llama : add grammar-based sampling (#1773)

* llama, main : constrain sampling to grammar

* allow loading grammar from file

* fix whitespace errors

* handle & print parser errors

* add comments to grammar syntax and allow newlines where unambiguous

* add missing include

* support alternates in root rule

* fix bugs with empty token and EOS

* adjust JSON grammar

* remove swp file

* rewrite ternary expressions

Co-authored-by: Henri Vasserman <[email protected]>

* use struct for grammar elements and add Unicode support

* add unicode escapes

* add inverse char ranges

* only sample full tokens (no peeking or truncation)

* llama : minor style changes

blindly applied in online editor - hopefully I didn't break something

* update help text

* add warning message if EOS is disabled

---------

Co-authored-by: Henri Vasserman <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>

Author: 3 people

Diff for: Makefile

@@ -323,6 +323,9 @@ llama.o: llama.cpp ggml.h ggml-cuda.h ggml-metal.h llama.h llama-util.h
 common.o: examples/common.cpp examples/common.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
+grammar-parser.o: examples/grammar-parser.cpp examples/grammar-parser.h
+	$(CXX) $(CXXFLAGS) -c $< -o $@
+
 libllama.so: llama.o ggml.o $(OBJS)
 	$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
 
@@ -333,7 +336,7 @@ clean:
 # Examples
 #
 
-main: examples/main/main.cpp                                  build-info.h ggml.o llama.o common.o $(OBJS)
+main: examples/main/main.cpp                                  build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 	@echo
 	@echo '====  Run ./main -h for help.  ===='

Diff for: examples/CMakeLists.txt

@@ -13,6 +13,8 @@ set(TARGET common)
 add_library(${TARGET} OBJECT
     common.h
     common.cpp
+    grammar-parser.h
+    grammar-parser.cpp
     )
 
 if (BUILD_SHARED_LIBS)

Diff for: examples/common.cpp

@@ -438,6 +438,28 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 break;
             }
             params.input_suffix = argv[i];
+        } else if (arg == "--grammar") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            params.grammar = argv[i];
+        } else if (arg == "--grammar-file") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            std::ifstream file(argv[i]);
+            if (!file) {
+                fprintf(stderr, "error: failed to open file '%s'\n", argv[i]);
+                invalid_param = true;
+                break;
+            }
+            std::copy(
+                std::istreambuf_iterator<char>(file),
+                std::istreambuf_iterator<char>(),
+                std::back_inserter(params.grammar)
+            );
         } else {
             fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
             gpt_print_usage(argc, argv, default_params);
@@ -514,6 +536,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stdout, "                        modifies the likelihood of token appearing in the completion,\n");
     fprintf(stdout, "                        i.e. `--logit-bias 15043+1` to increase likelihood of token ' Hello',\n");
     fprintf(stdout, "                        or `--logit-bias 15043-1` to decrease likelihood of token ' Hello'\n");
+    fprintf(stdout, "  --grammar GRAMMAR     BNF-like grammar to constrain generations (see samples in grammars/ dir)\n");
+    fprintf(stdout, "  --grammar-file FNAME  file to read grammar from\n");
     fprintf(stdout, "  --cfg-negative-prompt PROMPT \n");
     fprintf(stdout, "                        negative prompt to use for guidance. (default: empty)\n");
     fprintf(stdout, "  --cfg-scale N         strength of guidance (default: %f, 1.0 = disable)\n", params.cfg_scale);

Diff for: examples/common.h

@@ -63,6 +63,7 @@ struct gpt_params {
     std::string path_prompt_cache = "";  // path to file for saving/loading prompt eval state
     std::string input_prefix      = "";  // string to prefix user inputs with
     std::string input_suffix      = "";  // string to suffix user inputs with
+    std::string grammar           = "";  // optional BNF-like grammar to constrain sampling
     std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
 
     std::string lora_adapter = "";  // lora adapter path