-
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Paper • 2409.10516 • Published • 40 -
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
Paper • 2409.11242 • Published • 5 -
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
Paper • 2409.11136 • Published • 21 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 12
Tongyao PRO
tyzhu
AI & ML interests
Natural Language Processing
Organizations
None yet
Collections
1
models
211
tyzhu/llama3.2_3b_8k_intramask_cc_8k_iter-400000-ckpt-step-100000_hf
Updated
•
76
tyzhu/tiny_LLaMA_1b_16k_intramask_cc_16k_iter-480000-ckpt-step-60000_hf
Updated
•
6
tyzhu/tiny_LLaMA_1b_16k_intramask_cc_16k_iter-320000-ckpt-step-40000_hf
Updated
•
6
tyzhu/tiny_LLaMA_3b_8k_dm8_cc_8k
Updated
tyzhu/tiny_LLaMA_3b_8k_cc_merged_v2_8k
Updated
tyzhu/tiny_LLaMA_3b_2k_cc_merged_v2_2k
Updated
tyzhu/tiny_LLaMA_3b_2k_intramask_cc_2k
Updated
tyzhu/tiny_LLaMA_3b_8k_cc_8k
Updated
tyzhu/tiny_LLaMA_3b_2k_cc_2k
Updated
tyzhu/tiny_LLaMA_1b_4k_intramask_eng_thai_mixed_4k_iter-160000-ckpt-step-20000_hf
Updated
•
2
datasets
810
tyzhu/id_cc_pool
Viewer
•
Updated
•
72.5M
tyzhu/proweb
Viewer
•
Updated
•
46.3M
•
146
tyzhu/cmmlu_filtered
Updated
•
31
tyzhu/lmind_nq_train6000_eval6489_v1_docidx_v3
Viewer
•
Updated
•
76.7k
•
32
tyzhu/flan_max_300_added
Viewer
•
Updated
•
1.46M
•
34
tyzhu/lmind_nq_train6000_eval6489_v1_doc_qa_v3
Viewer
•
Updated
•
82.7k
•
31
tyzhu/lmind_nq_train6000_eval6489_v1_recite_qa_v3
Viewer
•
Updated
•
82.7k
•
36
tyzhu/lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3
Viewer
•
Updated
•
71.8k
•
29
tyzhu/lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3_v3
Viewer
•
Updated
•
71.8k
•
28
tyzhu/lmind_nq_train6000_eval6489_v1_reciteonly_qa_v2
Viewer
•
Updated
•
71.8k
•
39