CultriX/Wernicke-7B-dpo

Edit:

• DPO-finetune using truthy-dpo dataset and CultriX/Wernicke-7B-v9.

Wernicke-7B-v9

Wernicke-7B-v9 is a merge of the following models using LazyMergekit:

• FelixChao/WestSeverus-7B-DPO-v2
• CultriX/Wernicke-7B-v8
• vanillaOVO/supermario_v2

🧩 Configuration

models:
  - model: FelixChao/WestSeverus-7B-DPO-v2
    parameters:
      density: 0.50
      weight: 0.35
  - model: CultriX/Wernicke-7B-v8
    parameters:
      density: 0.50
      weight: 0.35
  - model: vanillaOVO/supermario_v2
    parameters:
      density: 0.50
      weight: 0.30
merge_method: dare_ties
base_model: FelixChao/WestSeverus-7B-DPO-v2
parameters:
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "CultriX/Wernicke-7B-v9"
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"])