alpha
alphaprime90
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
city96/Wan2.1-T2V-14B-gguf
new activity
2 days ago
city96/Wan2.1-T2V-14B-gguf:Can it run on CPU only?
liked
a model
25 days ago
mradermacher/Janus-Pro-7B-LM-GGUF
Organizations
None yet
alphaprime90's activity
Can it run on CPU only?
#5 opened 2 days ago
by
alphaprime90
Could you share the test result for each question?
3
#6 opened 10 months ago
by
alphaprime90
Could you talk about the changes you made to the model?
2
#2 opened 10 months ago
by
alphaprime90
OK llama 3 8b model is INSANE. Is almost as good as wizard 2 8x22b!
52
#5 opened 11 months ago
by
mirek190
Non-English language capabilities
6
#2 opened 11 months ago
by
oliviermills
mmproj files for smaller models mainly deepseek 1.3b and others.
1
#8 opened about 1 year ago
by
alphaprime90
How does it compare to phi-2 or other small models?
#1 opened about 1 year ago
by
alphaprime90
To the few who can run it, Post speeds, setup, results quality.
7
#1 opened about 1 year ago
by
alphaprime90
New quant 8bit method, how is it performing on your CPU? (share your token/s, CPU model and -- thread)
24
#2 opened almost 2 years ago
by
alphaprime90
Can someone share ggml 4bit version?
2
#2 opened almost 2 years ago
by
alphaprime90
What's the size of the data?
#5 opened almost 2 years ago
by
alphaprime90
Nice work. Very conversational, great formatting. Still hallucinates.
1
#1 opened almost 2 years ago
by
varch1tect
Fine-tuning the model
10
#1 opened almost 2 years ago
by
Muhammadreza