Alex Cardo
alexcardo
AI & ML interests
None yet
Organizations
None yet
alexcardo's activity
LM Studio Says "unknown model architecture"
5
#1 opened 4 days ago
by
alexcardo
ValueError: Model type gemma2 not supported
#2 opened 24 days ago
by
alexcardo
General knowledge issue
#1 opened 24 days ago
by
alexcardo
My experience
9
#9 opened about 1 month ago
by
SaisExperiments
surprising - that model is incredible for it's size.
20
#2 opened about 2 months ago
by
mirek190
GGML_ASSERT: src/llama.cpp:11811: false
2
#1 opened about 2 months ago
by
alexcardo
Can you provide the correct prompt template to use this model as a translator
3
#6 opened 4 months ago
by
alexcardo
Strange behavior
1
#2 opened 4 months ago
by
alexcardo
Another <EOS_TOKEN> issue
1
#2 opened 4 months ago
by
alexcardo
Why a different architecture from mini and medium?
5
#5 opened 4 months ago
by
winddude
Can you please also quantize Phi-3-SMALL!!!
5
#2 opened 4 months ago
by
alexcardo
Prompt example for LLAMA CPP for translations tasks
#1 opened 4 months ago
by
alexcardo
I'm experiencing the same endless loop with this version as well
#1 opened 4 months ago
by
alexcardo
Prompt Template example
3
#7 opened 5 months ago
by
101rakibulhasan
Still endless output with any gguf if not instruct mode
1
#14 opened 4 months ago
by
alexcardo
Template for LLama CPP server
#6 opened 4 months ago
by
alexcardo
Whether this model an open-source?
1
#20 opened 4 months ago
by
alexcardo
The best 8B in the planet right now. PERIOD!
2
#22 opened 5 months ago
by
cyberneticos
How to prompt it correctly?
3
#6 opened 6 months ago
by
alexcardo
Что лежит в основе модели и какой был датасет?
5
#4 opened 7 months ago
by
alexcardo
Glitch with Gemma model
1
#2 opened 7 months ago
by
alexcardo
This quant gives a terrifying output
3
#1 opened 7 months ago
by
alexcardo
Will there be quantized versions? (GGUF)
10
#4 opened 8 months ago
by
alexcardo
EOS token wrong
4
#1 opened 8 months ago
by
mljxy
What am I doing wrong?
1
#2 opened 8 months ago
by
alexcardo
Even this excellent high-end model doesn't follow my instructions
5
#8 opened 9 months ago
by
alexcardo
How is it possible that Q4_K_M performs better than any Q5, Q6 and even Q8?
1
#8 opened 9 months ago
by
alexcardo