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

Implement a demo HF wrapper for exllama to utilize existing HF transformers decoding. (#2777)

Browse source
This commit is contained in:
LarryVRH 2023-06-22 02:31:42 +08:00 • committed by GitHub
parent a06acd6d09
commit 580c1ee748
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 101 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

3
server.py
View file

@ -197,7 +197,7 @@ def create_model_menus():
with gr.Row():
with gr.Column():
shared.gradio['loader'] = gr.Dropdown(label="Model loader", choices=["Transformers", "AutoGPTQ", "GPTQ-for-LLaMa", "ExLlama", "llama.cpp"], value=None)
shared.gradio['loader'] = gr.Dropdown(label="Model loader", choices=["Transformers", "AutoGPTQ", "GPTQ-for-LLaMa", "ExLlama", "ExLlama_HF", "llama.cpp"], value=None)
with gr.Box():
with gr.Row():
with gr.Column():
@ -237,6 +237,7 @@ 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('ExLlama has to be installed manually. See the instructions here: [instructions](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 still a bit buggy, so feel free to help out by fixing issues.\n\nCheck out PR [#2777](https://github.com/oobabooga/text-generation-webui/pull/2777) for more details.')
with gr.Column():
with gr.Row():