### System:

### USER:{prompt}

### Assistant:

Temp: 1.0
min-p: 0.02-0.1

Example 1:

User:

Lumosia:

Example 2:

User:

Lumosia:

yaml
base_model: DopeorNope/SOLARC-M-10.7B
gate_mode: hidden
dtype: bfloat16

experts:
  - source_model: DopeorNope/SOLARC-M-10.7B
    positive_prompts:
    
    negative_prompts:

  - source_model: Sao10K/Fimbulvetr-10.7B-v1 [Updated]
    positive_prompts:
    
    negative_prompts:

  - source_model: jeonsworld/CarbonVillain-en-10.7B-v4 [Updated]
    positive_prompts:
    
    negative_prompts:

  - source_model: kyujinpy/Sakura-SOLAR-Instruct
    positive_prompts:
    
    negative_prompts:

python
!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Steelskull/Lumosia-v2-MoE-4x10.7"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])