mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add LoRA support to ExLlama_HF

Browse source
This commit is contained in:
oobabooga 2023-06-26 00:10:13 -03:00
parent b7c627f9a0
commit 22d455b072
3 changed files with 17 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
server.py
View file

@ -245,7 +245,7 @@ def create_model_menus():
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).')
shared.gradio['exllama_HF_info'] = gr.Markdown('ExLlama_HF is a wrapper that lets you use ExLlama like a Transformers model, which means it can use the Transformers samplers. It\'s a bit slower than the regular ExLlama and doesn\'t support LoRA.')
shared.gradio['exllama_HF_info'] = gr.Markdown('ExLlama_HF is a wrapper that lets you use ExLlama like a Transformers model, which means it can use the Transformers samplers. It\'s a bit slower than the regular ExLlama.')
with gr.Column():
with gr.Row():