Stéphane du Hamel
stduhpf
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
stabilityai/stable-codec-speech-16k
liked
a model
10 days ago
mistralai/Mistral-Nemo-Instruct-2407
new activity
11 days ago
Freepik/flux.1-lite-8B:Any plans on doing a "Fill" version of it?
Organizations
None yet
stduhpf's activity
Any plans on doing a "Fill" version of it?
1
#1 opened 12 days ago
by
stduhpf
French voice (FF Alpha) has more of a Quebec French accent than a French French accent
4
#4 opened 11 days ago
by
stduhpf
Upload mmproj-Qwen2-VL-2B-Instruct-f16.gguf
3
#1 opened 28 days ago
by
stduhpf
Sdcpp integration
2
#14 opened about 2 months ago
by
stduhpf
Possible to work with 8GB VRAM and 16GB RAM?
4
#7 opened 3 months ago
by
krigeta
Is there a Lora version of this model?
4
#10 opened 3 months ago
by
Vigilence
Running in Colab
1
#1 opened 3 months ago
by
Mohamed-Ayman
Confused about the need for CFG
2
#7 opened 3 months ago
by
stduhpf
how many languages supported?
2
#16 opened 4 months ago
by
xingwang1234
I get the exact same results as clip-L
2
#2 opened 4 months ago
by
stduhpf
missing pre-tokenizer?
2
#1 opened 8 months ago
by
stduhpf
Is IQ1_S broken? If so why list it here?
1
#9 opened 9 months ago
by
stduhpf
Was this model based of Mistral-7B-v0.2 from the start?
4
#72 opened 10 months ago
by
stduhpf
About q4_k and q5_k
1
#2 opened 10 months ago
by
stduhpf
Any plan of realeasing q2_k_s quants?
4
#1 opened 11 months ago
by
stduhpf
Seems very good as a draft model for speculative decoding!
1
#1 opened 12 months ago
by
stduhpf
Just curious about what to expect from this model.
2
#3 opened 12 months ago
by
stduhpf
Just curious about what to expect from this model.
2
#3 opened 12 months ago
by
stduhpf
Just curious about what to expect from this model.
2
#3 opened 12 months ago
by
stduhpf