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

Llava NousResearch Nous Hermes 2 Vision GGUF by billborkowski

 »  All LLMs  »  billborkowski  »  Llava NousResearch Nous Hermes 2 Vision GGUF   URL Share it on

  2066   
  Autotrain compatible Base model:mistralai/mistral-7... Base model:quantized:mistralai...   Chatml   Conversational   Distillation   En   Endpoints compatible   Finetuned   Gguf   Gpt4   Instruct   Llava   Llava mistral   Mistral   Multimodal   Pytorch   Q4   Quantized   Region:us   Sharded   Synthetic data   Vision
Model Card on HF 🤗: https://huggingface.co/billborkowski/llava-NousResearch_Nous-Hermes-2-Vision-GGUF 

Llava NousResearch Nous Hermes 2 Vision GGUF Benchmarks

LLME Score: 0.18259
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llava NousResearch Nous Hermes 2 Vision GGUF (billborkowski/llava-NousResearch_Nous-Hermes-2-Vision-GGUF)

Llava NousResearch Nous Hermes 2 Vision GGUF Parameters and Internals

Model Type 
Vision-Language Model, Vision-Language Action Model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Vision-language applications, Automations through function calling
Primary Use Cases:
Image understanding, Extracting information from images, Interactive vision-language tasks
Additional Notes 
It's noted there may still be a bug in the inference process that may be fixed upstream.
Supported Languages 
en (high)
Training Details 
Data Sources:
LVIS-INSTRUCT4V, ShareGPT4V, Private Function Calling Data, OpenHermes-2.5
Data Volume:
220K from LVIS-INSTRUCT4V, 60K from ShareGPT4V, 150K Private Function Calling Data, 50K conversations from OpenHermes-2.5
Methodology:
Custom Dataset Enriched with Function Calling
Model Architecture:
Uses SigLIP-400M for Vision and incorporates function calling.
Input Output 
Input Format:
Uses Vicuna-V1 prompt template.
Accepted Modalities:
text, image
Output Format:
JSON output for function calling
LLM NameLlava NousResearch Nous Hermes 2 Vision GGUF
Repository 🤗https://huggingface.co/billborkowski/llava-NousResearch_Nous-Hermes-2-Vision-GGUF 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM15.3 GB
Updated2025-02-22
Maintainerbillborkowski
Model Typellava_mistral
Model Files  4.1 GB   0.0 GB   0.8 GB   9.9 GB: 1-of-2   5.4 GB: 2-of-2   0.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q4
Model ArchitectureLlavaMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Llava NousResearch Nous Hermes 2 Vision GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Candle Llava V1.6 Mistral 7B32K / 15.1 GB700
Llava V1.6 Mistral 7B Bnb 4bit32K / 4.6 GB500
Llava V1.6 Mistral 7B32K / 15.1 GB44465234
Turkish BakLLaVa1.5 Mistral32K / 15.3 GB235
Llava Model32K / 15.1 GB60
Fc24 Mk332K / 20.6 GB60
Fc24 Mk232K / 20.6 GB80
CuMo Mistral 7B32K / 16.5 GB4415
Llava Mistral 7B Finetuned32K / 15.1 GB72
LLaVA NeXT Video 7B 32K32K / 15.1 GB477
Note: green Score (e.g. "73.2") means that the model is better than billborkowski/llava-NousResearch_Nous-Hermes-2-Vision-GGUF.

Rank the Llava NousResearch Nous Hermes 2 Vision GGUF Capabilities

🆘 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! 🌟

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? 43470 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