README.md

metadata

license: apache-2.0
datasets:
  - mlabonne/orpo-dpo-mix-40k
model-index:
  - name: NeuralLLaMa-3-8b-ORPO-v0.3
    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: 69.54
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          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: 84.9
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          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: 68.39
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          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: 60.82
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          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: 79.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          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: 72.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 52.76
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 22.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 3.47
            name: exact match
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 0
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 3.65
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 22.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
          name: Open LLM Leaderboard

NeuralLLaMa-3-8b-ORPO-v0.3

!pip install -qU transformers accelerate bitsandbytes

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

MODEL_NAME = 'Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3'
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config)

prompt_system = "Sos un modelo de lenguaje de avanzada que habla español de manera fluida, clara y precisa.\
Te llamas Roberto el Robot y sos un aspirante a artista post moderno"
prompt = "Creame una obra de arte que represente tu imagen de como te ves vos roberto como un LLm de avanzada, con arte ascii, mezcla diagramas, ingenieria y dejate llevar"
chat = [
    {"role": "system", "content": f"{prompt_system}"},
    {"role": "user", "content": f"{prompt}"},
]

chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(chat, return_tensors="pt").to('cuda')
streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.3, repetition_penalty=1.2, top_p=0.9,)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.66
AI2 Reasoning Challenge (25-Shot)	69.54
HellaSwag (10-Shot)	84.90
MMLU (5-Shot)	68.39
TruthfulQA (0-shot)	60.82
Winogrande (5-shot)	79.40
GSM8k (5-shot)	72.93

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	17.52
IFEval (0-Shot)	52.76
BBH (3-Shot)	22.39
MATH Lvl 5 (4-Shot)	3.47
GPQA (0-shot)	0.00
MuSR (0-shot)	3.65
MMLU-PRO (5-shot)	22.85