Orimo W
imoc
AI & ML interests
None yet
Recent Activity
liked
a model
1 day ago
unsloth/Llama-3.3-70B-Instruct-bnb-4bit
liked
a model
1 day ago
dnhkng/RYS-Gemma-2-27b-it
liked
a model
2 days ago
meta-llama/Llama-3.2-90B-Vision-Instruct
Organizations
None yet
imoc's activity
Which one?
#1 opened 2 days ago
by
imoc
too big to run
2
#320 opened 20 days ago
by
karan963
Why FP32?
2
#10 opened 4 days ago
by
imoc
The training data is not in ChatML format and it won't stop correctly.
3
#3 opened 16 days ago
by
imoc
Difference between this and the other (100 steps) model?
7
#1 opened 4 months ago
by
lemon07r
Nice work!
7
#1 opened 3 months ago
by
DeFactOfficial
32 B coding model please
3
#4 opened about 1 month ago
by
gopi87
vllm reply garbled
3
#29 opened 23 days ago
by
SongXiaoMao
This is way too much... USB? Yes. U SB.
3
#21 opened 24 days ago
by
imoc
Very good 7B, good job
#1 opened 24 days ago
by
imoc
Adds Chinese characters to responses
7
#16 opened 25 days ago
by
maxbenk
Nice name QAQ. I'll later upload a 4.7bpw quantized model if it works.
#12 opened 25 days ago
by
imoc
Nice work. Best 32B model(quantized to 4.7bpw) so far, more people should try.
1
#1 opened about 1 month ago
by
imoc
Does not work. The model size is wrong too. 1.5B x 5.5BPW should be ~1.6GB
4
#1 opened about 1 month ago
by
imoc
What's the prompt template though? It doesn't like to stop😂
2
#4 opened 8 months ago
by
imoc
WC models are heavily biased towards old standards/code samples
3
#8 opened 12 months ago
by
FizzyFolk