Juk Armstrong

jukofyork's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in jukofyork/creative-writing-control-vectors-v3.0 about 9 hours ago

THE THREAD OF DOOM

77

#12 opened 22 days ago by

jukofyork

liked a model about 17 hours ago

Qwen/QVQ-72B-Preview

Image-Text-to-Text • Updated about 18 hours ago • 1.07k • 226

liked a model 1 day ago

OpenGVLab/InternVL2_5-78B

Image-Text-to-Text • Updated 7 days ago • 4.36k • 159

upvoted a collection 17 days ago

K2

Collection

K2, LLM360's most powerful, scaled model series. • 7 items • Updated Oct 7 • 9

upvoted a collection 18 days ago

NOSLOP

Collection

Large language models which were NOT trained on synthetic data. • 8 items • Updated Oct 16 • 1

New activity in unsloth/Llama-3.3-70B-Instruct 18 days ago

Big thanks for these "without original" uploads!

1

#1 opened 18 days ago by

jukofyork

upvoted an article 21 days ago

view article

Article

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

By •

21 days ago

• 70

liked 3 models 22 days ago

jukofyork/Dark-Miqu-70B

Text Generation • Updated May 14 • 124 • 24

jukofyork/creative-writing-control-vectors-v3.0

Updated Sep 20 • 47k • 18

crestf411/L3-70B-daybreak-storywriter-v0.4

Text Generation • Updated Jun 2 • 36 • 5

New activity in jukofyork/creative-writing-control-vectors-v3.0 22 days ago

Discussion

1

#11 opened 22 days ago by

BigHuggyD

These seem to work with finetunes too

20

#3 opened 4 months ago by

gghfez

Model suggestions and requests

19

#5 opened 3 months ago by

jukofyork

*** llmixer's ExllamaV2 wrapper! ***

3

#10 opened about 2 months ago by

llmixer

updated a model 22 days ago

jukofyork/creative-writer-v0.2-bravo-35b

Text Generation • Updated 22 days ago • 31

New activity in Qwen/QwQ-32B-Preview 27 days ago

Adds Chinese characters to responses

7

#16 opened 27 days ago by

maxbenk

New activity in Qwen/Qwen2.5-Coder-32B-Instruct 27 days ago

How to run speculative decoding of this model with 0.5B model.

3

#18 opened about 1 month ago by

Eryk-Chmielewski

New activity in skytnt/midi-model 28 days ago

Do you know any good literature on how they created the base model?

5

#2 opened about 2 months ago by

jukofyork