README.md

metadata

license: cc-by-nc-4.0
tags:
  - moe
model-index:
  - name: Brunhilde-2x7b-MOE-DPO-v.01.5
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 69.54
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 87.02
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 65.47
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 80.9
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5
          name: Open LLM Leaderboard

Brunhilde-2x7b-MOE-DPO-v.01.5

Brunhilde-2x7b-MOE-DPO-v.01.5 is a Mixure of Experts (MoE).

• NurtureAI/neural-chat-7b-v3-16k
• mncai/mistral-7b-dpo-v6

Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "arlineka/Brunhilde-2x7b-MOE-DPO-v.01.5"

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.	71.81
AI2 Reasoning Challenge (25-Shot)	69.54
HellaSwag (10-Shot)	87.02
MMLU (5-Shot)	64.93
TruthfulQA (0-shot)	65.47
Winogrande (5-shot)	80.90
GSM8k (5-shot)	63.00