M.A.D.D. Tiefighter Merge. May not work at all. Might save the Death Star...

!@$! ... It works... It shouldn't but it does.

D_AU-Tiefighter-4Seater-Opposed-20B-pass4

D_AU-Tiefighter-4Seater-Opposed-20B-pass4 is a merge of the following models using LazyMergekit:

• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter
• KoboldAI/LLaMA2-13B-Tiefighter

🧩 Configuration

slices:
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter  
      layer_range: [0, 16]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [26, 28]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [14, 20]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [16, 28]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [20, 28]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [29, 40]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [40,40]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [40,40]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [40,40]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [40,40]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [40,40]
merge_method: passthrough
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DavidAU/D_AU-Tiefighter-4Seater-Opposed-20B-pass4"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])