Tingchen Fu's picture

10 3 6

Tingchen Fu

TingchenFu

·

TingchenFu

AI & ML interests

None yet

Recent Activity

liked a model 9 days ago

Qwen/QwQ-32B

upvoted a paper about 2 months ago

Autonomy-of-Experts Models

upvoted a paper about 2 months ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

View all activity

Organizations

None yet

TingchenFu's activity

New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 8 months ago

tokenizer configuration

#9 opened 8 months ago by

New activity in meta-llama/Meta-Llama-3-8B 8 months ago

[READ IF YOU DO NOT HAVE ACCESS] Getting access to the model

#172 opened 10 months ago by

New activity in baichuan-inc/Baichuan2-7B-Base about 1 year ago

The performnan on humaneval.

#5 opened about 1 year ago by

New activity in baichuan-inc/Baichuan2-13B-Chat about 1 year ago

how to accelerate the inference speed

#22 opened over 1 year ago by

New activity in microsoft/bloom-deepspeed-inference-fp16 over 1 year ago

How to split tensors to x shards?

#1 opened almost 2 years ago by

New activity in microsoft/bloom-deepspeed-inference-int8 almost 2 years ago

Can I load these weights into a model using 8 gpus?

#2 opened over 2 years ago by

New activity in bigscience/bloom-560m-intermediate almost 2 years ago

There might be some thing wrong with the 500,000 and 600,000 step checkpoint

#2 opened almost 2 years ago by

New activity in tloen/alpaca-lora-7b almost 2 years ago

This works, but training does not work at all

#4 opened almost 2 years ago by

New activity in bigscience/bloomz-560m almost 2 years ago

In config.json we only have n_embed=1024 while BLOOM was trained with a sequence length of 2048.

#9 opened almost 2 years ago by

New activity in evaluate-metric/bleurt about 2 years ago

Checkpoint seems not be loaded

#8 opened over 2 years ago by