Edit model card

osllm.ai Models Highlights Program

We believe there's no need to pay a token if you have a GPU on your computer.

Highlighting new and noteworthy models from the community. Join the conversation on Discord.

Model creator: Llama-3.2-11B-Vision-Instruct-bnb-4bit

Original model: Meta LLAMA 3.2

Official WebsiteDocumentationDiscord

NEW: Subscribe to our mailing list for updates and news!

Email: [email protected]

Acknowledgments
Our sincere gratitude to the Meta and Llama teams for their efforts in developing and releasing these models.

Model Overview
The Meta Llama 3.2 collection features multilingual large language models (LLMs), available in 1B and 3B sizes, with capabilities in both text input and output. The instruction-tuned Llama 3.2 models are optimized for multilingual dialogue, excelling in agentic retrieval and summarization tasks. They demonstrate superior performance on standard industry benchmarks compared to many open-source and closed chat models.

  • Developer: Meta
  • Architecture: Llama 3.2 is an auto-regressive language model utilizing an optimized transformer structure. Its tuned versions employ supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
  • Supported Languages: Officially supported languages include English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Llama 3.2 has been trained on a wider array of languages, and developers may further fine-tune the model for additional languages, subject to the Llama 3.2 Community License and Acceptable Use Policy. Responsible and safe deployment practices are required.
  • Token Counts: Token references pertain solely to pretraining data. All versions employ Grouped-Query Attention (GQA) to enhance inference scalability.

Release Information

  • Release Date: September 25, 2024
  • Status: This is a static model based on an offline dataset. Future updates may further enhance model performance and safety.
  • License: Llama 3.2 usage is governed by the Llama 3.2 Community License, a custom commercial license agreement.

Feedback and Further Information
For questions or feedback regarding Llama 3.2, please refer to the model README. Additional technical details and guidance on generation parameters, as well as usage recipes, can be found here.

Disclaimers

osllm.ai is not the creator, originator, or owner of any Model featured in the Community Model Program.
Each Community Model is created and provided by third parties. osllm.ai does not endorse, support, represent,
or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand
that Community Models can produce content that might be offensive, harmful, inaccurate, or otherwise
inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who
originated such Model. osllm.ai may not monitor or control the Community Models and cannot, and does not, take
responsibility for any such Model. osllm.ai disclaims all warranties or guarantees about the accuracy,
reliability, or benefits of the Community Models. osllm.ai further disclaims any warranty that the Community
Model will meet your requirements, be secure, uninterrupted, or available at any time or location, or
error-free, virus-free, or that any errors will be corrected, or otherwise. You will be solely responsible for
any damage resulting from your use of or access to the Community Models, your downloading of any Community
Model, or use of any other Community Model provided by or through osllm.ai.

Downloads last month
7
Safetensors
Model size
6.05B params
Tensor type
F32
·
BF16
·
U8
·
Inference Examples
Inference API (serverless) does not yet support transformers models for this pipeline type.

Collection including osllmai-community/Llama-3.2-11B-Vision-Instruct-bnb-4bit