base_model: fhnw/Llama-3-8B-pineapple-pizza-orpo
experts:
- source_model: fhnw/Llama-3-8B-pineapple-pizza-orpo
  positive_prompts: ["assistant", "chat"]
- source_model: fhnw/Llama-3-8B-pineapple-recipe-sft
  positive_prompts: ["recipe"]
gate_mode: hidden
dtype: float16

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "fhnw/Llama-3-pineapple-2x8B"

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(device)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Is pineapple on a pizza a crime?"}
]

input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))