SomeModelsMerge-7b

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

• liminerity/M7-7b
• Kukedlc/NeuralSirKrishna-7b
• Kukedlc/MyModelsMerge-7b
• AurelPx/Percival_01-7b-slerp
• MatthieuJ/Jason1903_SLERP
• MTSAIR/multi_verse_model
• Gille/StrangeMerges_30-7B-slerp
• chihoonlee10/T3Q-Mistral-Orca-Math-DPO
• yam-peleg/Experiment28-7B
• mlabonne/UltraMerge-7B

🧩 Configuration

models:
  - model: liminerity/M7-7b
    # no parameters necessary for base model
  - model: liminerity/M7-7b
    parameters:
      weight: 0.2
      density: 0.88
  - model: Kukedlc/NeuralSirKrishna-7b
    parameters:
      weight: 0.1
      density: 0.66
  - model: Kukedlc/MyModelsMerge-7b
    parameters:
      weight: 0.1
      density: 0.66
  - model: AurelPx/Percival_01-7b-slerp
    parameters:
      weight: 0.1
      density: 0.33
  - model: MatthieuJ/Jason1903_SLERP
    parameters:
      weight: 0.1
      density: 0.33
  - model: MTSAIR/multi_verse_model
    parameters:
      weight: 0.1
      density: 0.66
  - model: Gille/StrangeMerges_30-7B-slerp
    parameters:
      weight: 0.1
      density: 0.55
  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
    parameters:
      weight: 0.1
      density: 0.22
  - model: yam-peleg/Experiment28-7B
    parameters:
      weight: 0.1
      density: 0.44
  - model: mlabonne/UltraMerge-7B
    parameters:
      weight: 0.1
      density: 0.77
merge_method: dare_ties
base_model: liminerity/M7-7b

parameters:
  int8_mask: true
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/SomeModelsMerge-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"])