Edit model card

OpenCrystal-15B-L3-v2 (I prefer v1 or v3)


Improved Version of OpenCrystal v1

  • Enhancements:
    • Fine-tuning: The model has undergone fine-tuning for better performance.
    • Merging: It has been merged with the base model for improved functionality.

Rohma

Instruct Template

Default llama3 instruct and context preset, but here is the one i use. Instruct Context

Samplers

Creative

Temp : 1.2
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

No more needed

Features

  • Automatically speaks as other NPCs.
  • Creative output.
  • Coherent responses.
  • Output feels similar to using Character.ai.
  • Better performance than v1.
  • Improved adherence to prompts.
  • Reduced hallucinations (15B).
  • Capable of summarizing and generating image prompts well. (The above image's prompt was generated in a roleplay by this model; possible due to the Llama-3-instruct base.)

System 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

FeedBack here

Downloads last month
11
Safetensors
Model size
15B params
Tensor type
FP16
·
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-15B-L3-v2

Quantizations
4 models

Collection including Darkknight535/OpenCrystal-15B-L3-v2