TIPO 500M by KBlueLeaf

 ยป  All LLMs  ยป  KBlueLeaf  ยป  TIPO 500M   URL Share it on

  Arxiv:2411.08127   Autotrain compatible Dataset:captionemporium/coyo-h... Dataset:graph-based-captions/g... Dataset:kblueleaf/danbooru2023... Dataset:laion/conceptual-capti...   En   Endpoints compatible   Gguf   Llama   Quantized   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/KBlueLeaf/TIPO-500M 

TIPO 500M Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TIPO 500M (KBlueLeaf/TIPO-500M)

TIPO 500M Parameters and Internals

Model Type 
text-to-image
Supported Languages 
en (full)
Training Details 
Data Sources:
laion/conceptual-captions-12m-webdataset, CaptionEmporium/coyo-hd-11m-llavanext, KBlueLeaf/danbooru2023-metadata-database, graph-based-captions/GBC10M
Data Volume:
30B tokens
Context Length:
1024
Training Time:
100 hours
Hardware Used:
H100 x 8
Model Architecture:
LLaMA
Input Output 
Accepted Modalities:
text
Output Format:
image
LLM NameTIPO 500M
Repository ๐Ÿค—https://huggingface.co/KBlueLeaf/TIPO-500M 
Model Size500m
Required VRAM1 GB
Updated2024-12-22
MaintainerKBlueLeaf
Model Typellama
Model Files  1.0 GB   2.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32013
Torch Data Typefloat32

Best Alternatives to TIPO 500M

Best Alternatives
Context / RAM
Downloads
Likes
Text Arco8K / 1 GB1710
H2o Danube3 500M Chat8K / 1 GB620932
H2o Danube3 500M Base8K / 1 GB274728
Arco Plus8K / 1.6 GB1376
Danube Reasoner8K / 1 GB270
Clite 500M8K / 1 GB703
Massive8K / 1 GB650
APT3 500M Base2K / 1.9 GB5063
...ama 1.1B Textsql 500B 16layers2K / 2.2 GB00

Rank the TIPO 500M 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217