Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 10:35:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Fix a typo

Browse source
This commit is contained in:
oobabooga 2023-08-25 07:08:38 -07:00
parent 5c7d8bfdfd
commit f4f04c8c32
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -337,9 +337,9 @@ Optionally, you can use the following command-line flags:
| Flag | Description |
|------------------|-------------|
| `--alpha_value ALPHA_VALUE` | Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.
| `--rope_freq_base ROPE_FREQ_BASE` | If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)
| `--compress_pos_emb COMPRESS_POS_EMB` | Positional embeddings compression factor. Should be set to (context length) / (model's original context length). Equal to 1/rope_freq_scale.
| `--alpha_value ALPHA_VALUE` | Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both. |
| `--rope_freq_base ROPE_FREQ_BASE` | If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63). |
| `--compress_pos_emb COMPRESS_POS_EMB` | Positional embeddings compression factor. Should be set to (context length) / (model's original context length). Equal to 1/rope_freq_scale. |
#### Gradio

2
modules/shared.py
View file

@ -160,7 +160,7 @@ parser.add_argument('--rwkv-cuda-on', action='store_true', help='RWKV: Compile t
# RoPE
parser.add_argument('--alpha_value', type=int, default=1, help="Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.")
parser.add_argument('--rope_freq_base', type=int, default=1, help="If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)")
parser.add_argument('--rope_freq_base', type=int, default=0, help="If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63).")
parser.add_argument('--compress_pos_emb', type=int, default=1, help="Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.")
# Gradio