Neo_7b-merge5

Neo_7b-merge5 is a merge of the following models using LazyMergekit:

• m-a-p/neo_7b
• DewEfresh/neo_7b

🧩 Configuration

slices:
  # Group 1
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [0, 0]
      - model: DewEfresh/neo_7b
        layer_range: [0, 0]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [1, 1]
      - model: DewEfresh/neo_7b
        layer_range: [1, 1]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [2, 2]
      - model: DewEfresh/neo_7b
        layer_range: [2, 2]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [3, 3]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  # Group 2
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [4, 4]
      - model: DewEfresh/neo_7b
        layer_range: [4, 4]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [5, 5]
      - model: DewEfresh/neo_7b
        layer_range: [5, 5]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [6, 6]
      - model: DewEfresh/neo_7b
        layer_range: [6, 6]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [7, 7]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  # Group 3
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [8, 8]
      - model: DewEfresh/neo_7b
        layer_range: [8, 8]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [9, 9]
      - model: DewEfresh/neo_7b
        layer_range: [9, 9]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [10, 10]
      - model: DewEfresh/neo_7b
        layer_range: [10, 10]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [11, 11]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  # Group 4
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [12, 12]
      - model: DewEfresh/neo_7b
        layer_range: [12, 12]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [13, 13]
      - model: DewEfresh/neo_7b
        layer_range: [13, 13]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [14, 14]
      - model: DewEfresh/neo_7b
        layer_range: [14, 14]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [15, 15]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  # Group 5
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [16, 16]
      - model: DewEfresh/neo_7b
        layer_range: [16, 16]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [17, 17]
      - model: DewEfresh/neo_7b
        layer_range: [17, 17]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [18, 18]
      - model: DewEfresh/neo_7b
        layer_range: [18, 18]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [19, 19]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  # Group 6
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [20, 20]
      - model: DewEfresh/neo_7b
        layer_range: [20, 20]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [21, 21]
      - model: DewEfresh/neo_7b
        layer_range: [21, 21]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [22, 22]
      - model: DewEfresh/neo_7b
        layer_range: [22, 22]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [23, 23]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  # Group 7 (last group)
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [24, 24]
      - model: DewEfresh/neo_7b
        layer_range: [24, 24]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [25, 25]
      - model: DewEfresh/neo_7b
        layer_range: [25, 25]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [26, 26]
      - model: DewEfresh/neo_7b
        layer_range: [26, 26]
  - sources:
      - model: m-a-p/neo_7b
        layer_range: [27, 27]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
merge_method: slerp
base_model: m-a-p/neo_7b
parameters:
  t: 0.5  # Equal weight to both models
dtype: bfloat16
output_path: ./merged_map_dewefresh_neo_7b

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DewEfresh/Neo_7b-merge5"
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"])