Zhang Ruichong's picture

Zhang Ruichong

ZhangRC

·

https://www.zhihu.com/people/triangjyeddriung

Triang-jyed-driung

AI & ML interests

Mathematics (Real analysis, functional analysis, commutative algebra, etc)

Recent Activity

new activity 4 days ago

jonathan-roberts1/zerobench:Problem 90

liked a dataset 4 days ago

jonathan-roberts1/zerobench

updated a model 5 days ago

fla-hub/rwkv7-2.9B-world

View all activity

Organizations

ZhangRC's activity

New activity in jonathan-roberts1/zerobench 4 days ago

Problem 90

#3 opened 4 days ago by

New activity in fla-hub/rwkv7-2.9B-world 5 days ago

bfloat16 safetensors as required by Peng Bo

#1 opened 5 days ago by

New activity in edinburgh-dawg/mmlu-redux-2.0 10 days ago

Report: no correct answer

#2 opened 10 days ago by

New activity in fla-hub/rwkv7-1.5B-world 18 days ago

remove max_new_tokens parameter

#3 opened 18 days ago by

New activity in fla-hub/rwkv7-1.5B-world 23 days ago

missing automap

#1 opened 24 days ago by

New activity in fla-hub/rwkv7-168M-pile 29 days ago

safetensors metadata is None

#1 opened 30 days ago by

New activity in THUDM/chatglm3-6b 3 months ago

Inference error in transformers 4.42.1

#58 opened 8 months ago by

New activity in HuggingFaceFW/blogpost-fine-tasks 4 months ago

XNLI in Chinese is basically corrupted - that's why you got unreliable results

#1 opened 4 months ago by

commented a paper 7 months ago

GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression

Paper • 2407.12077 • Published Jul 16, 2024 • 55 •

commented a paper 10 months ago

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Paper • 2403.03853 • Published Mar 6, 2024 • 63 •

New activity in BlinkDL/rwkv-6-world 11 months ago

Will rwkv6-pile be released in the future？

#1 opened 11 months ago by

New activity in Jellyfish042/Bubble-Factory-V0 12 months ago

Add these datasets

#2 opened 12 months ago by

New activity in a686d380/rwkv-5-h-world about 1 year ago

🚩 Report: Ethical issue(s)

#1 opened about 1 year ago by

New activity in xiaol/rwkv-7B-world-novel-128k over 1 year ago

你好，你能嘗試在保留模型原本能力的同時，訓練模型能生成化學分子與分析嗎？

#1 opened over 1 year ago by

New activity in BlinkDL/rwkv-5-world over 1 year ago

Which languages are used in the dataset?

#1 opened over 1 year ago by

New activity in BlinkDL/rwkv-4-world over 1 year ago

How to fine-tune this model?

#2 opened over 1 year ago by

Unable to load tokenizer

#1 opened over 1 year ago by

New activity in BlinkDL/rwkv-4-raven almost 2 years ago

Any plan for bigger model such as 30B?

#10 opened almost 2 years ago by