Shane Tian's picture

8 3 8

Shane Tian

ShaneTian

·

ShaneTian

AI & ML interests

None yet

Recent Activity

New activity 9 days ago

infly/OpenCoder-8B-Base

reacted to singhsidhukuldeep's post with 👍 about 2 months ago

Organizations

None yet

ShaneTian's activity

New activity in infly/OpenCoder-8B-Base 9 days ago

What is the FIM template for the base model?

#4 opened 10 days ago by

New activity in bigcode/starcoder2-15b 9 months ago

Optimization details

#16 opened 9 months ago by

New activity in bigcode/the-stack-v2 9 months ago

About the compressed file size < 10MB

#7 opened 9 months ago by

New activity in TsinghuaAI/CPM-Generate 9 months ago

`CpmTokenizer` is different from the original CPM-1 tokenizer in GitHub

#1 opened over 2 years ago by

New activity in bigcode/the-stack-v2-train-full-ids 9 months ago

Not found `the-stack-v2-train-extras`

#5 opened 9 months ago by

New activity in bigcode/starcoder2-15b 9 months ago

Training loss or logs?

#15 opened 9 months ago by

New activity in deepseek-ai/deepseek-llm-67b-chat 12 months ago

ctx window & languages?

#1 opened 12 months ago by

New activity in codellama/CodeLlama-34b-hf about 1 year ago

Why does Code-Llama-34B not support infilling mode, i.e. FIM

#18 opened about 1 year ago by

New activity in bigcode/bigcode-models-leaderboard over 1 year ago

Are there plans to include some models that use OctoPack to fine-tune, like OctoCoder, etc

#7 opened over 1 year ago by

New activity in TsinghuaAI/CPM-Generate over 2 years ago

`CpmTokenizer` is different from the original CPM-1 tokenizer in GitHub

#1 opened over 2 years ago by