Molmo 7B O 0924 by allenai

 ยป  All LLMs  ยป  allenai  ยป  Molmo 7B O 0924   URL Share it on

  Arxiv:2409.17146   Autotrain compatible Base model:finetune:openai/cli... Base model:openai/clip-vit-lar...   Conversational   Custom code   En   Image-text-to-text   Molmo   Multimodal   Olmo   Pixmo   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/allenai/Molmo-7B-O-0924 

Molmo 7B O 0924 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Molmo 7B O 0924 (allenai/Molmo-7B-O-0924)

Molmo 7B O 0924 Parameters and Internals

Model Type 
multimodal, image-text-to-text
Use Cases 
Areas:
research, educational applications
Limitations:
struggles with transparent images
Additional Notes 
Checkpoint is a preview of the Molmo release. All artifacts used in the creation will be made available later.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
PixMo dataset, containing 1 million highly-curated image-text pairs
Data Volume:
1 million image-text pairs
Methodology:
Based on OLMo-7B-1124 and OpenAI CLIP
Input Output 
Input Format:
Image input via PIL image object, text via a string
Accepted Modalities:
image, text
Output Format:
Generated text from image and text input
Performance Tips:
Convert images to RGB format and handle transparent images with a background
LLM NameMolmo 7B O 0924
Repository ๐Ÿค—https://huggingface.co/allenai/Molmo-7B-O-0924 
Base Model(s)  openai/clip-vit-large-patch14-336   allenai/OLMo-7B-1124   openai/clip-vit-large-patch14-336   allenai/OLMo-7B-1124
Model Size7b
Required VRAM30.9 GB
Updated2024-12-21
Maintainerallenai
Model Typemolmo
Model Files  5.0 GB: 1-of-7   4.9 GB: 2-of-7   4.9 GB: 3-of-7   4.9 GB: 4-of-7   4.9 GB: 5-of-7   5.0 GB: 6-of-7   1.3 GB: 7-of-7
Supported Languagesen
Model ArchitectureMolmoForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.43.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100278
Torch Data Typefloat32

Quantized Models of the Molmo 7B O 0924

Model
Likes
Downloads
VRAM
Molmo 7B O Bnb 4bit86916 GB

Best Alternatives to Molmo 7B O 0924

Best Alternatives
Context / RAM
Downloads
Likes
Molmo 7B D 09244K / 32.2 GB226279459
Molmo 7B D Bnb 4bit4K / 7.9 GB434615
Molmo 7B O Bnb 4bit4K / 6.8 GB6918
Note: green Score (e.g. "73.2") means that the model is better than allenai/Molmo-7B-O-0924.

Rank the Molmo 7B O 0924 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? 40013 in total.

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