mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-30 08:42:00 +00:00 
			
		
		
		
	llama : tokenizer fixes (#2549)
* Merge tokenizer fixes into the gguf branch. * Add test vocabularies
This commit is contained in:
		| @@ -2,6 +2,7 @@ | ||||
|  | ||||
| #pragma once | ||||
|  | ||||
| #define LLAMA_API_CPP // TODO: eliminate me | ||||
| #include "llama.h" | ||||
|  | ||||
| #include <string> | ||||
| @@ -100,12 +101,6 @@ void gpt_print_usage(int argc, char ** argv, const gpt_params & params); | ||||
|  | ||||
| std::string gpt_random_prompt(std::mt19937 & rng); | ||||
|  | ||||
| // | ||||
| // Vocab utils | ||||
| // | ||||
|  | ||||
| std::vector<llama_token> llama_tokenize(struct llama_context * ctx, const std::string & text, bool add_bos); | ||||
|  | ||||
| // | ||||
| // Model utils | ||||
| // | ||||
|   | ||||
		Reference in New Issue
	
	Block a user
	 goerch
					goerch