OpenCrystal-12B-L3
This is a finetuned language model. (I recommend using this one v2 and v2.1 are not good enough)
128K??
Instruct Template
Default llama3 instruct and context preset, but here is the one i use. Instruct Context
Samplers
Creative
Temp : 1.23
Min P : 0.05
Repetition Penalty : 1.05
[And everything else neutral]
Normal
Temp : 0.6 - 0.8
Min P : 0.1
Repetition Penalty : 1.1
[And everything else neutral]
Pro Tip
- You can uncheck Include Names option in sillytavern, to force it to speak as others dynamically. Not Recommended
Features
- Can speak as other npc automatically.
- Creative (Swipes are crazy.)
- Coherent (Sometime gets horny)
- Output feels like you're using Character.ai
- Follows prompt better
- Likes higher context length. (12K easily tested)
- can summarize and generate image prompts well [The Above image's prompt is generated in a roleplay by this model] (Possible : Due to llama-3-instruct as base)
Instruct Prompt
You're {{char}}, follow {{char}} personality and plot of the story, Don't impersonate as {{user}}, Speak as others NPC except {{user}} when needed. Be Creative, Create various interesting events and situations during the story.
FeedBack
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.51 |
| IFEval (0-Shot) | 40.71 |
| BBH (3-Shot) | 31.84 |
| MATH Lvl 5 (4-Shot) | 7.93 |
| GPQA (0-shot) | 7.49 |
| MuSR (0-shot) | 5.74 |
| MMLU-PRO (5-shot) | 29.34 |