Roman Ivanov
perelmanych
AI & ML interests
None yet
Recent Activity
new activity
9 days ago
bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:R1 32b is much worse than QwQ ...
new activity
9 months ago
mradermacher/Llama3-ChatQA-1.5-70B-GGUF:IQ2_XS variant
Organizations
None yet
perelmanych's activity
R1 32b is much worse than QwQ ...
22
#6 opened 10 days ago
by
mirek190
SFT (Non-RL) distillation is this good on a sub-100B model?
3
#2 opened 11 days ago
by
KrishnaKaasyap
IQ2_XS variant
1
#2 opened 9 months ago
by
perelmanych
When we can expect vicuna variant of CodeLlama-2 34b model?
#10 opened over 1 year ago
by
perelmanych
Running with ExLlama and GPTQ-for-LLaMa in text-generation-webui gives errors
1
#3 opened over 1 year ago
by
perelmanych
All years and big numbers are truncated
1
#3 opened over 1 year ago
by
perelmanych
Can't load q5_1 model
3
#1 opened over 1 year ago
by
perelmanych
Error when using with web-ui "KeyError: 'model.layers.39.self_attn.q_proj.wf1'"
16
#7 opened almost 2 years ago
by
TheFairyMan
Error using ooba-gooba
39
#6 opened almost 2 years ago
by
blueisbest
Error using ooba-gooba
39
#6 opened almost 2 years ago
by
blueisbest
Error using ooba-gooba
39
#6 opened almost 2 years ago
by
blueisbest