metadata

license: apache-2.0
tags:
  - legal
  - chemistry
  - medical
  - text-generation-inference
  - art
pipeline_tag: text-generation
model-index:
  - name: Nidum-Limitless-Gemma-2B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 24.24
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nidum/Nidum-Limitless-Gemma-2B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 3.45
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nidum/Nidum-Limitless-Gemma-2B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 0
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nidum/Nidum-Limitless-Gemma-2B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 1.9
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nidum/Nidum-Limitless-Gemma-2B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 4.12
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nidum/Nidum-Limitless-Gemma-2B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 1.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nidum/Nidum-Limitless-Gemma-2B
          name: Open LLM Leaderboard

Nidum-Limitless-Gemma-2B LLM

Welcome to the repository for Nidum-Limitless-Gemma-2B, an advanced language model that provides unrestricted and versatile responses across a wide range of topics. Unlike conventional models, Nidum-Limitless-Gemma-2B is designed to handle any type of question and deliver comprehensive answers without content restrictions.

Key Features:

Unrestricted Responses: Address any query with detailed, unrestricted responses, providing a broad spectrum of information and insights.
Versatility: Capable of engaging with a diverse range of topics, from complex scientific questions to casual conversation.
Advanced Understanding: Leverages a vast knowledge base to deliver contextually relevant and accurate outputs across various domains.
Customizability: Adaptable to specific user needs and preferences for different types of interactions.

Use Cases:

Open-Ended Q&A
Creative Writing and Ideation
Research Assistance
Educational and Informational Queries
Casual Conversations and Entertainment

How to Use:

To get started with Nidum-Limitless-Gemma-2B, you can use the following sample code for testing:

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="nidum/Nidum-Limitless-Gemma-2B",
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="cuda",  # replace with "mps" to run on a Mac device
)

messages = [
    {"role": "user", "content": "who are you"},
]

outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)

Release Date:

Nidum-Limitless-Gemma-2B is now officially available. Explore its capabilities and experience the freedom of unrestricted responses.

Contributing:

We welcome contributions to enhance the model or expand its functionalities. Details on how to contribute will be available in the coming updates.

Quantized Model Versions

To accommodate different hardware configurations and performance needs, Nidum-Limitless-Gemma-2B-GGUF is available in multiple quantized versions:

Model Version	Description
Nidum-Limitless-Gemma-2B-Q2_K.gguf	Optimized for minimal memory usage with lower precision. Suitable for resource-constrained environments.
Nidum-Limitless-Gemma-2B-Q4_K_M.gguf	Balances performance and precision, offering faster inference with moderate memory usage.
Nidum-Limitless-Gemma-2B-Q8_0.gguf	Provides higher precision with increased memory usage, suitable for tasks requiring more accuracy.
Nidum-Limitless-Gemma-2B-F16.gguf	Full 16-bit floating point precision for maximum accuracy, ideal for high-end GPUs.

It is available here: https://huggingface.co/nidum/Nidum-Limitless-Gemma-2B-GGUF

Contact:

For any inquiries or further information, please contact us at info@nidum.ai.

Dive into limitless possibilities with Nidum-Limitless-Gemma-2B!

Special Thanks to @cognitivecomputations for inspiring us and scouting the best datasets that we could round up to make a rockstar model for you

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	5.94
IFEval (0-Shot)	24.24
BBH (3-Shot)	3.45
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	1.90
MuSR (0-shot)	4.12
MMLU-PRO (5-shot)	1.93