Inv_-_Konstanta-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Konstanta-7B - GGUF

• Model creator: https://huggingface.co/Inv/
• Original model: https://huggingface.co/Inv/Konstanta-7B/

Original model description:

language:

• en license: apache-2.0 tags:
• merge
• mergekit
• lazymergekit
• maywell/PiVoT-0.1-Evil-a
• mlabonne/NeuralOmniBeagle-7B-v2
• roleplay
• rp
• not-for-all-audiences base_model:
• maywell/PiVoT-0.1-Evil-a
• mlabonne/NeuralOmniBeagle-7B-v2 model-index:
• name: Konstanta-7B 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: 70.05 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-7B 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: 87.5 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-7B 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: 65.06 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-7B 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: 65.43 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-7B 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: 82.16 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-7B 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: 71.04 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Inv/Konstanta-7B name: Open LLM Leaderboard

---

Konstanta-7B

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

• maywell/PiVoT-0.1-Evil-a
• mlabonne/NeuralOmniBeagle-7B-v2

This is a test merge that is supposed to improve Kunoichi by merging it with new Beagle model and PiVoT Evil, which both show good performance. Even though the model's name is in Russian, it is not really capable of properly using it, as it was not the main goal of the model.

🧩 Configuration

merge_method: dare_ties
dtype: bfloat16
parameters:
  int8_mask: true
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
models:
  - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
  - model: maywell/PiVoT-0.1-Evil-a
    parameters:
      density: 0.65
      weight: 0.15
  - model: mlabonne/NeuralOmniBeagle-7B-v2
    parameters:
      density: 0.85
      weight: 0.45

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Inv/Konstanta-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