Wiederchat-7b-dpo / README.md
johannhartmann's picture
Update README.md
93d5ebf verified
|
raw
history blame
2.42 kB
metadata
tags:
  - merge
  - mergekit
  - lazymergekit
  - mlabonne/OmniTruthyBeagle-7B-v0
  - mayflowergmbh/Wiedervereinigung-7b-dpo-laser
  - cognitivecomputations/openchat-3.5-0106-laser
base_model:
  - mlabonne/OmniTruthyBeagle-7B-v0
  - mayflowergmbh/Wiedervereinigung-7b-dpo-laser
  - cognitivecomputations/openchat-3.5-0106-laser

Wiederchat-7b-dpo

Wiederchat-7b-dpo is a dpo-aligned merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: mlabonne/OmniTruthyBeagle-7B-v0
    parameters:
      density: 0.60
      weight: 0.30
  - model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
    parameters:
      density: 0.65
      weight: 0.40
  - model: cognitivecomputations/openchat-3.5-0106-laser
    parameters:
      density: 0.6
      weight: 0.3
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0

πŸ“ˆ Mt-Bench-De

{
    "first_turn": 7.8375,
    "second_turn": 7.4,
    "categories": {
        "writing": 8.975,
        "roleplay": 8.775,
        "reasoning": 6.4,
        "math": 4.1,
        "coding": 6.05,
        "extraction": 8.15,
        "stem": 9.175,
        "humanities": 9.325
    },
    "average": 7.61875
}

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "johannhartmann/Wiederchat-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"])