gate369_-_Blurdus-7b-v0.1-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Blurdus-7b-v0.1 - GGUF

• Model creator: https://huggingface.co/gate369/
• Original model: https://huggingface.co/gate369/Blurdus-7b-v0.1/

Original model description:

license: apache-2.0 tags:

• merge
• mergekit
• lazymergekit
• 222gate/Blurred-Beagle-7b-slerp
• 222gate/BrurryDog-7b-v0.1
• liminerity/Blur-7b-v1.21 base_model:
• 222gate/Blurred-Beagle-7b-slerp
• 222gate/BrurryDog-7b-v0.1
• liminerity/Blur-7b-v1.21 model-index:
• name: Blurdus-7b-v0.1 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: 72.27 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=222gate/Blurdus-7b-v0.1 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: 88.5 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=222gate/Blurdus-7b-v0.1 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: 64.82 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=222gate/Blurdus-7b-v0.1 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: 69.72 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=222gate/Blurdus-7b-v0.1 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: 82.95 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=222gate/Blurdus-7b-v0.1 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: 67.85 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=222gate/Blurdus-7b-v0.1 name: Open LLM Leaderboard

---

Blurdus-7b-v0.1

Blurdus-7b-v0.1 is a merge of the following models using LazyMergekit:

• 222gate/Blurred-Beagle-7b-slerp
• 222gate/BrurryDog-7b-v0.1
• liminerity/Blur-7b-v1.21

🧩 Configuration

models:
  - model: 222gate/Blurred-Beagle-7b-slerp
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: 222gate/BrurryDog-7b-v0.1
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: liminerity/Blur-7b-v1.21
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: udkai/Turdus
parameters:
  normalize: true
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "222gate/Blurdus-7b-v0.1"
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