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

Llava 7B V0 4bit 128g by wojtab

 »  All LLMs  »  wojtab  »  Llava 7B V0 4bit 128g   URL Share it on

  31   
  4bit   Autotrain compatible   Endpoints compatible   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/wojtab/llava-7b-v0-4bit-128g 

Llava 7B V0 4bit 128g Benchmarks

LLME Score: 0.10561
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llava 7B V0 4bit 128g (wojtab/llava-7b-v0-4bit-128g)

Llava 7B V0 4bit 128g Parameters and Internals

Model Type 
quantized, multimodal
Additional Notes 
Quantized using GPTQ for LLama CUDA branch with 4-bit precision and group size of 128.
LLM NameLlava 7B V0 4bit 128g
Repository 🤗https://huggingface.co/wojtab/llava-7b-v0-4bit-128g 
Model Size7b
Required VRAM4 GB
Updated2024-12-22
Maintainerwojtab
Model Typellama
Model Files  4.0 GB
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseother
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32004
Torch Data Typefloat16

Best Alternatives to Llava 7B V0 4bit 128g

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 6.0bpw H6 EXL2195K / 26.4 GB144
Smaugv0.1 5.0bpw H6 EXL2195K / 22.3 GB143
Smaugv0.1 4.0bpw H6 EXL2195K / 18 GB181
Smaugv0.1 8.0bpw H8 EXL2195K / 34.9 GB151
Smaugv0.1 3.0bpw H6 EXL2195K / 13.9 GB141
Smaugv0.1 4.65bpw H6 EXL2195K / 20.8 GB141
Mistral 7B A U0.5 B2 Ver0.432K / 14.4 GB48570
Mistral 7B OP U1k Ver0.632K / 14.4 GB48510
Mistral 7B Openplatypus 1K32K / 29 GB11560
Mistral 7B OpenOrca 1K32K / 29 GB11533
Note: green Score (e.g. "73.2") means that the model is better than wojtab/llava-7b-v0-4bit-128g.

Rank the Llava 7B V0 4bit 128g 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? 40066 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 v20241217
  Support LLM Explorer