Ralfi Kier
electroglyph
AI & ML interests
None yet
Recent Activity
new activity
about 2 hours ago
Qwen/Qwen3-Embedding-0.6B-GGUF:Getting token embeddings instead of sentence embeddings
updated
a model
about 13 hours ago
electroglyph/unsloth_test3
published
a model
about 13 hours ago
electroglyph/unsloth_test3
Organizations
None yet
Getting token embeddings instead of sentence embeddings
5
#8 opened 7 months ago
by
cicada330117
Question about Mistral Vibe being recommended
2
#8 opened 21 days ago
by
electroglyph
Seems to prefer shorter content? Model config issue?
👍
1
23
#8 opened 4 months ago
by
hichaelmart
How did you quantize the model into uint8?
4
#1 opened 6 months ago
by
galabala
how to run onnx model in python code?
6
#3 opened 7 months ago
by
minhdang
does the tokenizer need to be updated for this model?
1
#5 opened 6 months ago
by
electroglyph
nvm =)
#2 opened 7 months ago
by
electroglyph
Any chance of a GrayLine version of this model?
#1 opened 7 months ago
by
electroglyph
here I did some tests if anyone is interested and plans to use this model.....
👍
1
5
#12 opened 10 months ago
by
Sreta
mind doing phi 4 mini?
6
#5 opened 10 months ago
by
electroglyph
high memory use
5
#3 opened about 1 year ago
by
rootw0rm
high memory use
5
#3 opened about 1 year ago
by
rootw0rm
high memory use
5
#3 opened about 1 year ago
by
rootw0rm