Jaron
JaronTHU
·
AI & ML interests
None yet
Recent Activity
new activity
12 days ago
internlm/internlm3-8b-instruct:Fast Tokenizer
new activity
26 days ago
internlm/internlm3-8b-instruct:Fast Tokenizer
upvoted
a
collection
2 months ago
Phi-3
Organizations
JaronTHU's activity
Fast Tokenizer
2
#17 opened 26 days ago
by
JaronTHU
Question about lm_head weights in Gemma-2-9b-it model
2
#34 opened 7 months ago
by
mjkmain
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6435a57b2d0ed796668d8a3f/fsOmfjqCS9TkI9NMjCFM2.png)
Fails to generate with `inputs_embeds`
2
#18 opened 8 months ago
by
JaronTHU
"It is strongly recommended to train Gemma2 models with the `eager` attention implementation "
2
#10 opened 8 months ago
by
JaronTHU
"It is strongly recommended to train Gemma2 models with the `eager` attention implementation "
2
#10 opened 8 months ago
by
JaronTHU