Archangel is a suite of human feedback-aligned LLMs, released as part of the Human-Aware Loss Functions (HALOs) project by Ethayarajh et al. (2024).
ContextualAI
company
Verified
AI & ML interests
Enterprise-grade retrieval augmented language models
models
81
ContextualAI/tiny-random-MistralForCausalLM
Text Generation
•
Updated
•
4.26k
ContextualAI/zephyr_sft_dpo
Text Generation
•
Updated
•
2
ContextualAI/zephyr_sft_kto_unary
Text Generation
•
Updated
•
2
ContextualAI/zephyr_sft_kto
Text Generation
•
Updated
•
6
•
1
ContextualAI/Contextual_KTO_Mistral_PairRM
Text Generation
•
Updated
•
107
•
30
ContextualAI/archangel_kto_pythia6-9b
Text Generation
•
Updated
•
14
ContextualAI/archangel_kto_pythia2-8b
Text Generation
•
Updated
•
17
ContextualAI/archangel_kto_pythia1-4b
Text Generation
•
Updated
•
17
ContextualAI/archangel_ppo_pythia2-8b
Text Generation
•
Updated
•
20
ContextualAI/archangel_ppo_pythia1-4b
Text Generation
•
Updated
•
13
datasets
14
ContextualAI/ultrafeedback_clair_32k
Viewer
•
Updated
•
29.1k
•
60
•
4
ContextualAI/ultrafeedback_rlaif-offpolicy_32k
Viewer
•
Updated
•
29.1k
•
45
•
1
ContextualAI/ultrafeedback_stronger-preferred_32k
Viewer
•
Updated
•
29.1k
•
43
•
1
ContextualAI/ultrafeedback_rlaif_32k
Viewer
•
Updated
•
31.8k
•
45
•
1
ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized
Viewer
•
Updated
•
60.9k
•
41
ContextualAI/ultrabin_clean_max_chosen_rand_rejected_rationalized
Viewer
•
Updated
•
60.9k
•
38
ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized_helpfulness
Viewer
•
Updated
•
60.9k
•
47
ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized_truthfulness
Viewer
•
Updated
•
60.9k
•
45
ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized_honesty
Viewer
•
Updated
•
60.9k
•
38
ContextualAI/ultrabin_clean_max_chosen_min_rejected_rationalized_instruction_following
Viewer
•
Updated
•
60.9k
•
42
•
3