OxytocinEngineering_v0-10B-passthrough

OxytocinEngineering_v0-10B-passthrough is a merge of the following models using LazyMergekit:

• Sao10K/Fimbulvetr-11B-v2
• KoboldAI/LLaMA2-13B-Tiefighter

🧩 Configuration

slices:
  - sources:
    - model: Sao10K/Fimbulvetr-11B-v2
      layer_range: [0, 32]
  - sources:
    - model: KoboldAI/LLaMA2-13B-Tiefighter
      layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "weezywitasneezy/OxytocinEngineering_v0-31B-passthrough"
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"])