-
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Paper • 2409.10516 • Published • 41 -
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
Paper • 2409.11242 • Published • 6 -
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
Paper • 2409.11136 • Published • 22 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 13
Tongyao PRO
tyzhu
AI & ML interests
Natural Language Processing
Organizations
None yet
Collections
1
models
216
tyzhu/tiny_LLaMA_1b_32k_dm2_cc_32k_iter-100000-ckpt-step-100000_hf
Updated
•
13
tyzhu/tiny_LLaMA_1b_32k_cc_32k_iter-100000-ckpt-step-100000_hf
Updated
•
12
tyzhu/pystack_clean
Updated
tyzhu/llama3.2_3b_8k_intramask_cc_8k_iter-400000-ckpt-step-100000_hf
Updated
•
840
tyzhu/tiny_LLaMA_120M_8k_proweb_dec2
Updated
tyzhu/cc_small_valid
Updated
tyzhu/tiny_LLaMA_3b_8k_cc_8k
Updated
tyzhu/tiny_LLaMA_3b_8k_dm8_cc_8k
Updated
tyzhu/tiny_LLaMA_1b_16k_intramask_cc_16k_iter-480000-ckpt-step-60000_hf
Updated
•
11
tyzhu/tiny_LLaMA_1b_16k_intramask_cc_16k_iter-320000-ckpt-step-40000_hf
Updated
•
11
datasets
812
tyzhu/the-stack-py
Viewer
•
Updated
•
16.3M
tyzhu/pystack_clean
Viewer
•
Updated
•
9.44M
•
37
tyzhu/id_cc_pool
Viewer
•
Updated
•
72.5M
•
7
tyzhu/proweb
Viewer
•
Updated
•
46.3M
•
239
tyzhu/cmmlu_filtered
Updated
•
29
tyzhu/lmind_nq_train6000_eval6489_v1_docidx_v3
Viewer
•
Updated
•
76.7k
•
30
tyzhu/flan_max_300_added
Viewer
•
Updated
•
1.46M
•
34
tyzhu/lmind_nq_train6000_eval6489_v1_doc_qa_v3
Viewer
•
Updated
•
82.7k
•
28
tyzhu/lmind_nq_train6000_eval6489_v1_recite_qa_v3
Viewer
•
Updated
•
82.7k
•
32
tyzhu/lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3
Viewer
•
Updated
•
71.8k
•
26