mirror of
https://github.com/ollama/ollama.git
synced 2025-05-11 10:26:53 +02:00
llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)
This commit is contained in:
Jeffrey Morgan
GitHub
parent
2db96c18e7
commit
d7d7e99662
149 changed files with 18215 additions and 11009 deletions
112
llama/llama.cpp/common/json-schema-to-grammar.cpp
vendored
112
llama/llama.cpp/common/json-schema-to-grammar.cpp
vendored
|
|
@ -1,4 +1,6 @@
|
|||
#include "json-schema-to-grammar.h"
|
||||
#include "common.h"
|
||||
|
||||
#include <algorithm>
|
||||
#include <fstream>
|
||||
#include <map>
|
||||
|
|
@ -11,11 +13,6 @@
|
|||
|
||||
using json = nlohmann::ordered_json;
|
||||
|
||||
template <typename Iterator>
|
||||
static std::string join(Iterator begin, Iterator end, const std::string & separator);
|
||||
|
||||
static std::string repeat(const std::string & str, size_t n);
|
||||
|
||||
static std::string build_repetition(const std::string & item_rule, int min_items, int max_items, const std::string & separator_rule = "") {
|
||||
auto has_max = max_items != std::numeric_limits<int>::max();
|
||||
|
||||
|
|
@ -128,8 +125,8 @@ static void _build_min_max_int(int min_value, int max_value, std::stringstream &
|
|||
if (sub_len > 0) {
|
||||
auto from_sub = from.substr(i + 1);
|
||||
auto to_sub = to.substr(i + 1);
|
||||
auto sub_zeros = repeat("0", sub_len);
|
||||
auto sub_nines = repeat("9", sub_len);
|
||||
auto sub_zeros = string_repeat("0", sub_len);
|
||||
auto sub_nines = string_repeat("9", sub_len);
|
||||
|
||||
auto to_reached = false;
|
||||
out << "(";
|
||||
|
|
@ -188,8 +185,8 @@ static void _build_min_max_int(int min_value, int max_value, std::stringstream &
|
|||
auto max_digits = max_s.length();
|
||||
|
||||
for (auto digits = min_digits; digits < max_digits; digits++) {
|
||||
uniform_range(min_s, repeat("9", digits));
|
||||
min_s = "1" + repeat("0", digits);
|
||||
uniform_range(min_s, string_repeat("9", digits));
|
||||
min_s = "1" + string_repeat("0", digits);
|
||||
out << " | ";
|
||||
}
|
||||
uniform_range(min_s, max_s);
|
||||
|
|
@ -318,49 +315,6 @@ std::unordered_map<char, std::string> GRAMMAR_LITERAL_ESCAPES = {
|
|||
std::unordered_set<char> NON_LITERAL_SET = {'|', '.', '(', ')', '[', ']', '{', '}', '*', '+', '?'};
|
||||
std::unordered_set<char> ESCAPED_IN_REGEXPS_BUT_NOT_IN_LITERALS = {'^', '$', '.', '[', ']', '(', ')', '|', '{', '}', '*', '+', '?'};
|
||||
|
||||
template <typename Iterator>
|
||||
std::string join(Iterator begin, Iterator end, const std::string & separator) {
|
||||
std::ostringstream result;
|
||||
if (begin != end) {
|
||||
result << *begin;
|
||||
for (Iterator it = begin + 1; it != end; ++it) {
|
||||
result << separator << *it;
|
||||
}
|
||||
}
|
||||
return result.str();
|
||||
}
|
||||
|
||||
static std::vector<std::string> split(const std::string & str, const std::string & delimiter) {
|
||||
std::vector<std::string> tokens;
|
||||
size_t start = 0;
|
||||
size_t end = str.find(delimiter);
|
||||
|
||||
while (end != std::string::npos) {
|
||||
tokens.push_back(str.substr(start, end - start));
|
||||
start = end + delimiter.length();
|
||||
end = str.find(delimiter, start);
|
||||
}
|
||||
|
||||
tokens.push_back(str.substr(start));
|
||||
|
||||
return tokens;
|
||||
}
|
||||
|
||||
static std::string repeat(const std::string & str, size_t n) {
|
||||
if (n == 0) {
|
||||
return "";
|
||||
}
|
||||
|
||||
std::string result;
|
||||
result.reserve(str.length() * n);
|
||||
|
||||
for (size_t i = 0; i < n; ++i) {
|
||||
result += str;
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
static std::string replacePattern(const std::string & input, const std::regex & regex, const std::function<std::string(const std::smatch &)> & replacement) {
|
||||
std::smatch match;
|
||||
std::string result;
|
||||
|
|
@ -389,6 +343,7 @@ static std::string format_literal(const std::string & literal) {
|
|||
|
||||
class SchemaConverter {
|
||||
private:
|
||||
friend std::string build_grammar(const std::function<void(const common_grammar_builder &)> & cb, const common_grammar_options & options);
|
||||
std::function<json(const std::string &)> _fetch_json;
|
||||
bool _dotall;
|
||||
std::unordered_map<std::string, std::string> _rules;
|
||||
|
|
@ -418,7 +373,7 @@ private:
|
|||
for (size_t i = 0; i < alt_schemas.size(); i++) {
|
||||
rules.push_back(visit(alt_schemas[i], name + (name.empty() ? "alternative-" : "-") + std::to_string(i)));
|
||||
}
|
||||
return join(rules.begin(), rules.end(), " | ");
|
||||
return string_join(rules, " | ");
|
||||
}
|
||||
|
||||
std::string _visit_pattern(const std::string & pattern, const std::string & name) {
|
||||
|
|
@ -481,7 +436,7 @@ private:
|
|||
for (const auto & item : ret) {
|
||||
results.push_back(to_rule(item));
|
||||
}
|
||||
return std::make_pair(join(results.begin(), results.end(), " "), false);
|
||||
return std::make_pair(string_join(results, " "), false);
|
||||
};
|
||||
|
||||
while (i < length) {
|
||||
|
|
@ -539,7 +494,7 @@ private:
|
|||
}
|
||||
curly_brackets += '}';
|
||||
i++;
|
||||
auto nums = split(curly_brackets.substr(1, curly_brackets.length() - 2), ",");
|
||||
auto nums = string_split(curly_brackets.substr(1, curly_brackets.length() - 2), ",");
|
||||
int min_times = 0;
|
||||
int max_times = std::numeric_limits<int>::max();
|
||||
try {
|
||||
|
|
@ -809,10 +764,11 @@ private:
|
|||
public:
|
||||
SchemaConverter(
|
||||
const std::function<json(const std::string &)> & fetch_json,
|
||||
bool dotall)
|
||||
bool dotall,
|
||||
bool compact_spaces)
|
||||
: _fetch_json(fetch_json), _dotall(dotall)
|
||||
{
|
||||
_rules["space"] = SPACE_RULE;
|
||||
_rules["space"] = compact_spaces ? "\" \"?" : SPACE_RULE;
|
||||
}
|
||||
|
||||
void resolve_refs(json & schema, const std::string & url) {
|
||||
|
|
@ -854,7 +810,7 @@ public:
|
|||
return;
|
||||
}
|
||||
std::string pointer = ref.substr(ref.find('#') + 1);
|
||||
std::vector<std::string> tokens = split(pointer, "/");
|
||||
std::vector<std::string> tokens = string_split(pointer, "/");
|
||||
for (size_t i = 1; i < tokens.size(); ++i) {
|
||||
std::string sel = tokens[i];
|
||||
if (target.is_null() || !target.contains(sel)) {
|
||||
|
|
@ -905,7 +861,7 @@ public:
|
|||
for (const auto & v : schema["enum"]) {
|
||||
enum_values.push_back(_generate_constant_rule(v));
|
||||
}
|
||||
return _add_rule(rule_name, "(" + join(enum_values.begin(), enum_values.end(), " | ") + ") space");
|
||||
return _add_rule(rule_name, "(" + string_join(enum_values, " | ") + ") space");
|
||||
} else if ((schema_type.is_null() || schema_type == "object")
|
||||
&& (schema.contains("properties") ||
|
||||
(schema.contains("additionalProperties") && schema["additionalProperties"] != true))) {
|
||||
|
|
@ -1019,10 +975,10 @@ public:
|
|||
|
||||
void check_errors() {
|
||||
if (!_errors.empty()) {
|
||||
throw std::runtime_error("JSON schema conversion failed:\n" + join(_errors.begin(), _errors.end(), "\n"));
|
||||
throw std::runtime_error("JSON schema conversion failed:\n" + string_join(_errors, "\n"));
|
||||
}
|
||||
if (!_warnings.empty()) {
|
||||
fprintf(stderr, "WARNING: JSON schema conversion was incomplete: %s\n", join(_warnings.begin(), _warnings.end(), "; ").c_str());
|
||||
fprintf(stderr, "WARNING: JSON schema conversion was incomplete: %s\n", string_join(_warnings, "; ").c_str());
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -1035,11 +991,35 @@ public:
|
|||
}
|
||||
};
|
||||
|
||||
std::string json_schema_to_grammar(const json & schema) {
|
||||
SchemaConverter converter([](const std::string &) { return json::object(); }, /* dotall= */ false);
|
||||
auto copy = schema;
|
||||
converter.resolve_refs(copy, "input");
|
||||
converter.visit(copy, "");
|
||||
std::string json_schema_to_grammar(const json & schema, bool force_gbnf) {
|
||||
#ifdef LLAMA_USE_LLGUIDANCE
|
||||
if (!force_gbnf) {
|
||||
return "%llguidance {}\nstart: %json " + schema.dump();
|
||||
}
|
||||
#else
|
||||
(void)force_gbnf;
|
||||
#endif // LLAMA_USE_LLGUIDANCE
|
||||
return build_grammar([&](const common_grammar_builder & callbacks) {
|
||||
auto copy = schema;
|
||||
callbacks.resolve_refs(copy);
|
||||
callbacks.add_schema("", copy);
|
||||
});
|
||||
}
|
||||
|
||||
std::string build_grammar(const std::function<void(const common_grammar_builder &)> & cb, const common_grammar_options & options) {
|
||||
SchemaConverter converter([&](const std::string &) { return json(); }, options.dotall, options.compact_spaces);
|
||||
common_grammar_builder builder {
|
||||
/* .add_rule = */ [&](const std::string & name, const std::string & rule) {
|
||||
return converter._add_rule(name, rule);
|
||||
},
|
||||
/* .add_schema = */ [&](const std::string & name, const nlohmann::ordered_json & schema) {
|
||||
return converter.visit(schema, name == "root" ? "" : name);
|
||||
},
|
||||
/* .resolve_refs = */ [&](nlohmann::ordered_json & schema) {
|
||||
converter.resolve_refs(schema, "");
|
||||
}
|
||||
};
|
||||
cb(builder);
|
||||
converter.check_errors();
|
||||
return converter.format_grammar();
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue