From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
•
55
ContextualAI
company
Verified
AI & ML interests
Enterprise-grade retrieval augmented language models
Recent Activity
Articles
Models & Datasets for LMunit evaluation
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/archangel_sft_llama7b
Text Generation • 7B • Updated • 5 • 1 -
ContextualAI/archangel_kto_llama30b
Text Generation • 33B • Updated • 5 • 2 -
ContextualAI/archangel_sft-kto_llama13b
Text Generation • 13B • Updated • 1.45k • 3 -
ContextualAI/archangel_sft-kto_llama30b
Text Generation • 33B • Updated • 11 • 2
Data and Models for the paper "Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment"
-
ContextualAI/ultrafeedback_clair_32k
Viewer • Updated • 29.1k • 31 • 4 -
ContextualAI/ultrafeedback_rlaif_32k
Viewer • Updated • 31.8k • 17 • 1 -
ContextualAI/ultrafeedback_rlaif-offpolicy_32k
Viewer • Updated • 29.1k • 12 • 1 -
ContextualAI/ultrafeedback_stronger-preferred_32k
Viewer • Updated • 29.1k • 8 • 1
Models & Datasets for LMunit evaluation
Text-to-SQL models
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/archangel_sft_llama7b
Text Generation • 7B • Updated • 5 • 1 -
ContextualAI/archangel_kto_llama30b
Text Generation • 33B • Updated • 5 • 2 -
ContextualAI/archangel_sft-kto_llama13b
Text Generation • 13B • Updated • 1.45k • 3 -
ContextualAI/archangel_sft-kto_llama30b
Text Generation • 33B • Updated • 11 • 2
Aligned models based on Zephyr-SFT from Table 2 and 3 in the KTO paper by Ethayarajh et al. (2024) (https://arxiv.org/pdf/2402.01306).
Data and Models for the paper "Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment"
-
ContextualAI/ultrafeedback_clair_32k
Viewer • Updated • 29.1k • 31 • 4 -
ContextualAI/ultrafeedback_rlaif_32k
Viewer • Updated • 31.8k • 17 • 1 -
ContextualAI/ultrafeedback_rlaif-offpolicy_32k
Viewer • Updated • 29.1k • 12 • 1 -
ContextualAI/ultrafeedback_stronger-preferred_32k
Viewer • Updated • 29.1k • 8 • 1