-
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Paper • 2402.12030 • Published -
mistralai/Mistral-7B-Instruct-v0.2
Text Generation • Updated • 2.3M • 2.13k -
meta-llama/Llama-2-7b-chat-hf
Text Generation • Updated • 1.49M • 3.47k -
EleutherAI/pythia-160m-deduped
Text Generation • Updated • 94.9k • 2
Nicolas-BZRD
Nicolas-BZRD
AI & ML interests
PhD Student | NLP - LLMs - Adaptation real-world problem
Optimization
Organizations
Collections
1
models
92
Nicolas-BZRD/mt0-base_dialogsum_Mistral-7B-Instruct-v0.2_uld_loss
Text2Text Generation
•
Updated
•
75
Nicolas-BZRD/mt0-base_dialogsum_Mistral-7B-Instruct-v0.2_text_teacher
Text2Text Generation
•
Updated
•
134
Nicolas-BZRD/mt0-base_pubmed_qa_Llama-2-7b-chat-hf_uld_loss
Text2Text Generation
•
Updated
•
59
Nicolas-BZRD/mt0-base_pubmed_qa_Llama-2-7b-chat-hf_text_teacher
Text2Text Generation
•
Updated
•
46
Nicolas-BZRD/mt0-base_qed_Llama-2-7b-chat-hf_uld_loss
Text2Text Generation
•
Updated
•
16
Nicolas-BZRD/mt0-base_qed_Llama-2-7b-chat-hf_text_teacher
Text2Text Generation
•
Updated
•
2
Nicolas-BZRD/mt0-base_dialogsum_Llama-2-7b-chat-hf_uld_loss
Text2Text Generation
•
Updated
•
1
Nicolas-BZRD/mt0-base_dialogsum_Llama-2-7b-chat-hf_text_teacher
Text2Text Generation
•
Updated
•
1
Nicolas-BZRD/pythia-160m-deduped_FairytaleQA_Llama-2-7b-chat-hf_uld_loss
Text Generation
•
Updated
•
3
Nicolas-BZRD/pythia-160m-deduped_FairytaleQA_Llama-2-7b-chat-hf_text_teacher
Text Generation
•
Updated
•
2
datasets
30
Nicolas-BZRD/uld_loss_Mistral-7B-Instruct-v0.2-pubmed_qa_50k
Viewer
•
Updated
•
1
Nicolas-BZRD/uld_loss_Llama-2-7b-chat-hf-squad
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Mistral-7B-Instruct-v0.2-squad
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Llama-2-7b-chat-hf-dialogsum
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Mistral-7B-Instruct-v0.2-qed
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Mistral-7B-Instruct-v0.2-FairytaleQA
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Llama-2-7b-chat-hf-FairytaleQA
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Mistral-7B-Instruct-v0.2-dialogsum
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Llama-2-7b-chat-hf-qed
Viewer
•
Updated
Nicolas-BZRD/uld_loss_Llama-2-7b-chat-hf-pubmed_qa_50k
Viewer
•
Updated
•
10