README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - senseable/Westlake-7B-v2
  - decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
  - mlabonne/NeuralMarcoro14-7B
base_model:
  - senseable/Westlake-7B-v2
  - decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
  - mlabonne/NeuralMarcoro14-7B
model-index:
  - name: WestOrcaNeuralMarco-DPO-v2-DARETIES-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: 71.93
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-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: 88.06
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-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: 64.99
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-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: 65.96
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-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: 82.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-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: 70.13
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-7B
          name: Open LLM Leaderboard

WestOrcaNeuralMarco-DPO-v2-DARETIES-7B

WestOrcaNeuralMarco-DPO-v2-DARETIES-7B is a merge of the following models using LazyMergekit:

• senseable/Westlake-7B-v2
• decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
• mlabonne/NeuralMarcoro14-7B

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: senseable/Westlake-7B-v2
    parameters:
      density: 0.73
      weight: 0.4
  - model: decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
    parameters:
      density: 0.55
      weight: 0.3
  - model: mlabonne/NeuralMarcoro14-7B  
    parameters:
      density: 0.45
      weight: 0.3  
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-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.	73.98
AI2 Reasoning Challenge (25-Shot)	71.93
HellaSwag (10-Shot)	88.06
MMLU (5-Shot)	64.99
TruthfulQA (0-shot)	65.96
Winogrande (5-shot)	82.79
GSM8k (5-shot)	70.13