diff --git a/server.py b/server.py index d7819bc7..429cf59d 100644 --- a/server.py +++ b/server.py @@ -250,7 +250,6 @@ def create_model_menus(): shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram) shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock) shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed) - shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17') shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Make sure to inspect the .py files inside the model folder before loading it with this option enabled.') shared.gradio['gptq_for_llama_info'] = gr.Markdown('GPTQ-for-LLaMa is currently 2x faster than AutoGPTQ on some systems. It is installed by default with the one-click installers. Otherwise, it has to be installed manually following the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#installation-1).') shared.gradio['exllama_info'] = gr.Markdown('For more information, consult the [docs](https://github.com/oobabooga/text-generation-webui/blob/main/docs/ExLlama.md).')