Gemma 2 Lyco Infinity 9B
Gemma 2 Lyco Infinity 9B is a merge of the following models using Mergekit:
🧩 Configuration
base_model: recoilme/recoilme-gemma-2-9B-v0.4
models:
- model: recoilme/recoilme-gemma-2-9B-v0.4
# No parameters necessary for base model
- model: BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
parameters:
density: 0.525
weight: 1
merge_method: dare_ties
tokenizer_source: base
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "AELLM/gemma-2-lyco-infinity-9b"
messages = [{"role": "user", "content": "You're an AI assistant for a time traveler. How do you help them blend into different historical eras without causing any time paradoxes?"}]
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"])