Gustavo de Rosa
gugarosa
AI & ML interests
None yet
Recent Activity
authored
a paper
12 days ago
Phi-4 Technical Report
upvoted
a
paper
12 days ago
Phi-4 Technical Report
Organizations
gugarosa's activity
Add attention_bias to make TGI work
1
#64 opened 7 months ago
by
philschmid
Add attention_bias to make TGI work
1
#68 opened 7 months ago
by
philschmid
Upload 3 files
#1 opened 7 months ago
by
bapatra
Upload 3 files
#1 opened 7 months ago
by
bapatra
error in tokenizer
1
#5 opened 8 months ago
by
Algaliarept
Upload 25 files
#59 opened 8 months ago
by
jf8441
Fine-tuning is not improving the domain knowledge? it is very complicated, could you help?
5
#50 opened 8 months ago
by
aaditya
Model can't stop from explaining itself
14
#53 opened 8 months ago
by
fedeparra
Pipeline tokenizer does not get initialized when loading from string
1
#50 opened 8 months ago
by
connorboyle
model destroyed by deleting tokens?
1
#52 opened 8 months ago
by
NickyNicky
Phi-3 instruct model continuously repeating the answer
2
#55 opened 8 months ago
by
bitmman-nch
Get target_modules
1
#56 opened 8 months ago
by
danny3
System prompts ignored in chat completions
20
#51 opened 8 months ago
by
joshuaturner
Phi-3 support for GPU training with MPS on Mac
1
#52 opened 8 months ago
by
chaishirin
Leaking Training Data
3
#40 opened 8 months ago
by
qunitindk
fix(tokenizer_config): Adjusts `rstrip` of special tokens.
#54 opened 8 months ago
by
gugarosa
fix(tokenizer_config): Adjusts `rstrip` of special tokens.
#53 opened 8 months ago
by
gugarosa
Instruct model needs work
8
#35 opened 8 months ago
by
Nafnlaus
gguf
30
#24 opened 8 months ago
by
LaferriereJC
Very good model for its size (7b and 14b are gonna be amazing)
4
#43 opened 8 months ago
by
rombodawg