VincentN
vince62s
AI & ML interests
None yet
Recent Activity
new activity
5 days ago
utter-project/EuroLLM-9B-Instruct:Training data
new activity
15 days ago
HuggingFaceTB/smollm-corpus:Going multilingual
new activity
17 days ago
HuggingFaceFW/fineweb-edu:Most of the data is duplicated?
Organizations
vince62s's activity
Training data
7
#2 opened 4 months ago
by
BramVanroy

Going multilingual
#16 opened 15 days ago
by
vince62s

Most of the data is duplicated?
8
#7 opened 10 months ago
by
underspirit
bigger model
1
#7 opened about 1 month ago
by
vince62s

When it comes to maths, the model does not generate correct Latex tags which triggers awful outputs.
#6 opened 3 months ago
by
vince62s

missing special_tokens_map.json file
#2 opened 3 months ago
by
vince62s

Adding `safetensors` variant of this model
#1 opened 4 months ago
by
SFconvertbot

Text Clusters
1
#55 opened 4 months ago
by
vince62s

Results discussion
4
#6 opened 6 months ago
by
vince62s

Clarification on the way the tokenizer should be used
3
#6 opened 6 months ago
by
vince62s

Quality Estimation
4
#1 opened 6 months ago
by
ymoslem

Dataset for pretraining ?
1
#2 opened 7 months ago
by
vince62s

Question on the usage of TowerBlocks to train this model
1
#3 opened 7 months ago
by
vince62s

Bug with the HF Tokenizer
1
#7 opened 7 months ago
by
vince62s

IndexError: index out of range in self
4
#2 opened 10 months ago
by
ljhwild
Will there be a XXL version released in the future ?
1
#3 opened 9 months ago
by
zszsz10
Half precision
1
#1 opened 10 months ago
by
ljhwild
Can we run this in FP16 instead of FP32 ?
7
#3 opened about 1 year ago
by
vince62s

TruthfulQA score look odd, no ?
3
#3 opened about 1 year ago
by
vince62s

torch.cuda.OutOfMemoryError
7
#26 opened about 1 year ago
by
shiwanglai