merged-dpo-binarized-NeutrixOmnibe-7B/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
apache-2.0	merge mergekit lazymergekit eren23/dpo-binarized-NeutrixOmnibe-7B Kukedlc/NeuTrixOmniBe-7B-model-remix	eren23/dpo-binarized-NeutrixOmnibe-7B Kukedlc/NeuTrixOmniBe-7B-model-remix	name results merged-dpo-binarized-NeutrixOmnibe-7B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 72.7 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 89.03 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 64.59 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 76.9 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 85.08 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 68.92 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B Open LLM Leaderboard

merged-dpo-binarized-NeutrixOmnibe-7B

merged-dpo-binarized-NeutrixOmnibe-7B is a merge of the following models using LazyMergekit:

• eren23/dpo-binarized-NeutrixOmnibe-7B
• Kukedlc/NeuTrixOmniBe-7B-model-remix

🧩 Configuration

slices:
  - sources:
      - model: eren23/dpo-binarized-NeutrixOmnibe-7B
        layer_range: [0, 32]
      - model: Kukedlc/NeuTrixOmniBe-7B-model-remix
        layer_range: [0, 32]
merge_method: slerp
base_model: eren23/dpo-binarized-NeutrixOmnibe-7B
parameters:
  t:
    - filter: self_attn
      value: [0.2, 0.7, 0.8, 0.7, 1]
    - filter: mlp
      value: [0.8, 0.3, 0.2, 0.3, 0]
    - value: 0.45
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "eren23/merged-dpo-binarized-NeutrixOmnibe-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.	76.20
AI2 Reasoning Challenge (25-Shot)	72.70
HellaSwag (10-Shot)	89.03
MMLU (5-Shot)	64.59
TruthfulQA (0-shot)	76.90
Winogrande (5-shot)	85.08
GSM8k (5-shot)	68.92