Blur-7b-v1.21/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
apache-2.0	merge mergekit lazymergekit udkai/Turdus decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP liminerity/Blur-7b-v1.2	udkai/Turdus decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP liminerity/Blur-7b-v1.2	name results Blur-7b-v1.21 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 70.82 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.21 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 88.07 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.21 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 64.85 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.21 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 67.99 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.21 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 83.82 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.21 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 69.52 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-v1.21 Open LLM Leaderboard

Blur-7b-v1.21

Blur-7b-v1.21 is a merge of the following models using LazyMergekit:

• udkai/Turdus
• decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
• liminerity/Blur-7b-v1.2

🧩 Configuration

models:
  - model: udkai/Turdus
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: liminerity/Blur-7b-v1.2
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: fblgit/UNA-TheBeagle-7b-v1
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-v1.21"
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.	74.18
AI2 Reasoning Challenge (25-Shot)	70.82
HellaSwag (10-Shot)	88.07
MMLU (5-Shot)	64.85
TruthfulQA (0-shot)	67.99
Winogrande (5-shot)	83.82
GSM8k (5-shot)	69.52