vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Remove model assign in main(). Clarified stop in README.

Browse source 
The model will now load the default from gptparams ("models/7B/ggml-model.bin")
This commit is contained in:
Randall Fitzgerald 2023-06-09 16:29:10 -04:00
parent 7cdeb08483
commit 1a9141b6c3
2 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/README.md
View file

@ -110,7 +110,7 @@ node .
`prompt`: Provide a prompt. Internally, the prompt is compared, and it detects if a part has already been evaluated, and the remaining part will be evaluate. `prompt`: Provide a prompt. Internally, the prompt is compared, and it detects if a part has already been evaluated, and the remaining part will be evaluate.
`stop`: Specify the strings that indicate a stop. `stop`: Specify a JSON array of stopping strings.
These words will not be included in the completion, so make sure to add them to the prompt for the next iteration (default: []). These words will not be included in the completion, so make sure to add them to the prompt for the next iteration (default: []).
`tfs_z`: Enable tail free sampling with parameter z (default: 1.0, 1.0 = disabled). `tfs_z`: Enable tail free sampling with parameter z (default: 1.0, 1.0 = disabled).

1
examples/server/server.cpp
View file

@ -774,7 +774,6 @@ int main(int argc, char ** argv)
// struct that contains llama context and inference // struct that contains llama context and inference
llama_server_context llama; llama_server_context llama;
params.model = "ggml-model.bin";
server_params_parse(argc, argv, sparams, params); server_params_parse(argc, argv, sparams, params);