metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - liminerity/M7-7b
  - Kukedlc/Neural4gsm8k
  - Kukedlc/Jupiter-k-7B-slerp
  - Kukedlc/NeuralMaxime-7B-slerp
  - Kukedlc/NeuralFusion-7b-Dare-Ties
  - Kukedlc/Neural-Krishna-Multiverse-7b-v3
  - Kukedlc/NeuTrixOmniBe-DPO
  - Kukedlc/NeuralSirKrishna-7b
base_model:
  - liminerity/M7-7b
  - Kukedlc/Neural4gsm8k
  - Kukedlc/Jupiter-k-7B-slerp
  - Kukedlc/NeuralMaxime-7B-slerp
  - Kukedlc/NeuralFusion-7b-Dare-Ties
  - Kukedlc/Neural-Krishna-Multiverse-7b-v3
  - Kukedlc/NeuTrixOmniBe-DPO
  - Kukedlc/NeuralSirKrishna-7b

MyModelsMerge-7b

MyModelsMerge-7b is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: Kukedlc/NeuralSirKrishna-7b
    # no parameters necessary for base model
  - model: liminerity/M7-7b
    parameters:
      weight: 0.1
      density: 0.88
  - model: Kukedlc/Neural4gsm8k
    parameters:
      weight: 0.1
      density: 0.66
  - model: Kukedlc/Jupiter-k-7B-slerp
    parameters:
      weight: 0.1
      density: 0.66
  - model: Kukedlc/NeuralMaxime-7B-slerp
    parameters:
      weight: 0.1
      density: 0.44
  - model: Kukedlc/NeuralFusion-7b-Dare-Ties
    parameters:
      weight: 0.1
      density: 0.44
  - model: Kukedlc/Neural-Krishna-Multiverse-7b-v3
    parameters:
      weight: 0.2
      density: 0.66
  - model: Kukedlc/NeuTrixOmniBe-DPO
    parameters:
      weight: 0.1
      density: 0.33
  - model: Kukedlc/NeuralSirKrishna-7b
    parameters:
      weight: 0.2
      density: 0.88
merge_method: dare_ties
base_model: Kukedlc/NeuralSirKrishna-7b

parameters:
  int8_mask: true
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/MyModelsMerge-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"])