DiscoPhoenix-7B-dpo

DiscoPhoenix-7B

DiscoPhoenix-7B is a dpo tuned merge of the following models using LazyMergekit:

• DiscoResearch/DiscoLM_German_7b_v1
• DRXD1000/Phoenix
• OpenPipe/mistral-ft-optimized-1227

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: DiscoResearch/DiscoLM_German_7b_v1
    parameters:
      density: 0.6
      weight: 0.3
  - model: DRXD1000/Phoenix
    parameters:
      density: 0.6
      weight: 0.3
  - model: OpenPipe/mistral-ft-optimized-1227
    parameters:
      density: 0.6
      weight: 0.4
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

mt-bench-de results

{
    "first_turn": 7.3354430379746836,
    "second_turn": 6.65,
    "categories": {
        "writing": 8.7,
        "roleplay": 7.605263157894737,
        "reasoning": 5.75,
        "math": 3.3,
        "coding": 5.3,
        "extraction": 7.55,
        "stem": 8.4,
        "humanities": 9.35
    },
    "average": 6.9927215189873415
}

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mayflowergmbh/DiscoPhoenix-7B"
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"])