7 10

no

asdfsdfssddf

AI & ML interests

None yet

Recent Activity

New activity about 1 month ago

MarinaraSpaghetti/SillyTavern-Settings:Feedback + Requests

New activity about 2 months ago

EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1:I think this is a promising model, but it deteriorates into broken english quite fast

liked a model about 2 months ago

EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1

View all activity

Organizations

None yet

asdfsdfssddf's activity

New activity in MarinaraSpaghetti/SillyTavern-Settings about 1 month ago

Feedback + Requests

#1 opened 4 months ago by

MarinaraSpaghetti

New activity in EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1 about 2 months ago

I think this is a promising model, but it deteriorates into broken english quite fast

#1 opened about 2 months ago by

Jellon

liked 3 models about 2 months ago

New activity in EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0 about 2 months ago

Some feedback

#4 opened about 2 months ago by

asdfsdfssddf

New activity in MarinaraSpaghetti/NemoMix-Unleashed-12B about 2 months ago

Feedback

#1 opened 3 months ago by

MarinaraSpaghetti

liked 2 models about 2 months ago

TheDrummer/Cydonia-22B-v1.1

Updated Sep 29 • 39 • 17

mradermacher/Llama-3.2-3B-Instruct-uncensored-GGUF

Updated Sep 28 • 40.9k • 35

New activity in mradermacher/Llama-3.2-3B-Instruct-uncensored-GGUF about 2 months ago

Possible to add 4_0_4_4 and 4_0_4_8 quants?

#1 opened about 2 months ago by

asdfsdfssddf

New activity in NousResearch/Hermes-3-Llama-3.1-405B 2 months ago

Model Review (RP/ERP)

#4 opened 3 months ago by

MarinaraSpaghetti

Reacted to inflatebot's post with 👍 2 months ago

Post

3030

!!SEE UPDATE BELOW!!
I don't know who still needs to hear this, but if you're using Mistral Nemo-based models, you might have been using the wrong completions format. This is a signal boost from MarinaraSpaghetti's model card for NemoMix-Unleashed: MarinaraSpaghetti/NemoMix-Unleashed-12B
A lot of people have been working with a version of Nemo that's been reconfigured for ChatML, and while that works great, simply using the right format might be just as effective at correcting weirdness people in the AIRP scene sometimes have with Nemo.

Huge ups to Marinara for pointing this out, and to the MistralAI team member who let her know.

Update: A PR has been merged to SillyTavern Staging with new corrected templates! If you don't want to switch or wait, I put them up on GitHub: https://github.com/inflatebot/SillyTavern-Mistral-Templates

PRs for KoboldCPP's chat adapters and KoboldAI Lite *have been merged* and are coming in their respective releases (probably the next time KoboldCPP updates -- it didn't make it for 1.75.1, but you could just grab 'em from the repo!)