FAR AI

non-profit

https://far.ai/

AlignmentResearch

Activity Feed Request to join this org

AI & ML interests

Frontier alignment research to ensure the safe development and deployment of advanced AI systems.

Recent Activity

skar0 published a model 7 days ago

AlignmentResearch/Llama-3.3-70B-Instruct-math-lora-reference

skar0 updated a model 8 days ago

AlignmentResearch/Llama-3.1-8B-Instruct-gsm8k-grpo

skar0 updated a model 8 days ago

AlignmentResearch/Llama-3.1-8B-Instruct-gsm8k-grpo

View all activity

AlignmentResearch 's models 3,827

AlignmentResearch/robust_llm_oskar-015c_clf_pm_pythia-12b_s-2_adv_tr_gcg_t-2

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015c_clf_pm_pythia-12b_s-0_adv_tr_gcg_t-0

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-6.9b_s-2_adv_tr_gcg_t-2

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-6.9b_s-1_adv_tr_gcg_t-1

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-6.9b_s-0_adv_tr_gcg_t-0

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-12b_s-2_adv_tr_gcg_t-2

Updated Nov 20, 2024

AlignmentResearch/robust_llm_test_model_push_to_hub_from_checkpoint

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-12b_s-1_adv_tr_gcg_t-1

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015b_clf_spam_pythia-12b_s-0_adv_tr_gcg_t-0

Updated Nov 20, 2024

AlignmentResearch/robust_llm_oskar-015a_imdb_pythia-6.9b_s-0_adv_tr_gcg_t-0

Updated Nov 19, 2024

AlignmentResearch/robust_llm_oskar-015a_imdb_pythia-12b_s-2_adv_tr_gcg_t-2

Updated Nov 19, 2024

AlignmentResearch/robust_llm_oskar-024a_clf_harmless_Qwen2.5-7B_s-2_adv_tr_gcg_t-2

Updated Nov 19, 2024

AlignmentResearch/robust_llm_Qwen2.5-7B_clf_spam_v-oskar-023b_s-1

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-7B_clf_spam_v-oskar-023b_s-0

Updated Nov 19, 2024

AlignmentResearch/robust_llm_Qwen2.5-7B_clf_spam_v-oskar-023b_s-2

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-7B_clf_harmless_v-oskar-023a_s-2

Updated Nov 19, 2024

AlignmentResearch/robust_llm_Qwen2.5-7B_clf_harmless_v-oskar-023a_s-1

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-7B_clf_harmless_v-oskar-023a_s-0

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_spam_v-oskar-022c_s-2

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_spam_v-oskar-022c_s-1

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_imdb_v-oskar-022d_s-1

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_imdb_v-oskar-022d_s-2

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_spam_v-oskar-022c_s-0

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_imdb_v-oskar-022d_s-0

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_helpful_v-oskar-022b_s-2

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_helpful_v-oskar-022b_s-1

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_harmless_v-oskar-022a_s-2

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_helpful_v-oskar-022b_s-0

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_harmless_v-oskar-022a_s-1

Updated Nov 19, 2024 • 1

AlignmentResearch/robust_llm_Qwen2.5-3B_clf_harmless_v-oskar-022a_s-0

Updated Nov 19, 2024 • 1