MonaTrix-v6 / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
49e222c verified
|
raw
history blame
5.19 kB
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - mlabonne/AlphaMonarch-7B
  - Kukedlc/NeuralMaxime-7B-slerp
  - bardsai/jaskier-7b-dpo-v5.6
base_model:
  - mlabonne/AlphaMonarch-7B
  - Kukedlc/NeuralMaxime-7B-slerp
  - bardsai/jaskier-7b-dpo-v5.6
model-index:
  - name: MonaTrix-v6
    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: 72.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/MonaTrix-v6
          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: 88.9
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/MonaTrix-v6
          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: 64.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/MonaTrix-v6
          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: 77.45
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/MonaTrix-v6
          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=CultriX/MonaTrix-v6
          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: 67.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/MonaTrix-v6
          name: Open LLM Leaderboard

MonaTrix-v6

MonaTrix-v6 is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: eren23/dpo-binarized-NeutrixOmnibe-7B
    # No parameters necessary for base model
  - model: mlabonne/AlphaMonarch-7B
    #Emphasize the beginning of Vicuna format models
    parameters:
      weight: 0.6
      density: 0.59
  - model: Kukedlc/NeuralMaxime-7B-slerp
    parameters:
      weight: 0.1
      density: 0.55
  # Vicuna format
  - model: bardsai/jaskier-7b-dpo-v5.6
    parameters:
      weight: 0.3
      density: 0.55

merge_method: dare_ties
base_model: eren23/dpo-binarized-NeutrixOmnibe-7B
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "CultriX/MonaTrix-v6"
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. 76.01
AI2 Reasoning Challenge (25-Shot) 72.78
HellaSwag (10-Shot) 88.90
MMLU (5-Shot) 64.45
TruthfulQA (0-shot) 77.45
Winogrande (5-shot) 84.61
GSM8k (5-shot) 67.85