merge_method: task_arithmetic
dtype: float16
base_model: jeiku/Average_Normie_v2_l3_8B
models:
  - model: Kaoeiri/Keiana-L3-Test4.7-8B-3
    parameters:
      weight: 1.0
  - model: vicgalle/Roleplay-Llama-3-8B
    parameters:
      weight: 1.0

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kaoeiri/Keiana-L3-Test5.0-8B-6"
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"])