nvidia/Nemotron-CrossThink
Preview
•
Updated
•
2.27k
•
48
Lucas Atkins
Crystalcareai
AI & ML interests
MoE Models & Dataset Curation
Recent Activity
liked
a dataset
4 days ago
nvidia/Nemotron-CrossThink
liked
a model
about 2 months ago
Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
new activity
2 months ago
arcee-ai/Arcee-Blitz:change prompt from virtuoso-medium-3 to arcee-blitz
Organizations
Crystalcareai's activity
liked
a
dataset
4 days ago
liked
a
model
about 2 months ago
change prompt from virtuoso-medium-3 to arcee-blitz
#2 opened 2 months ago
by
Crystalcareai
updated
3
models
2 months ago
published
a
model
2 months ago
Following the instructions
1
#1 opened 2 months ago
by
Markobes
merge_method: arcee_fusion ?
3
#1 opened 2 months ago
by
Undi95
liked
a
model
2 months ago
published
4
models
3 months ago
updated
2
models
3 months ago
reacted to
sometimesanotion's
post with 👍🚀
3 months ago
Post
3326
**Update** Either I had some wrong numbers plugged in to estimate benchmark numbers from comparator, or the benchmark changed. Virtuoso Small v2 at 41.07 average is still very impressive, especially for writing draft copy for business purposes, while Lamarck remains a chatty generalist-reasoning model.
I've felt confident that 14B Qwen finetunes and merges could break the 42.0 average, and Arcee **came close** with https://huggingface.co/arcee-ai/Virtuoso-Small-2. Congratulations to @arcee-ai !
Just two months ago, it was easy to think that 14B had plateaued, that you could have high IFEVAL or high MUSR/MATH/GPQA at 14B, but not both. That barrier is completely shattered. I see a pathway to even better, and Virtuoso Small 2 is a big part of why. Very impressive work. This community would expect no less from Arcee.
Just look at this graph! Keep in mind, my merges here build on the first Virtuoso Small, and *-DS merges build on DeepSeek R1. There are some impressive merges in the pipe!
I've felt confident that 14B Qwen finetunes and merges could break the 42.0 average, and Arcee **came close** with https://huggingface.co/arcee-ai/Virtuoso-Small-2. Congratulations to @arcee-ai !
Just two months ago, it was easy to think that 14B had plateaued, that you could have high IFEVAL or high MUSR/MATH/GPQA at 14B, but not both. That barrier is completely shattered. I see a pathway to even better, and Virtuoso Small 2 is a big part of why. Very impressive work. This community would expect no less from Arcee.
Just look at this graph! Keep in mind, my merges here build on the first Virtuoso Small, and *-DS merges build on DeepSeek R1. There are some impressive merges in the pipe!
-
- 5 replies
replied to
sometimesanotion's
post
3 months ago
Thank you for sharing this! We haven’t publicized v2 yet as we’re building out our model engine to support all these different models - but there’s more come here. Along with some updates to mergekit!
published
a
model
3 months ago