Blur-7b-v1.22/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
apache-2.0	merge mergekit lazymergekit s3nh/Sonya-Panda-7B-slerp argilla/distilabeled-Marcoro14-7B-slerp Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp	s3nh/Sonya-Panda-7B-slerp argilla/distilabeled-Marcoro14-7B-slerp Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp	name results Blur-7b-v1.22 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 62.29 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22 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 82.0 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22 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 58.03 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22 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 68.01 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22 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 78.61 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22 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 31.16 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.22 Open LLM Leaderboard

Blur-7b-v1.22

Blur-7b-v1.22 is a merge of the following models using LazyMergekit:

• s3nh/Sonya-Panda-7B-slerp
• argilla/distilabeled-Marcoro14-7B-slerp
• Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp

🧩 Configuration

models:
  - model: s3nh/Sonya-Panda-7B-slerp
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: argilla/distilabeled-Marcoro14-7B-slerp
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: liminerity/Blur-7b-v1.21
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "liminerity/Blur-7b-v1.22"
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.	63.35
AI2 Reasoning Challenge (25-Shot)	62.29
HellaSwag (10-Shot)	82.00
MMLU (5-Shot)	58.03
TruthfulQA (0-shot)	68.01
Winogrande (5-shot)	78.61
GSM8k (5-shot)	31.16