README updates and improvements (#3198)
This commit is contained in:
parent
b09e4f10fd
commit
f653546484
5 changed files with 38 additions and 37 deletions
|
@ -153,8 +153,6 @@ parser.add_argument('--desc_act', action='store_true', help='For models that don
|
|||
# ExLlama
|
||||
parser.add_argument('--gpu-split', type=str, help="Comma-separated list of VRAM (in GB) to use per GPU device for model layers, e.g. 20,7,7")
|
||||
parser.add_argument('--max_seq_len', type=int, default=2048, help="Maximum sequence length.")
|
||||
parser.add_argument('--compress_pos_emb', type=int, default=1, help="Positional embeddings compression factor. Should typically be set to max_seq_len / 2048.")
|
||||
parser.add_argument('--alpha_value', type=int, default=1, help="Positional embeddings alpha factor for NTK RoPE scaling. Same as above. Use either this or compress_pos_emb, not both.")
|
||||
|
||||
# FlexGen
|
||||
parser.add_argument('--flexgen', action='store_true', help='DEPRECATED')
|
||||
|
@ -171,6 +169,10 @@ parser.add_argument('--local_rank', type=int, default=0, help='DeepSpeed: Option
|
|||
parser.add_argument('--rwkv-strategy', type=str, default=None, help='RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8".')
|
||||
parser.add_argument('--rwkv-cuda-on', action='store_true', help='RWKV: Compile the CUDA kernel for better performance.')
|
||||
|
||||
# RoPE
|
||||
parser.add_argument('--compress_pos_emb', type=int, default=1, help="Positional embeddings compression factor. Should typically be set to max_seq_len / 2048.")
|
||||
parser.add_argument('--alpha_value', type=int, default=1, help="Positional embeddings alpha factor for NTK RoPE scaling. Scaling is not identical to embedding compression. Use either this or compress_pos_emb, not both.")
|
||||
|
||||
# Gradio
|
||||
parser.add_argument('--listen', action='store_true', help='Make the web UI reachable from your local network.')
|
||||
parser.add_argument('--listen-host', type=str, help='The hostname that the server will use.')
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue