DareBeagel-2x7B/README.md

license, tags, model-index

license	tags	model-index
apache-2.0	moe merge mergekit lazymergekit mlabonne/NeuralBeagle14-7B mlabonne/NeuralDaredevil-7B	name results DareBeagel-2x7B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 72.01 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 88.12 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 64.51 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 69.09 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 82.72 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 70.51 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/DareBeagel-2x7B Open LLM Leaderboard

Beyonder-2x7B-v2

Beyonder-2x7B-v2 is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

• mlabonne/NeuralBeagle14-7B
• mlabonne/NeuralDaredevil-7B

🧩 Configuration

base_model: mlabonne/NeuralBeagle14-7B
gate_mode: random
experts:
  - source_model: mlabonne/NeuralBeagle14-7B
    positive_prompts: [""]
  - source_model: mlabonne/NeuralDaredevil-7B
    positive_prompts: [""]

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "shadowml/Beyonder-2x7B-v2"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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.	74.49
AI2 Reasoning Challenge (25-Shot)	72.01
HellaSwag (10-Shot)	88.12
MMLU (5-Shot)	64.51
TruthfulQA (0-shot)	69.09
Winogrande (5-shot)	82.72
GSM8k (5-shot)	70.51