NeuralMonarch-7B / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
87b57ba verified
|
raw
history blame
9.71 kB
metadata
language:
  - en
license: cc-by-nc-4.0
tags:
  - merge
  - lazymergekit
  - dpo
  - rlhf
dataset:
  - mlabonne/truthy-dpo-v0.1
  - mlabonne/distilabel-intel-orca-dpo-pairs
base_model:
  - mlabonne/Monarch-7B
model-index:
  - name: NeuralMonarch-7B
    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: 73.21
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
          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: 89.09
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
          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: 64.41
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
          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: 77.79
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
          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: 84.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
          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: 67.78
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
          name: Open LLM Leaderboard

image/jpeg

πŸ‘‘ NeuralMonarch-7B

NeuralMonarch-7B is a DPO fine-tuned of mlabonne/Monarch-7B using the jondurbin/truthy-dpo-v0.1 and argilla/distilabel-intel-orca-dpo-pairs preference datasets.

It is based on a merge of the following models using LazyMergekit:

Special thanks to Jon Durbin, Intel, and Argilla for the preference datasets.

Try the demo: https://huggingface.co/spaces/mlabonne/NeuralMonarch-7B-GGUF-Chat

πŸ” Applications

This model uses a context window of 8k. I recommend using it with the Mistral Instruct chat template (works perfectly with LM Studio).

Compared to other 7B models, it performs well in instruction following and reasoning tasks. For a chat/RP model with strong reasoning abilities, check out mlabonne/AlphaMonarch-7B.

⚑ Quantized models

πŸ† Evaluation

Nous

NeuralMonarch-7B is one of the best-performing 7B models on Nous' benchmark suite (evaluation performed using LLM AutoEval). See the entire leaderboard here.

Model Average AGIEval GPT4All TruthfulQA Bigbench
NeuralMonarch-7B πŸ“„ 62.73 45.31 76.99 78.35 50.28
AlphaMonarch-7B πŸ“„ 62.74 45.37 77.01 78.39 50.2
Monarch-7B πŸ“„ 62.68 45.48 77.07 78.04 50.14
teknium/OpenHermes-2.5-Mistral-7B πŸ“„ 52.42 42.75 72.99 52.99 40.94
mlabonne/NeuralHermes-2.5-Mistral-7B πŸ“„ 53.51 43.67 73.24 55.37 41.76
mlabonne/NeuralBeagle14-7B πŸ“„ 60.25 46.06 76.77 70.32 47.86
mlabonne/NeuralOmniBeagle-7B πŸ“„ 62.3 45.85 77.26 76.06 50.03
eren23/dpo-binarized-NeuralTrix-7B πŸ“„ 62.5 44.57 76.34 79.81 49.27
CultriX/NeuralTrix-7B-dpo πŸ“„ 62.5 44.61 76.33 79.8 49.24

EQ-bench

NeuralMonarch-7B is also outperforming 70B and 120B parameter models on EQ-bench by Samuel J. Paech, who kindly ran the evaluations.

image/png

Open LLM Leaderboard

NeuralMonarch-7B is one of the best-performing 7B models on the Open LLM Leaderboard.

MT-Bench

########## First turn ##########
                                    score
model                       turn         
gpt-4                       1     8.95625
OmniBeagle-7B               1     8.31250
AlphaMonarch-7B             1     8.23750
claude-v1                   1     8.15000
NeuralMonarch-7B            1     8.09375
gpt-3.5-turbo               1     8.07500
claude-instant-v1           1     7.80000

########## Second turn ##########
                                     score
model                       turn          
gpt-4                       2     9.025000
claude-instant-v1           2     8.012658
OmniBeagle-7B               2     7.837500
gpt-3.5-turbo               2     7.812500
claude-v1                   2     7.650000
AlphaMonarch-7B             2     7.618750
NeuralMonarch-7B            2     7.375000

########## Average ##########
                                score
model                                
gpt-4                        8.990625
OmniBeagle-7B                8.075000
gpt-3.5-turbo                7.943750
AlphaMonarch-7B              7.928125
claude-instant-v1            7.905660
claude-v1                    7.900000
NeuralMonarch-7B             7.734375
NeuralBeagle14-7B            7.628125

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/NeuralMonarch-7B"
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. 76.15
AI2 Reasoning Challenge (25-Shot) 73.21
HellaSwag (10-Shot) 89.09
MMLU (5-Shot) 64.41
TruthfulQA (0-shot) 77.79
Winogrande (5-shot) 84.61
GSM8k (5-shot) 67.78