Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-24 13:28:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add some clarifications

Browse Source
This commit is contained in:
oobabooga 2023-06-16 19:07:16 -03:00
parent 7ef6a50e84
commit dea43685b0
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
modules/loaders.py
View File

@ -50,6 +50,7 @@ loaders_and_params = {
'quant_type',
'compute_dtype',
'trust_remote_code',
'transformers_info'
],
}

3
server.py
View File

@ -201,6 +201,7 @@ def create_model_menus():
shared.gradio[f'gpu_memory_{i}'] = gr.Slider(label=f"gpu-memory in MiB for device :{i}", maximum=total_mem[i], value=default_gpu_mem[i])
shared.gradio['cpu_memory'] = gr.Slider(label="cpu-memory in MiB", maximum=total_cpu_mem, value=default_cpu_mem)
shared.gradio['transformers_info'] = gr.Markdown('load-in-4bit params:')
shared.gradio['compute_dtype'] = gr.Dropdown(label="compute_dtype", choices=["bfloat16", "float16", "float32"], value=shared.args.compute_dtype)
shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type)
shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=32, value=shared.args.threads)
@ -218,11 +219,11 @@ def create_model_menus():
shared.gradio['no_inject_fused_attention'] = gr.Checkbox(label="no_inject_fused_attention", value=shared.args.no_inject_fused_attention, info='Disable fused attention. Fused attention improves inference performance but uses more VRAM. Disable if running low on VRAM.')
shared.gradio['no_inject_fused_mlp'] = gr.Checkbox(label="no_inject_fused_mlp", value=shared.args.no_inject_fused_mlp, info='Affects Triton only. Disable fused MLP. Fused MLP improves performance but uses more VRAM. Disable if running low on VRAM.')
shared.gradio['desc_act'] = gr.Checkbox(label="desc_act", value=shared.args.desc_act, info='\'desc_act\', \'wbits\', and \'groupsize\' are used for old models without a quantize_config.json.')
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices)
shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit")
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)