Shane Tian
ShaneTian
AI & ML interests
None yet
Organizations
None yet
ShaneTian's activity
Optimization details
2
#16 opened 5 months ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)
About the compressed file size < 10MB
2
#7 opened 5 months ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)
`CpmTokenizer` is different from the original CPM-1 tokenizer in GitHub
3
#1 opened almost 2 years ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)
Not found `the-stack-v2-train-extras`
1
#5 opened 5 months ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)
Training loss or logs?
#15 opened 5 months ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)
ctx window & languages?
4
#1 opened 8 months ago
by
JosephusCheung
Why does Code-Llama-34B not support infilling mode, i.e. FIM
1
#18 opened 9 months ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)
Are there plans to include some models that use OctoPack to fine-tune, like OctoCoder, etc
2
#7 opened 12 months ago
by
ShaneTian
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660138927470-62e37ac7a0be7413eb879b0a.jpeg)