Zeze Nene
Neman
AI & ML interests
LLM, evolutionary programming, AI
Recent Activity
liked
a model
3 days ago
ai-forever/MoVQGAN
liked
a model
5 days ago
QuantFactory/orpheus-3b-0.1-ft-GGUF
liked
a model
6 days ago
canopylabs/orpheus-3b-0.1-pretrained
Organizations
None yet
Neman's activity
Only 9 European languages?
1
#4 opened 27 days ago
by
Neman

Problem with demo code using pipeline
1
#2 opened about 1 month ago
by
Neman

unknown pre-tokenizer type: 'deepseek-r1-qwen'
7
#1 opened 3 months ago
by
Neman

unknown pre-tokenizer type: 'deepseek-r1-qwen'
2
#1 opened 3 months ago
by
Neman

safetensors size
4
#1 opened 3 months ago
by
Neman

Phone number format
#4 opened 7 months ago
by
Neman

Flash Attention
1
#3 opened 10 months ago
by
Neman

What ViT?
2
#2 opened 11 months ago
by
Neman

4-bit quant?
2
#3 opened about 1 year ago
by
Neman

Base or Chat?
2
#1 opened about 1 year ago
by
Neman

NameError: name 'flash_attn_func' is not defined
2
#4 opened about 1 year ago
by
Neman

'QWenTokenizer' object has no attribute 'IMAGE_ST'
4
#1 opened over 1 year ago
by
Neman

Will it come?
21
#2 opened over 1 year ago
by
Neman

Update of checkpoints?
#1 opened over 1 year ago
by
Neman

ImportError: cannot import name 'SeamlessM4TModel' from 'transformers'
3
#13 opened over 1 year ago
by
Neman

Question What are the results for image captioning for fuyu-8b in comparison to other models?
1
#8 opened over 1 year ago
by
Said2k
What are the memory requirements for running the model?
9
#6 opened over 1 year ago
by
joanfihu
gguf variant?
1
#1 opened over 1 year ago
by
scrawnyether
Will it come?
21
#2 opened over 1 year ago
by
Neman
