xianfeng's picture

xianfeng

xianf

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 days ago

Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding

upvoted a paper 11 days ago

Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling

new activity about 1 month ago

nex-agi/agent-sft:Is it normal that there is no thinking process in the content?

View all activity

Organizations

None yet

New activity in nex-agi/agent-sft about 1 month ago

Is it normal that there is no thinking process in the content?

#4 opened about 1 month ago by

New activity in openai/gpt-oss-20b 5 months ago

How to turn off thinking mode

#86 opened 5 months ago by

New activity in BAAI/CCI4.0-ZH-HQ-Classifiers 6 months ago

What does the pred score predicted by the model represent?

#3 opened 6 months ago by

New activity in bigcode/the-stack-v2-train-smol-ids about 1 year ago

script to download the data

#7 opened about 1 year ago by

New activity in Qwen/Qwen2-1.5B over 1 year ago

lm_eval results is weird

#2 opened over 1 year ago by

New activity in zai-org/glm-4-9b over 1 year ago

使用 lm_eval 测试时报错了

#1 opened over 1 year ago by

New activity in Qwen/Qwen-1_8B over 1 year ago

QWEN-1.8B finetune 之后输出全是重复的 token

#1 opened about 2 years ago by

New activity in allenai/dolma over 1 year ago

Please provide a list of file hashes in order to check integrity of downloads

#24 opened almost 2 years ago by deleted

New activity in edugp/kenlm over 2 years ago

Add korean kenLMs

#6 opened over 2 years ago by

New activity in bigscience/mt0-base almost 3 years ago

Why the vocab_size of tokenizer is different from model?

#2 opened almost 3 years ago by

New activity in SirNeural/flan_v2 almost 3 years ago

Is the missing data repaired?

#1 opened almost 3 years ago by