3WaD/Lamarck-14B-v0.7-bnb-4bit
Updated
•
3
•
1
sometimesanotion PRO
sometimesanotion
AI & ML interests
Agentic LLM services, model merging, finetunes, distillation
Recent Activity
liked
a model
about 2 hours ago
3WaD/Lamarck-14B-v0.7-bnb-4bit
new activity
about 4 hours ago
CultriX/MergeStage2v3:This is starting to look a bit like the Lamarck process
liked
a model
about 4 hours ago
CultriX/MergeStage1
Organizations
sometimesanotion's activity
liked
a
model
about 2 hours ago
This is starting to look a bit like the Lamarck process
#1 opened about 4 hours ago
by
sometimesanotion
liked
a
model
about 4 hours ago
Impressive fusion
1
#2 opened about 11 hours ago
by
jpacifico
updated
2
models
2 days ago
Congratulations!
#2 opened 5 days ago
by
sometimesanotion
updated
a
model
4 days ago
published
a
model
4 days ago
liked
a
model
4 days ago
updated
a
model
4 days ago
posted
an
update
4 days ago
Post
517
I am really pleased to see
jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 take #4 on the 14B segment of the Open LLM leaderboard. It is a fine-tune of a merge of Arcee's
arcee-ai/Virtuoso-Small-v2, and my
sometimesanotion/Lamarck-14B-v0.7 and
sometimesanotion/Qwenvergence-14B-v12-Prose-DS. Don't let the numbers fool you, in its element, it's quite smooth. I really enjoy merges of Lamarck with near siblings like this one.
Don't be surprised when it's challenging to bring in the full reasoning strength of a reason-heavy prose model like Qwenvergence v12-DS into a high IFEVAL model like Lamarck or Virtuoso Small v2. That's a lot of work to get right, because IFEVAL, precise reasoning, and prose quality are often in tension against each other. Gaining as much as this did is really respectable, and fine-tuning it makes it a more stable base for the coming iterations.
Don't be surprised when it's challenging to bring in the full reasoning strength of a reason-heavy prose model like Qwenvergence v12-DS into a high IFEVAL model like Lamarck or Virtuoso Small v2. That's a lot of work to get right, because IFEVAL, precise reasoning, and prose quality are often in tension against each other. Gaining as much as this did is really respectable, and fine-tuning it makes it a more stable base for the coming iterations.
liked
a
model
4 days ago
published
2
models
5 days ago
This merge makes sense
2
#1 opened 5 days ago
by
sometimesanotion
Excellent model!
8
#3 opened 6 days ago
by
nixudos
No, this is promising
6
#1 opened 8 days ago
by
CultriX
A tour of 14B finetuning
1
#1 opened 5 days ago
by
sometimesanotion
liked
a
model
5 days ago