Evertide-RX-12B

👁 evertide_rx

A generalist model, with some reasoning capabilities and multi-lang support.

Supported languages:

• English
• French
• German
• Spanish
• Italian
• Portuguese
• Russian
• Chinese
• Japanese

This model is trained in FFT based on unreleased cowriter model merge (uses same models as Retreatcost/KansenSakura-Erosion-RP-12b, credits to all original model authors.), using in-progress dateset, that I am creating for another project.

Training stats can be found in "Training metrics" tab.

Reasoning should work out of the box most of the times with occasional replies without it. For absolute consistency you can prefill model responses with "< think >\n" (think tag without spaces, line break is preferred).

Intended use

• General conversations, chatting.
• Co-writing, brainstorming.
• Short roleplaying.

Inference Tips

1. Temperature: 0.7 (0.6 - 0.8 range should work fine)
2. Repetition Penalty: 1.05
3. TOP_P: 0.90
4. TOP_K: 0 (disable)
5. MIN_P: 0.025
6. Template Format: ChatML
7. Max Output: 2048 (Due to additional reasoning budget I suggest giving the model at least 768 tokens, preferrably over 1K, but usually it rarely outputs answers longer than 1.35K, 2K is a safe max).
8. Context Management: 8K

I haven't really tested or trained the model for long context, so it will probably break earlier than regular models. You can set a higher context, for example 16K, 24K or 32K, but I don't guarantee how it will behave.

Training details

FAQ

Special Thanks

• Team mradermacher: for awesome quants in GGUF format
• DeathGodlike for awesome quants in EXL3 format

Base model

Retreatcost/KansenSakura-Erosion-CW-12b

(1)

Master of none • 2 items • Updated 23 days ago • 2