README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - mlabonne/OmniBeagle-7B
  - flemmingmiguel/MBX-7B-v3
  - AiMavenAi/AiMaven-Prometheus
base_model:
  - mlabonne/OmniBeagle-7B
  - flemmingmiguel/MBX-7B-v3
  - AiMavenAi/AiMaven-Prometheus
model-index:
  - name: NeuralTrix-7B-dpo
    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: 72.27
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/NeuralTrix-7B-dpo
          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: 88.91
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/NeuralTrix-7B-dpo
          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: 64.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/NeuralTrix-7B-dpo
          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: 79.06
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/NeuralTrix-7B-dpo
          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/NeuralTrix-7B-dpo
          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: 68.01
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=CultriX/NeuralTrix-7B-dpo
          name: Open LLM Leaderboard

Edit: Please see This Thread

NeuralTrix-7B-v1

NeuralTrix-7B-v1 is a merge of the following models using LazyMergekit:

• mlabonne/OmniBeagle-7B
• flemmingmiguel/MBX-7B-v3
• AiMavenAi/AiMaven-Prometheus

It was then trained with DPO using:

• https://huggingface.co./datasets/jondurbin/truthy-dpo-v0.1

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: mlabonne/OmniBeagle-7B
    parameters:
      density: 0.65
      weight: 0.4
  - model: flemmingmiguel/MBX-7B-v3
    parameters:
      density: 0.6
      weight: 0.35
  - model: AiMavenAi/AiMaven-Prometheus
    parameters:
      density: 0.6
      weight: 0.35
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "CultriX/NeuralTrix-7B-v1"
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)	72.27
HellaSwag (10-Shot)	88.91
MMLU (5-Shot)	64.06
TruthfulQA (0-shot)	79.06
Winogrande (5-shot)	84.61
GSM8k (5-shot)	68.01