diff --git a/README.md b/README.md index 40f8d2c3..4bf0fc06 100644 --- a/README.md +++ b/README.md @@ -386,6 +386,23 @@ generated_text = inference(prompt_text) print(generated_text) ``` +### Mixtral +- Utilize Mixtral in a very simple API, +- Utilize 4bit quantization for a increased speed and less memory usage +- Use Flash Attention 2.0 for increased speed and less memory usage +```python +from swarms.models import Mixtral + +# Initialize the Mixtral model with 4 bit and flash attention! +mixtral = Mixtral(load_in_4bit=True, use_flash_attention_2=True) + +# Generate text for a simple task +generated_text = mixtral.run("Generate a creative story.") + +# Print the generated text +print(generated_text) +``` + --- # Features 🤖 diff --git a/mkdocs.yml b/mkdocs.yml index f8fe3e76..de263ac6 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -83,6 +83,7 @@ nav: - vLLM: "swarms/models/vllm.md" - MPT7B: "swarms/models/mpt.md" - Mistral: "swarms/models/mistral.md" + - Mixtral: "swarms/models/mixtral.md" - MultiModal: - BaseMultiModalModel: "swarms/models/base_multimodal_model.md" - Fuyu: "swarms/models/fuyu.md" diff --git a/pyproject.toml b/pyproject.toml index 907d1914..cf214581 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api" [tool.poetry] name = "swarms" -version = "2.4.1" +version = "2.4.2" description = "Swarms - Pytorch" license = "MIT" authors = ["Kye Gomez "]