Steelskull/L3.3-Damascus-R1
Text Generation
•
Updated
•
252
•
22
Vitor Lima
Duttones
AI & ML interests
None yet
Recent Activity
liked
a model
about 7 hours ago
Steelskull/L3.3-Damascus-R1
liked
a model
21 days ago
Konnect1221/The-Inception-Presets-Methception-LLamaception-Qwenception
updated
a model
28 days ago
Duttones/Nemo-12b-Humanize-KTO-Experimental-Latest-Q8_0-GGUF
Organizations
None yet
Duttones's activity
liked
a
model
about 7 hours ago
liked
a
model
21 days ago
updated
a
model
28 days ago
updated
a
collection
about 1 month ago
liked
a
model
about 2 months ago
Awesome
2
#11 opened about 2 months ago
by
Darkknight535
liked
a
model
2 months ago
liked
3
models
3 months ago
Great model!
2
#3 opened 3 months ago
by
notafraud
liked
3
models
3 months ago
Wow! What a good hack!
#1 opened 3 months ago
by
Duttones
liked
a
model
3 months ago
Short responses?
1
#1 opened 4 months ago
by
Duttones
liked
a
model
4 months ago
reacted to
inflatebot's
post with 🔥
5 months ago
Post
3049
!!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
replied to
inflatebot's
post
5 months ago
Many thanks for this post. I didn't knew that we need to use an output string on mistral nemo. That really changed completely the response of my Nemo models.