DopeyGay/DolphinButtocks-7B-slerp

VERY IMPORTANT:

This model has not been tested or evaluated, and its performance, characteristics, and operational status (NOT functional, afaik) are currently unknown. Feedback is appreciated.

AI is a powerful tool, that being said, it may sometimes generate harmful, biased, untrue, or inappropriate content, and this model is no different. Please exercise caution and use it at your own risk, just like you would a drill, or a hammer, or any other tool

DolphinButtocks-7B-slerp

DolphinButtocks-7B-slerp is a merge of the following models using LazyMergekit:

• TeeZee/Buttocks-7B-v1.1
• cognitivecomputations/dolphin-2.8-mistral-7b-v02

🧩 Configuration

slices:
  - sources:
      - model: TeeZee/Buttocks-7B-v1.1
        layer_range: [0, 32]
      - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
        layer_range: [0, 32]
merge_method: slerp
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DopeyGay/DolphinButtocks-7B-slerp"
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"])