Article
Merge Large Language Models with mergekit
By
•
•
101Anton Kratz
akratz
AI & ML interests
None yet
Recent Activity
upvoted
an
article
about 1 month ago
Merge Large Language Models with mergekit
commented on
an
article
about 1 month ago
Merge Large Language Models with mergekit
new activity
almost 2 years ago
ctheodoris/Geneformer:Input files for example notebooks
Organizations
None yet
akratz's activity
upvoted
an
article
about 1 month ago
commented on
Merge Large Language Models with mergekit
about 1 month ago
Awesome article. It seems to me that only models with identical architecture (e.g., same number of layers, hidden dimensions, attention heads) can be merged with this approach. Is that correct? How do you know which models have identical architectures?
Input files for example notebooks
6
#4 opened almost 2 years ago
by
GMFranceschini
nonzero median
1
#1 opened almost 2 years ago
by
akratz
liked
2
models
almost 2 years ago
🚩424 Failed dependency
6
#243 opened almost 2 years ago
by
bvk1ng
What is the length of the prompt considered by BLOOM?
4
#236 opened almost 2 years ago
by
akratz
Is Bloom still being improved and updated or was it just released and abandoned?
2
#219 opened almost 2 years ago
by
Alysialr
What is the task that BLOOM has been trained on?
1
#237 opened almost 2 years ago
by
akratz
🚩 Report : Not working
2
#9 opened almost 2 years ago
by
TempoNaoTenho
Why does the ROOTS Corpus not include German language?
2
#221 opened almost 2 years ago
by
akratz
Trying this demo, all I get is a message "Error" when pasting the example texts.
1
#2 opened almost 2 years ago
by
akratz