CoolFace
Modelpublic

v000000/SwallowMaid-8B-L3-SPPO-abliterated

sourceHugging Faceupdated 2y agoView on Hugging Face
7likes48downloads
Model Card

<!DOCTYPE html> <style>

h1 { color: #900C3F; / Red color / font-size: 1.25em; / Larger font size / text-align: left; / Center alignment / text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5); / Shadow effect / background: linear-gradient(90deg, #900C3F, #fba8a8); / Gradient background / -webkit-background-clip: text; / Clipping the background to text / -webkit-text-fill-color: transparent; / Making the text transparent / }

</style> <html lang="en"> <head> </head> <body> General Instruct, RP, Q&A and Storywriting.

<h1>SwallowMaid-8B-Llama-3-SPPO-abliterated</h1>

image/png

"Llama-3-Instruct-8B-SPPO-Iter3" fully uncensored with 35% RP-Mix infused vector direction to gain some roleplay capabilities and prose while attempting to preserve the qualities of Meta's Llama-3-Instruct finetune.

<a>Thank you mradermacher for the quants!</a>

<a>Quants</a>

<h1>merge</h1>

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

<h1>Merge Details</h1>

<h1>Merge Method</h1>

This model was merged using a multi-step merge method.

<h1>Models Merged</h1>

The following models were included in the merge:

<h1>Configuration</h1>

The following YAML configuration was used to produce this model:

yaml
# Part 3, Apply abliteration (SwallowMaid-8B)
models:
  - model: sppo-rpmix-part2+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    parameters:
      weight: 1.0
merge_method: linear
dtype: float32

# Part 2, infuse 35% swallow+rpmix to SPPO-Iter3 (sppo-rpmix-part2)
models:
  - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
    parameters:
      weight: 1.0
  - model: rpmix-part1
    parameters:
      weight: 0.35
merge_method: task_arithmetic
base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
parameters:
    normalize: false
dtype: float32

# Part 1, linear merge rpmix (rpmix-part1)
models:
  - model: Nitral-AI/Hathor_Respawn-L3-8B-v0.8
    parameters:
      weight: 0.6
  - model: maldv/llama-3-fantasy-writer-8b
    parameters:
      weight: 0.1
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
    parameters:
      weight: 0.4
  - model: tokyotech-llm/Llama-3-Swallow-8B-v0.1
    parameters:
      weight: 0.15
merge_method: linear
dtype: float32

<h1>Prompt Template:</h1>

bash
<|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|>

</body> </html>