LLAMA_ARG_NO_CONTEXT_SHIFT

Author: ngxson

common/arg.cpp

@@ -691,7 +691,7 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
         [](gpt_params & params) {
             params.ctx_shift = false;
         }
-    ).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}));
+    ).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
     add_opt(llama_arg(
         {"--chunks"}, "N",
         format("max number of chunks to process (default: %d, -1 = all)", params.n_chunks),

examples/server/README.md

@@ -127,7 +127,7 @@ The project is under active development, and we are [looking for feedback and co
 
 | Argument | Explanation |
 | -------- | ----------- |
-| `--no-context-shift` | disables context shift on inifinite text generation (default: disabled) |
+| `--no-context-shift` | disables context shift on inifinite text generation (default: disabled)<br/>(env: LLAMA_ARG_NO_CONTEXT_SHIFT) |
 | `-sp, --special` | special tokens output enabled (default: false) |
 | `--spm-infill` | use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. (default: disabled) |
 | `--pooling {none,mean,cls,last}` | pooling type for embeddings, use model default if unspecified<br/>(env: LLAMA_ARG_POOLING) |