vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-15 11:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

default to autoguess for chat completions adapter

Browse source
This commit is contained in:
Concedo 2025-01-30 00:25:13 +08:00
parent 70f1d8d746
commit 646df4b126
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
koboldcpp.py
View file

@ -3238,7 +3238,7 @@ def show_gui():
customrope_var = ctk.IntVar() customrope_var = ctk.IntVar()
customrope_scale = ctk.StringVar(value="1.0") customrope_scale = ctk.StringVar(value="1.0")
customrope_base = ctk.StringVar(value="10000") customrope_base = ctk.StringVar(value="10000")
chatcompletionsadapter_var = ctk.StringVar() chatcompletionsadapter_var = ctk.StringVar(value="AutoGuess")
moeexperts_var = ctk.StringVar(value=str(-1)) moeexperts_var = ctk.StringVar(value=str(-1))
model_var = ctk.StringVar() model_var = ctk.StringVar()
@ -5620,7 +5620,7 @@ if __name__ == '__main__':
advparser.add_argument("--draftgpusplit", help="GPU layer distribution ratio for draft model (default=same as main). Only works if multi-GPUs selected for MAIN model and tensor_split is set!", metavar=('[Ratios]'), type=float, nargs='+') advparser.add_argument("--draftgpusplit", help="GPU layer distribution ratio for draft model (default=same as main). Only works if multi-GPUs selected for MAIN model and tensor_split is set!", metavar=('[Ratios]'), type=float, nargs='+')
advparser.add_argument("--password", metavar=('[API key]'), help="Enter a password required to use this instance. This key will be required for all text endpoints. Image endpoints are not secured.", default=None) advparser.add_argument("--password", metavar=('[API key]'), help="Enter a password required to use this instance. This key will be required for all text endpoints. Image endpoints are not secured.", default=None)
advparser.add_argument("--ignoremissing", help="Ignores all missing non-essential files, just skipping them instead.", action='store_true') advparser.add_argument("--ignoremissing", help="Ignores all missing non-essential files, just skipping them instead.", action='store_true')
advparser.add_argument("--chatcompletionsadapter", metavar=('[filename]'), help="Select an optional ChatCompletions Adapter JSON file to force custom instruct tags.", default="") advparser.add_argument("--chatcompletionsadapter", metavar=('[filename]'), help="Select an optional ChatCompletions Adapter JSON file to force custom instruct tags.", default="AutoGuess")
advparser.add_argument("--flashattention", help="Enables flash attention.", action='store_true') advparser.add_argument("--flashattention", help="Enables flash attention.", action='store_true')
advparser.add_argument("--quantkv", help="Sets the KV cache data type quantization, 0=f16, 1=q8, 2=q4. Requires Flash Attention, and disables context shifting.",metavar=('[quantization level 0/1/2]'), type=int, choices=[0,1,2], default=0) advparser.add_argument("--quantkv", help="Sets the KV cache data type quantization, 0=f16, 1=q8, 2=q4. Requires Flash Attention, and disables context shifting.",metavar=('[quantization level 0/1/2]'), type=int, choices=[0,1,2], default=0)
advparser.add_argument("--forceversion", help="If the model file format detection fails (e.g. rogue modified model) you can set this to override the detected format (enter desired version, e.g. 401 for GPTNeoX-Type2).",metavar=('[version]'), type=int, default=0) advparser.add_argument("--forceversion", help="If the model file format detection fails (e.g. rogue modified model) you can set this to override the detected format (enter desired version, e.g. 401 for GPTNeoX-Type2).",metavar=('[version]'), type=int, default=0)