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

cli : auto activate conversation mode if chat template is available (#11214)

Browse source 
* cli : auto activate conversation mode if chat template is detected

* add warn on bad template

* update readme (writing with the help of chatgpt)

* update readme (2)

* do not activate -cnv for non-instruct models
This commit is contained in:
Xuan Son Nguyen 2025-01-13 20:18:12 +01:00 • committed by GitHub
parent 39509fb082
commit 84a44815f7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 75 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

20
common/arg.cpp
View file

@ -777,15 +777,19 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"-cnv", "--conversation"},
string_format(
"run in conversation mode:\n"
"- does not print special tokens and suffix/prefix\n"
"- interactive mode is also enabled\n"
"(default: %s)",
params.conversation ? "true" : "false"
),
"run in conversation mode:\n"
"- does not print special tokens and suffix/prefix\n"
"- interactive mode is also enabled\n"
"(default: auto enabled if chat template is available)",
[](common_params & params) {
params.conversation = true;
params.conversation_mode = COMMON_CONVERSATION_MODE_ENABLED;
}
).set_examples({LLAMA_EXAMPLE_MAIN}));
add_opt(common_arg(
{"-no-cnv", "--no-conversation"},
"force disable conversation mode (default: false)",
[](common_params & params) {
params.conversation_mode = COMMON_CONVERSATION_MODE_DISABLED;
}
).set_examples({LLAMA_EXAMPLE_MAIN}));
add_opt(common_arg(

9
common/common.h
View file

@ -103,6 +103,12 @@ enum dimre_method {
DIMRE_METHOD_MEAN,
};
enum common_conversation_mode {
COMMON_CONVERSATION_MODE_DISABLED = 0,
COMMON_CONVERSATION_MODE_ENABLED = 1,
COMMON_CONVERSATION_MODE_AUTO = 2,
};
// sampling parameters
struct common_params_sampling {
uint32_t seed = LLAMA_DEFAULT_SEED; // the seed used to initialize llama_sampler
@ -275,7 +281,6 @@ struct common_params {
bool special = false; // enable special token output
bool interactive = false; // interactive mode
bool interactive_first = false; // wait for user input immediately
bool conversation = false; // conversation mode (does not print special tokens and suffix/prefix)
bool prompt_cache_all = false; // save user input and generations to prompt cache
bool prompt_cache_ro = false; // open the prompt cache read-only and do not update it
@ -301,6 +306,8 @@ struct common_params {
ggml_type cache_type_k = GGML_TYPE_F16; // KV cache data type for the K
ggml_type cache_type_v = GGML_TYPE_F16; // KV cache data type for the V
common_conversation_mode conversation_mode = COMMON_CONVERSATION_MODE_AUTO;
// multimodal models (see examples/llava)
std::string mmproj = ""; // path to multimodal projector // NOLINT
std::vector<std::string> image; // path to image file(s)