Edit model card

Gemma 2 Aeria Infinity 9B

Gemma 2 Aeria Infinity 9B is a merge of the following models using Mergekit:

🧩 Configuration

base_model: ifable/gemma-2-Ifable-9B
models:
  - model: ifable/gemma-2-Ifable-9B
    # No parameters necessary for base model
  - model: BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
    parameters:
      density: 0.5
      weight: 1
merge_method: dare_ties
parameters:
  int8_mask: true
dtype: bfloat16

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "AELLM/gemma-2-aeria-infinity-9b"
messages = [{"role": "user", "content": "You're a chef AI in a kitchen that serves alien species. What would you cook, and how do you handle bizarre ingredient requests?"}]

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"])
Downloads last month
84
Safetensors
Model size
9.24B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for AELLM/gemma-2-aeria-infinity-9b