merge-llama-3-8b

merge-llama-3-8b

merge-llama-3-8b is a merge of the following models using LazyMergekit:

• catrinbaze/llama-refueled-merge
• NousResearch/Meta-Llama-3-8B-instruct
• Locutusque/Llama-3-Orca-1.0-8B
• lighteternal/Llama3-merge-biomed-8b
• mlabonne/NeuralDaredevil-8B-abliterated
• mlabonne/Daredevil-8B

🧩 Configuration

slices:
models:
  - model: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: catrinbaze/llama-refueled-merge
    parameters:
      density: 0.6
      weight: 0.6
  - model: NousResearch/Meta-Llama-3-8B-instruct
    parameters:
      density: 0.58
      weight: 0.2
  - model: Locutusque/Llama-3-Orca-1.0-8B
    parameters:
      density: 0.56
      weight: 0.05
  - model: lighteternal/Llama3-merge-biomed-8b 
    parameters:
      density: 0.56
      weight: 0.05
  - model: mlabonne/NeuralDaredevil-8B-abliterated
    parameters:
      density: 0.55
      weight: 0.05
  - model: mlabonne/Daredevil-8B
    parameters:
      density: 0.55
      weight: 0.05
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "catrinbaze/merge-llama-3-8b"
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"])