README.md

metadata

license: mit
model-index:
  - name: NeuralHermes-2.5-Mistral-7B-distilabel
    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: 65.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel
          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: 84.97
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel
          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: 63.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel
          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: 55.86
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel
          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: 78.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel
          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: 61.49
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel
          name: Open LLM Leaderboard

Experiment with distilabel:

dataset = load_dataset("argilla/distilabel-intel-orca-dpo-pairs", split="train", token=hf_token)
dataset = dataset.filter(lambda r: r["status"]!="tie" and r["chosen_score"]>5)

def chatml_format(example):
    # Format system
    if len(example['system']) > 0:
        message = {"role": "system", "content": example['system']}
        system = tokenizer.apply_chat_template([message], tokenize=False)
    else:
        system = ""

    # Format instruction
    message = {"role": "user", "content": example['input']}
    prompt = tokenizer.apply_chat_template([message], tokenize=False, add_generation_prompt=True)

    # Format chosen answer
    chosen = example['chosen'] + "<|im_end|>\n"

    # Format rejected answer
    rejected = example['rejected'] + "<|im_end|>\n"

    return {
        "prompt": system + prompt,
        "chosen": chosen,
        "rejected": rejected,
    }

# Load dataset
#dataset = load_dataset("Intel/orca_dpo_pairs")['train']

# Save columns
original_columns = dataset.column_names

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "left"

# Format dataset
dataset = dataset.map(
    chatml_format,
    remove_columns=original_columns
)

# Print sample
dataset[1]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.40
AI2 Reasoning Challenge (25-Shot)	65.78
HellaSwag (10-Shot)	84.97
MMLU (5-Shot)	63.63
TruthfulQA (0-shot)	55.86
Winogrande (5-shot)	78.69
GSM8k (5-shot)	61.49