license, tags, base_model, model-index

license	tags	base_model	model-index
apache-2.0	merge mergekit lazymergekit Gille/StrangeMerges_17-7B-dare_ties teknium/OpenHermes-2.5-Mistral-7B	Gille/StrangeMerges_17-7B-dare_ties teknium/OpenHermes-2.5-Mistral-7B	name results StrangeMerges_18-7B-dare_ties 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 64.08 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_18-7B-dare_ties 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 84.37 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_18-7B-dare_ties 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 63.65 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_18-7B-dare_ties 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 52.17 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_18-7B-dare_ties 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 77.27 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_18-7B-dare_ties 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 60.8 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_18-7B-dare_ties Open LLM Leaderboard

StrangeMerges_18-7B-dare_ties

StrangeMerges_18-7B-dare_ties is a merge of the following models using LazyMergekit:

• Gille/StrangeMerges_17-7B-dare_ties
• teknium/OpenHermes-2.5-Mistral-7B

🧩 Configuration

models:
  - model: Gille/StrangeMerges_17-7B-dare_ties
    # no parameters necessary for base model
  - model: Gille/StrangeMerges_17-7B-dare_ties
    parameters:
      density: 0.5
      weight: 0.4
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.6
merge_method: dare_ties
base_model: Gille/StrangeMerges_17-7B-dare_ties
parameters:
  normalize: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Gille/StrangeMerges_18-7B-dare_ties"
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.	67.06
AI2 Reasoning Challenge (25-Shot)	64.08
HellaSwag (10-Shot)	84.37
MMLU (5-Shot)	63.65
TruthfulQA (0-shot)	52.17
Winogrande (5-shot)	77.27
GSM8k (5-shot)	60.80