invisietch/RainbowsEdge-v0.1-rc1-18B-GGUF

<div align="center"> <b style="font-size: 36px;">RainbowsEdge-v0.1-rc1-18B-GGUF</b>

<b style="font-size: 24px;color:#ffff00">Important note: this model has a broken config which prevents ROPE from working. Please use <a href="https://huggingface.co/invisietch/RainbowsEdge-v0.1-rc2-18B-GGUF">release candidate 2</a> instead. It is an identical model apart from fixing this issue, and supporting closer to 16k context with ROPE.</b>

<img src="https://huggingface.co/invisietch/RainbowsEdge-v0.1-rc1-18B-GGUF/resolve/main/header.png" style="width:60%"> </div>

Model Details

This is a release candidate model. That means it has not been tested as extensively as my full releases and as such you should expect various issues. The primary purpose of uploading this model is to get feedback.

Rainbow's Edge is a passthrough upscale of two highly capable Llama 3 8B roleplay models, with a goal to create a very uncensored and very capable release model which matches a lot of GPUs.

The Q8_0 runs well on a 24GB GPU.

The Q5KM runs well on a 16GB GPU.

Due to this being a Llama 3 (not Llama 3.1) merge, context sizes above 8192 are not supported or recommended. Catastrophic collapse is the expected behavior beyond this context length.

Feedback

Please, please, please, give feedback on this merge. It is simply the result of a theory and minimally tested to ensure that it doesn't completely collapse. I welcome feedback in the community section here, or on Discord (name is the same as on here). I can be found on the Chub & SillyTavern Discord servers in the local LLM channels frequently too.

Quantization Formats

As this is a release candidate, I have only provided GGUFs.

Disclaimer

This model is built on an abliterated base and as such is largely uncensored. It can generate explicit, disturbing or offensive responses. Use responsibly. I am not responsible for your use of this model.

Settings

Samplers

I'm using these sampler settings:

• —Context: 8192
• —Temperature: 0.8
• —Top P: 0.9
• —Min P: 0.08
• —Repetition Penalty: 1.11 (or DRY)
• —Rep Pen Range: 1536

These are by no means the perfect settings, feel free to experiment.

Prompting Format

I'd recommend Llama-3 Instruct prompting format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Some of the models included in the merge were trained on ChatML &amp; Alpaca so you can try those. I have not tested them.

Example Storywriting

N/A.

Merge Strategy

Models Used

The following models were used to create RainbowsEdge v0.1 RC1:

• —SicariusSicariiStuff/Dusk_Rainbow
• —invisietch/EtherealRainbow-v0.3-8B

Mergekit Config

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: invisietch/EtherealRainbow-v0.3-8B
- sources:
  - layer_range: [8,24]
    model: SicariusSicariiStuff/Dusk_Rainbow
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [8,24]
    model: invisietch/EtherealRainbow-v0.3-8B
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [8,24]
    model: SicariusSicariiStuff/Dusk_Rainbow
    parameters:
      scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
- sources:
  - layer_range: [24, 32]
    model: invisietch/EtherealRainbow-v0.3-8B