Tony W
tonyaw
AI & ML interests
None yet
Organizations
None yet
tonyaw's activity
It looks the model is in 8K context length. May I ask why context length of Llama3.1 is 128K
2
#153 opened 3 months ago
by
tonyaw
Incorrect vocab size?
8
#2 opened about 1 year ago
by
claudiuv
"vocab_size" is inconsistent with tokenizer.get_vocab()
1
#7 opened about 1 year ago
by
tonyaw
How to use PEFT+LoRA to fine-tune starchat-alpha
1
#17 opened over 1 year ago
by
tonyaw
Python library version recommendation
1
#3 opened over 1 year ago
by
tonyaw
KeyError: 'model.layers.0.self_attn.rotary_emb.cos_cached'
#9 opened over 1 year ago
by
tonyaw