Thanh Ng
thanhnew2001
AI & ML interests
None yet
Organizations
thanhnew2001's activity
Weird results with ct2fast-Llama-2-7b versus the unquantized Llama-2-7b
#3 opened over 1 year ago
by
thanhnew2001
Is is possible to run the model in 2 gpu?
1
#5 opened over 1 year ago
by
thanhnew2001
GPU memory usage/requirement?
5
#2 opened over 1 year ago
by
Bilibili
![](https://cdn-avatars.huggingface.co/v1/production/uploads/61c2e44c39245e7bf62def6f/WnppxWX6Rv8cy9mBb00k7.png)
Smaller but better? Why quantization improves the performance?
3
#3 opened over 1 year ago
by
Bilibili
![](https://cdn-avatars.huggingface.co/v1/production/uploads/61c2e44c39245e7bf62def6f/WnppxWX6Rv8cy9mBb00k7.png)
How to speed up inferring?
7
#21 opened almost 2 years ago
by
merlinarer
Create science.jsonl
#1 opened over 1 year ago
by
thanhnew2001
Not able to run hello world example, bigcode/starcoder is not a valid model identifier
14
#11 opened almost 2 years ago
by
rameshn