powermove72/Elysium-Omni-Itt-11b

models:
  - model: powermove72/GreenScorpius2-xb
    parameters:
      weight: 0.7
  - model: powermove72/Trinity_Notus2-xb
    parameters:
      weight: 0.3
merge_method: linear
tokenizer_source: union
dtype: float16

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "powermove72/Elysium-Omni-Itt-11b"
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"])