OpenCrystal-12B-L3.1 (128K)

This is a merge of pre-trained language models created using mergekit.

Rohma

NOTE

I've not tested this model yet, it's just a 128K (llama 3.1) variant of OpenCrystal-12B-L3, so do provide feedback.

FeedBack

FeedBack here

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 : 0.8
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
  • Coherent (Sometime gets horny)
  • (it's llama 3.1 so you know, not good as llama 3)
  • can summarize and generate image prompts well.

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.
Downloads last month
4
Safetensors
Model size
11.5B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Darkknight535/OpenCrystal-12B-L3.1-128K

Quantizations
3 models

Collection including Darkknight535/OpenCrystal-12B-L3.1-128K