RichardErkhov/mlabonne_-_NeuralDarewin-7B-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NeuralDarewin-7B - bnb 8bits

• Model creator: https://huggingface.co/mlabonne/
• Original model: https://huggingface.co/mlabonne/NeuralDarewin-7B/

Original model description:

license: apache-2.0 model-index: - name: NeuralDarewin-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: 70.14 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDarewin-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: 86.4 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDarewin-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: 64.85 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDarewin-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: 62.92 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDarewin-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: 79.72 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDarewin-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: 66.72 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDarewin-7B name: Open LLM Leaderboard

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

• Intel/neural-chat-7b-v3-3
• openaccess-ai-collective/DPOpenHermes-7B-v2
• fblgit/una-cybertron-7b-v2-bf16
• openchat/openchat-3.5-0106
• OpenPipe/mistral-ft-optimized-1227
• mlabonne/NeuralHermes-2.5-Mistral-7B

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: Intel/neural-chat-7b-v3-3
    parameters:
      density: 0.6
      weight: 0.2
  - model: openaccess-ai-collective/DPOpenHermes-7B-v2
    parameters:
      density: 0.6
      weight: 0.1
  - model: fblgit/una-cybertron-7b-v2-bf16
    parameters:
      density: 0.6
      weight: 0.2
  - model: openchat/openchat-3.5-0106
    parameters:
      density: 0.6
      weight: 0.15
  - model: OpenPipe/mistral-ft-optimized-1227
    parameters:
      density: 0.6
      weight: 0.25
  - model: mlabonne/NeuralHermes-2.5-Mistral-7B
    parameters:
      density: 0.6
      weight: 0.1
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 = "mlabonne/NeuralDarewin-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.	71.79
AI2 Reasoning Challenge (25-Shot)	70.14
HellaSwag (10-Shot)	86.40
MMLU (5-Shot)	64.85
TruthfulQA (0-shot)	62.92
Winogrande (5-shot)	79.72
GSM8k (5-shot)	66.72