diff --git a/README.md b/README.md index 7837bfd..0229d0b 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ python -m pip install https://github.com/jllllll/exllama/releases/download/0.0.1 Name | Description :--- | :--- Loader | Used to load 4-bit GPTQ Llama/2 models. You can find a lot of them on [Hugging Face](https://huggingface.co/TheBloke).
Clone the model repository or download all the files and place them in an empty directory, then specify the path in `model_dir`. The `model.safetensors` file won't work on its own.

ExLlama allocates memory based on `max_seq_len`. Lowering it is a good way to save on VRAM.
It's currently not possible to [offload](https://github.com/turboderp/exllama/issues/177) the model to RAM. -LoRA Loader | Used to load LoRAs. The directory should contain `adapter_model.bin` and `adapter_config.json`.
LoRA parameter count has to match the model. +LoRA | Used to load LoRAs. The directory should contain `adapter_model.bin` and `adapter_config.json`.
LoRA parameter count has to match the model. Generator | Generates a `string` based on the given `prompt` for use with other nodes.
Default values correspond to the `simple-1` preset from [text-generation-webui](https://github.com/oobabooga/text-generation-webui).

ExLlama isn't [deterministic](https://github.com/turboderp/exllama/issues/201), so the outputs may differ even with the same seed. Previewer | Displays generated outputs in the UI and appends them to workflow metadata. diff --git a/__init__.py b/__init__.py index fb7779a..b287d9a 100644 --- a/__init__.py +++ b/__init__.py @@ -1,15 +1,15 @@ -from .nodes import Generator, Loader, LoraLoader, Previewer +from .nodes import Generator, Loader, Lora, Previewer NODE_CLASS_MAPPINGS = { "ZuellniExLlamaLoader": Loader, - "ZuellniExLlamaLoraLoader": LoraLoader, + "ZuellniExLlamaLora": Lora, "ZuellniExLlamaGenerator": Generator, "ZuellniExLlamaPreviewer": Previewer, } NODE_DISPLAY_NAME_MAPPINGS = { "ZuellniExLlamaLoader": "ExLlama Loader", - "ZuellniExLlamaLoraLoader": "ExLlama LoRA Loader", + "ZuellniExLlamaLora": "ExLlama LoRA", "ZuellniExLlamaGenerator": "ExLlama Generator", "ZuellniExLlamaPreviewer": "ExLlama Previewer", } diff --git a/nodes.py b/nodes.py index 2ad8bb7..6846e12 100644 --- a/nodes.py +++ b/nodes.py @@ -133,7 +133,7 @@ class Loader: return (generator,) -class LoraLoader: +class Lora: @classmethod def INPUT_TYPES(cls): return { diff --git a/requirements.txt b/requirements.txt index 26038f9..3447dfc 100644 --- a/requirements.txt +++ b/requirements.txt @@ -2,5 +2,5 @@ https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu121 https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and python_version == "3.11" https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and python_version == "3.10" +colorama sentencepiece -colorama \ No newline at end of file