Edit model card

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
571
Safetensors
Model size
11.5B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

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

Quantizations
2 models

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