preview • Updated • 31
yakazimir/preference_alignment_ultra_cut
Viewer • Updated • 39.5k • 31
yakazimir/preference_tuning_hh_ultra
Viewer • Updated • 133k • 33 • 1
yakazimir/preference_alignment_total
Viewer • Updated • 153k • 23