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

quantize: add imatrix and dataset metadata in GGUF (#6658)

Browse source 
* imatrix: save the dataset file used in the output file

* llama: support kv overrides type string string

* common: factorize KV Overrides parsing between common and server

* quantize: add imatrix n entries and dataset KV metadata
quantize: factorize KV Overrides parsing between common
#6656

* llama: remove kv override str_value initialization as it does not compile on some toolchain

* quantize: add imatrix m_last_call as `quantize.imatrix.chunks_count`

* quantize: add imatrix filename in KV

* llama: add llama_model_kv_override_free

* common: add llama_model_kv_override_free
common: free kv override if used after model loading

* llama: finally move the string KV override value to the stack

* llama : minor

* no need to add a NUL to the std::vector, std::string can be initialized from a pair of iterators.

Co-authored-by: slaren <slarengh@gmail.com>

* kv override: ensure string termination

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-04-26 20:06:33 +02:00 • committed by GitHub
parent 017e6999b5
commit 0c4d489e29
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 186 additions and 171 deletions
Download patch file Download diff file Expand all files Collapse all files

36
examples/server/server.cpp
View file

@ -2392,7 +2392,7 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" -n, --n-predict maximum tokens to predict (default: %d)\n", params.n_predict);
printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" advanced option to override model metadata by key. may be specified multiple times.\n");
printf(" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
printf(" types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
printf(" -gan N, --grp-attn-n N set the group attention factor to extend context size through self-extend(default: 1=disabled), used together with group attention width `--grp-attn-w`\n");
printf(" -gaw N, --grp-attn-w N set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`\n");
printf(" --chat-template JINJA_TEMPLATE\n");
@ -2823,43 +2823,11 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
invalid_param = true;
break;
}
char * sep = strchr(argv[i], '=');
if (sep == nullptr || sep - argv[i] >= 128) {
fprintf(stderr, "error: Malformed KV override: %s\n", argv[i]);
invalid_param = true;
break;
}
struct llama_model_kv_override kvo;
std::strncpy(kvo.key, argv[i], sep - argv[i]);
kvo.key[sep - argv[i]] = 0;
sep++;
if (strncmp(sep, "int:", 4) == 0) {
sep += 4;
kvo.tag = LLAMA_KV_OVERRIDE_TYPE_INT;
kvo.int_value = std::atol(sep);
} else if (strncmp(sep, "float:", 6) == 0) {
sep += 6;
kvo.tag = LLAMA_KV_OVERRIDE_TYPE_FLOAT;
kvo.float_value = std::atof(sep);
} else if (strncmp(sep, "bool:", 5) == 0) {
sep += 5;
kvo.tag = LLAMA_KV_OVERRIDE_TYPE_BOOL;
if (std::strcmp(sep, "true") == 0) {
kvo.bool_value = true;
} else if (std::strcmp(sep, "false") == 0) {
kvo.bool_value = false;
} else {
fprintf(stderr, "error: Invalid boolean value for KV override: %s\n", argv[i]);
invalid_param = true;
break;
}
} else {
if (!parse_kv_override(argv[i], params.kv_overrides)) {
fprintf(stderr, "error: Invalid type for KV override: %s\n", argv[i]);
invalid_param = true;
break;
}
params.kv_overrides.push_back(kvo);
} else {
fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
server_print_usage(argv[0], default_params, default_sparams);