LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Ninja V2 7B by Local-Novel-LLM-project

 ยป  All LLMs  ยป  Local-Novel-LLM-project  ยป  Ninja V2 7B   URL Share it on

  96   
  Autotrain compatible   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Local-Novel-LLM-project/Ninja-V2-7B 

Ninja V2 7B Benchmarks

LLME Score: 0.20428
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ninja V2 7B (Local-Novel-LLM-project/Ninja-V2-7B)

Ninja V2 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
general-purpose including chat and text creation
Applications:
Wide range of functions including chat and writing tasks
Primary Use Cases:
Text generation, chat applications
Training Details 
Methodology:
Creating combination models using a 'mergekit' and 'ninja_merger' with methods like 'sub','mix','add'. Consists of combining multiple pre-trained models.
Hardware Used:
High performance GPU server from LocalAI ใƒใƒƒใ‚ซใ‚ฝใƒณ
Input Output 
Input Format:
Vicuna-1.1 template can be used but is not mandatory
Performance Tips:
No preferred template for simple text generation.
LLM NameNinja V2 7B
Repository ๐Ÿค—https://huggingface.co/Local-Novel-LLM-project/Ninja-V2-7B 
Base Model(s)  Nina V2 7B   Virt-io/Nina-v2-7B
Model Size7b
Required VRAM14.4 GB
Updated2025-01-22
MaintainerLocal-Novel-LLM-project
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Quantization Typeq8|gguf
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Ninja V2 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB42589
MegaBeam Mistral 7B 512K512K / 14.4 GB528649
SpydazWeb AI HumanAI RP512K / 14.4 GB201
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB462215
Hebrew Mistral 7B 200K256K / 30 GB273515
Astral 256K 7B250K / 14.4 GB120
Astral 256K 7B V2250K / 14.4 GB90
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than Local-Novel-LLM-project/Ninja-V2-7B.

Rank the Ninja V2 7B Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 41728 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer