TheDrummer/Cydonia-22B-v1.3-GGUF
Updated
•
14.1k
•
16
no
asdfsdfssddf
·
AI & ML interests
None yet
Recent Activity
liked
a model
22 days ago
TheDrummer/Cydonia-22B-v1.3-GGUF
new activity
22 days ago
TheDrummer/Cydonia-22B-v1.3-GGUF:any chance of IQ quants?
Organizations
None yet
asdfsdfssddf's activity
liked
a
model
22 days ago
any chance of IQ quants?
#3 opened 22 days ago
by
asdfsdfssddf
Feedback + Requests
17
#1 opened 4 months ago
by
MarinaraSpaghetti
I think this is a promising model, but it deteriorates into broken english quite fast
15
#1 opened 2 months ago
by
Jellon
liked
a
model
2 months ago
liked
2
models
3 months ago
Some feedback
#4 opened 3 months ago
by
asdfsdfssddf
Feedback
44
#1 opened 4 months ago
by
MarinaraSpaghetti
liked
2
models
3 months ago
Possible to add 4_0_4_4 and 4_0_4_8 quants?
1
#1 opened 3 months ago
by
asdfsdfssddf
Model Review (RP/ERP)
13
#4 opened 3 months ago
by
MarinaraSpaghetti
reacted to
inflatebot's
post with 👍
3 months ago
Post
3038
!!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!)
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!)
- 1 reply
Possibly the provided prompt format is wrong.
12
#1 opened 3 months ago
by
vevi33
liked
3
models
4 months ago
updated
a
collection
4 months ago