llama-3-luminous-merged

llama-3-luminous-merged is a merge of the following models using LazyMergekit:

• nbeerbower/llama-3-stella-8B
• defog/llama-3-sqlcoder-8b
• nbeerbower/llama-3-gutenberg-8B
• openchat/openchat-3.6-8b-20240522
• Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
• cstr/llama3-8b-spaetzle-v20
• mlabonne/ChimeraLlama-3-8B-v3
• flammenai/Mahou-1.1-llama3-8B
• KingNish/KingNish-Llama3-8b

🧩 Configuration

models:
  - model: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: nbeerbower/llama-3-stella-8B
    parameters:
      density: 0.6
      weight: 0.16
  - model: defog/llama-3-sqlcoder-8b
    parameters:
      density: 0.56
      weight: 0.1
  - model: nbeerbower/llama-3-gutenberg-8B
    parameters:
      density: 0.6
      weight: 0.18
  - model: openchat/openchat-3.6-8b-20240522
    parameters:
      density: 0.56
      weight: 0.13
  - model: Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
    parameters:
      density: 0.58
      weight: 0.18
  - model: cstr/llama3-8b-spaetzle-v20
    parameters:
      density: 0.56
      weight: 0.08
  - model: mlabonne/ChimeraLlama-3-8B-v3
    parameters:
      density: 0.56
      weight: 0.07
  - model: flammenai/Mahou-1.1-llama3-8B
    parameters:
      density: 0.55
      weight: 0.05
  - model: KingNish/KingNish-Llama3-8b
    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 = "BlackBeenie/llama-3-luminous-merged"
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.48
IFEval (0-Shot)	43.23
BBH (3-Shot)	30.64
MATH Lvl 5 (4-Shot)	7.85
GPQA (0-shot)	5.70
MuSR (0-shot)	10.63
MMLU-PRO (5-shot)	30.81