2.1 KiB
Open-Llama
This model is in maintenance mode only, we don't accept any new PRs changing its code.
If you run into any issues running this model, please reinstall the last version that supported this model: v4.31.0.
You can do so by running the following command: pip install -U transformers==4.31.0.
This model differs from the OpenLLaMA models on the Hugging Face Hub, which primarily use the LLaMA architecture.
Overview
The Open-Llama model was proposed in the open source Open-Llama project by community developer s-JoL.
The model is mainly based on LLaMA with some modifications, incorporating memory-efficient attention from Xformers, stable embedding from Bloom, and shared input-output embedding from PaLM. And the model is pre-trained on both Chinese and English, which gives it better performance on Chinese language tasks.
This model was contributed by s-JoL. The original code was released on GitHub by s-JoL, but is now removed.
OpenLlamaConfig
autodoc OpenLlamaConfig
OpenLlamaModel
autodoc OpenLlamaModel - forward
OpenLlamaForCausalLM
autodoc OpenLlamaForCausalLM - forward
OpenLlamaForSequenceClassification
autodoc OpenLlamaForSequenceClassification - forward