Stéphane du Hamel
stduhpf
AI & ML interests
None yet
Recent Activity
new activity
5 days ago
stduhpf/google-gemma-3-12b-it-qat-q4_0-gguf-small:Upload gemma-3-12b-it-q4_0_s.gguf
new activity
5 days ago
stduhpf/google-gemma-3-12b-it-qat-q4_0-gguf-small:Update?
new activity
6 days ago
google/gemma-3-12b-it-qat-q4_0-gguf:Token issue? <start_of_turn> split into multiple tokens
Organizations
None yet
stduhpf's activity
Upload gemma-3-12b-it-q4_0_s.gguf
1
#5 opened 5 days ago
by
Dampfinchen
Update?
1
1
#4 opened 5 days ago
by
CHNtentes
Token issue? <start_of_turn> split into multiple tokens
4
#3 opened 12 days ago
by
mw55a
Token issue
1
2
#3 opened 6 days ago
by
tdh111
error with ollama
3
#2 opened 8 days ago
by
eramax

Checksum doesn't match the file
15
#1 opened 9 days ago
by
dsent-zen
This model breaks apart after a few tokens when the context gets long
2
4
#1 opened 9 days ago
by
stduhpf
Why did you cut off the vision encoder of the model?
2
#1 opened 10 days ago
by
PavelSaranskiy
why is the size bigger than regular Q4_0 quants ?
2
4
#1 opened 12 days ago
by
lefromage
Broken old models
5
#2 opened 14 days ago
by
DasaNeon
Invalid tokenizer regex?
1
5
#1 opened 16 days ago
by
stduhpf
What is guidance-distilled?
1
#17 opened 8 months ago
by
YangHu
Any plans on doing a "Fill" version of it?
1
#1 opened 4 months ago
by
stduhpf
French voice (FF Alpha) has more of a Quebec French accent than a French French accent
4
#4 opened 3 months ago
by
stduhpf
Possible to work with 8GB VRAM and 16GB RAM?
4
#7 opened 6 months ago
by
krigeta
Is there a Lora version of this model?
4
#10 opened 6 months ago
by
Vigilence
Running in Colab
1
#1 opened 6 months ago
by
Mohamed-Ayman
Confused about the need for CFG
2
#7 opened 7 months ago
by
stduhpf
how many languages supported?
2
#16 opened 7 months ago
by
xingwang1234
I get the exact same results as clip-L
2
#2 opened 7 months ago
by
stduhpf