Hugging Face's logo
Neo Dim's picture
8 1 88

Neo Dim

NeoDim
21world's profile picture xhyi's profile picture maddes8cht's profile picture
·

AI & ML interests

None yet

Organizations

None yet

NeoDim's activity

New activity in bartowski/starchat2-15b-v0.1-GGUF 7 months ago

What is the prompt format?

13
#1 opened 8 months ago by siddhesh22
New activity in NeoDim/starcoder-GGML over 1 year ago

how did you convert `transformers.PreTrainedTokenizer` to ggml format?

1
#2 opened over 1 year ago by keunwoochoi
New activity in NeoDim/starchat-alpha-GGML over 1 year ago

demo space

2
#4 opened over 1 year ago by matthoffner

Looks like the starchat-alpha-ggml-q4_1.bin is broken

8
#3 opened over 1 year ago by xhyi
New activity in NeoDim/starcoderbase-GGML over 1 year ago

missing tok_embeddings.weight error when trying to run with llama.cpp

2
#1 opened over 1 year ago by ultra2mh
New activity in NeoDim/starcoder-GGML over 1 year ago

Cannot run on llama.cpp and koboldcpp

3
#1 opened over 1 year ago by FenixInDarkSolo
New activity in NeoDim/starchat-alpha-GGML over 1 year ago

Which inference repo is this quantized for?

3
#2 opened over 1 year ago by xhyi

Can the quantized model be loaded in gpu to have faster inference ?

6
#1 opened over 1 year ago by MohamedRashad

Can the quantized model be loaded in gpu to have faster inference ?

6
#1 opened over 1 year ago by MohamedRashad
New activity in NeoDim/starcoder-GGML over 1 year ago

Cannot run on llama.cpp and koboldcpp

3
#1 opened over 1 year ago by FenixInDarkSolo
New activity in NeoDim/starchat-alpha-GGML over 1 year ago

Can the quantized model be loaded in gpu to have faster inference ?

6
#1 opened over 1 year ago by MohamedRashad