Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-24 17:06:53 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update cache_4bit documentation (#5649)

Browse Source 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
This commit is contained in:
Bartowski 2024-03-07 11:08:21 -05:00 committed by GitHub
parent bef08129bc
commit 104573f7d4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -279,7 +279,7 @@ List of command-line flags
|`--cfg-cache` | ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader. |
|`--no_flash_attn` | Force flash-attention to not be used. |
|`--cache_8bit` | Use 8-bit cache to save VRAM. |
|`--cache_4bit` | Use 4-bit cache to save VRAM. |
|`--cache_4bit` | Use Q4 cache to save VRAM. |
|`--num_experts_per_token NUM_EXPERTS_PER_TOKEN` | Number of experts to use for generation. Applies to MoE models like Mixtral. |
#### AutoGPTQ

1
docs/04 - Model Tab.md
View File

@ -46,6 +46,7 @@ Examples:
* **cfg-cache**: Creates a second cache to hold the CFG negative prompts. You need to set this if and only if you intend to use CFG in the "Parameters" > "Generation" tab. Checking this parameter doubles the cache VRAM usage.
* **no_flash_attn**: Disables flash attention. Otherwise, it is automatically used as long as the library is installed.
* **cache_8bit**: Create a 8-bit precision cache instead of a 16-bit one. This saves VRAM but increases perplexity (I don't know by how much).
* **cache_4bit**: Creates a Q4 cache using grouped quantization.
### ExLlamav2

2
modules/exllamav2_hf.py
View File

@ -63,6 +63,8 @@ class Exllamav2HF(PreTrainedModel):
if shared.args.cfg_cache:
if shared.args.cache_8bit:
self.ex_cache_negative = ExLlamaV2Cache_8bit(self.ex_model)
elif shared.args.cache_4bit:
self.ex_cache_negative = ExLlamaV2Cache_Q4(self.ex_model)
else:
self.ex_cache_negative = ExLlamaV2Cache(self.ex_model)

2
modules/shared.py
View File

@ -139,7 +139,7 @@ group.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequen
group.add_argument('--cfg-cache', action='store_true', help='ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
group.add_argument('--no_flash_attn', action='store_true', help='Force flash-attention to not be used.')
group.add_argument('--cache_8bit', action='store_true', help='Use 8-bit cache to save VRAM.')
group.add_argument('--cache_4bit', action='store_true', help='Use 4-bit cache to save VRAM.')
group.add_argument('--cache_4bit', action='store_true', help='Use Q4 cache to save VRAM.')
group.add_argument('--num_experts_per_token', type=int, default=2, help='Number of experts to use for generation. Applies to MoE models like Mixtral.')
# AutoGPTQ

2
modules/ui_model_menu.py
View File

@ -132,7 +132,7 @@ def create_ui():
shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.')
shared.gradio['cache_4bit'] = gr.Checkbox(label="cache_4bit", value=shared.args.cache_4bit, info='Use 4-bit cache to save VRAM.')
shared.gradio['cache_4bit'] = gr.Checkbox(label="cache_4bit", value=shared.args.cache_4bit, info='Use Q4 cache to save VRAM.')
shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.')
shared.gradio['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn, info='Force flash-attention to not be used.')
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Necessary to use CFG with this loader.')