metadata

license: other
tags:
  - merge
  - mergekit
  - lazymergekit
base_model:
  - NousResearch/Meta-Llama-3-8B-Instruct
  - mlabonne/OrpoLlama-3-8B
  - cognitivecomputations/dolphin-2.9-llama3-8b
  - Danielbrdz/Barcenas-Llama3-8b-ORPO
  - VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
  - vicgalle/Configurable-Llama-3-8B-v0.3
  - MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
model-index:
  - name: ChimeraLlama-3-8B-v3
    results:
      - 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: 44.08
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
          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: 27.65
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
          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: 7.85
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
          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: 5.59
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
          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: 8.38
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
          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: 29.65
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/ChimeraLlama-3-8B-v3
          name: Open LLM Leaderboard

ChimeraLlama-3-8B-v3

ChimeraLlama-3-8B-v3 is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: NousResearch/Meta-Llama-3-8B
    # No parameters necessary for base model
  - model: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      density: 0.6
      weight: 0.5
  - model: mlabonne/OrpoLlama-3-8B
    parameters:
      density: 0.55
      weight: 0.05
  - model: cognitivecomputations/dolphin-2.9-llama3-8b
    parameters:
      density: 0.55
      weight: 0.05
  - model: Danielbrdz/Barcenas-Llama3-8b-ORPO
    parameters:
      density: 0.55
      weight: 0.2
  - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
    parameters:
      density: 0.55
      weight: 0.1
  - model: vicgalle/Configurable-Llama-3-8B-v0.3
    parameters:
      density: 0.55
      weight: 0.05
  - model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
    parameters:
      density: 0.55
      weight: 0.05
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/ChimeraLlama-3-8B-v3"
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.	20.53
IFEval (0-Shot)	44.08
BBH (3-Shot)	27.65
MATH Lvl 5 (4-Shot)	7.85
GPQA (0-shot)	5.59
MuSR (0-shot)	8.38
MMLU-PRO (5-shot)	29.65