Sakalti/Saka-14B
Text Generation
•
Updated
•
5
•
2
Sthenno
sthenno
AI & ML interests
To contact me: [email protected]
Recent Activity
liked
a model
about 5 hours ago
Sakalti/Saka-14B
liked
a model
1 day ago
sometimesanotion/KytheraMix-7B-v0.2
liked
a dataset
1 day ago
open-thoughts/OpenThoughts-114k
Organizations
sthenno's activity
liked
a
model
about 5 hours ago
liked
a
model
1 day ago
liked
a
dataset
1 day ago
updated
a
model
1 day ago
liked
a
model
1 day ago
published
a
model
1 day ago
liked
a
Space
2 days ago
liked
2
models
2 days ago
liked
5
models
3 days ago
CultriX/Qwen2.5-14B-Ultimav2
Text Generation
•
Updated
•
49
•
3
CultriX/Qwen2.5-14B-Ultima
Text Generation
•
Updated
•
17
•
2
CultriX/Enhanced-TIES-Base-v1
Text Generation
•
Updated
•
68
•
2
CultriX/Qwen2.5-14B-Qwentangledv2
Text Generation
•
Updated
•
20
•
3
sometimesanotion/Qwenvergence-14B-v13-Prose-DS
Text Generation
•
Updated
•
75
•
5
reacted to
sometimesanotion's
post with 👍
5 days ago
Post
3093
**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
5 days ago
Congratulations as well! When I first saw the evaluation results for Virtuoso-Small-2, I quickly abandoned the release of "miscii-14b-0130". Although BBH and IFEval were once strengths of the miscii series - I admit that within my limited personal technical capabilities, I was indeed beaten by @arcee-ai ;)
reacted to
sometimesanotion's
post with 🚀
5 days ago
Post
3093
**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
updated
a
model
5 days ago
liked
a
model
5 days ago
updated
a
model
5 days ago