convert : add BPE pre-tokenization for DBRX (#7132)

* Add BPE pre-tokenization for DBRX.

* Add vocab GGUFs.

* Remove test.

* Remove GGUFs.

convert-hf-to-gguf-update.py

@@ -68,6 +68,7 @@ models = [
     {"name": "refact",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
     {"name": "command-r",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
     {"name": "olmo",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
+    {"name": "dbrx",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
 ]
 
 # make directory "models/tokenizers" if it doesn't exist
@@ -151,6 +152,8 @@ for model in models:
     # print the "pre_tokenizer" content from the tokenizer.json
     with open(f"models/tokenizers/{name}/tokenizer.json", "r", encoding="utf-8") as f:
         cfg = json.load(f)
+        normalizer = cfg["normalizer"]
+        logger.info("normalizer: " + json.dumps(normalizer, indent=4))
         pre_tokenizer = cfg["pre_tokenizer"]
         logger.info("pre_tokenizer: " + json.dumps(pre_tokenizer, indent=4))
 

convert-hf-to-gguf.py

@@ -317,6 +317,9 @@ class Model(ABC):
         if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
             # ref: https://huggingface.co/allenai/OLMo-1.7-7B-hf
             res = "olmo"
+        if chkhsh == "a8594e3edff7c29c003940395316294b2c623e09894deebbc65f33f1515df79e":
+            # ref: https://huggingface.co/databricks/dbrx-instruct
+            res = "dbrx"
 
         if res is None:
             logger.warning("\n")

llama.cpp

@@ -4394,6 +4394,9 @@ static void llm_load_vocab(
             } else if (
                 tokenizer_pre == "olmo") {
                 vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_OLMO;
+            } else if (
+                tokenizer_pre == "dbrx") {
+                vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DBRX;
             } else {
                 throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
             }
@@ -12200,6 +12203,7 @@ struct llm_tokenizer_bpe {
             case LLAMA_VOCAB_TYPE_BPE:
                 switch (vocab.type_pre) {
                     case LLAMA_VOCAB_PRE_TYPE_LLAMA3:
+                    case LLAMA_VOCAB_PRE_TYPE_DBRX:
                         word_collection = unicode_regex_split(text, {
                             // original regex from tokenizer.json
                             //"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",

llama.h

@@ -82,6 +82,7 @@ extern "C" {
         LLAMA_VOCAB_PRE_TYPE_REFACT         = 8,
         LLAMA_VOCAB_PRE_TYPE_COMMAND_R      = 9,
         LLAMA_VOCAB_PRE_TYPE_OLMO           = 10,
+        LLAMA_VOCAB_PRE_TYPE_DBRX           = 11,
     };
 
     // note: these values should be synchronized with ggml_rope

scripts/compare-llama-bench.py

@@ -93,11 +93,14 @@ help_s = (
     "specified values are averaged WITHOUT weighing by the --repetitions parameter of llama-bench."
 )
 parser.add_argument("-s", "--show", help=help_s)
+parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
 
 known_args, unknown_args = parser.parse_known_args()
 
+logging.basicConfig(level=logging.DEBUG if known_args.verbose else logging.INFO)
+
 if unknown_args:
-    logger.error(f"Received unknown args: {unknown_args}.")
+    logger.error(f"Received unknown args: {unknown_args}.\n")
     parser.print_help()
     sys.exit(1)
 
@@ -110,7 +113,7 @@ if input_file is None:
         input_file = sqlite_files[0]
 
 if input_file is None:
-    logger.error("Cannot find a suitable input file, please provide one.")
+    logger.error("Cannot find a suitable input file, please provide one.\n")
     parser.print_help()
     sys.exit(1)
 
@@ -202,12 +205,12 @@ elif repo is not None:
     hexsha8_baseline = find_parent_in_data(repo.heads.master.commit)
 
     if hexsha8_baseline is None:
-        logger.error("No baseline was provided and did not find data for any master branch commits.")
+        logger.error("No baseline was provided and did not find data for any master branch commits.\n")
         parser.print_help()
         sys.exit(1)
 else:
     logger.error("No baseline was provided and the current working directory "
-                 "is not part of a git repository from which a baseline could be inferred.")
+                 "is not part of a git repository from which a baseline could be inferred.\n")
     parser.print_help()
     sys.exit(1)
 
@@ -238,7 +241,7 @@ elif repo is not None:
             break
 
     if hexsha8_compare is None:
-        logger.error("No compare target was provided and did not find data for any non-master commits.")
+        logger.error("No compare target was provided and did not find data for any non-master commits.\n")
         parser.print_help()
         sys.exit(1)
 else:
@@ -361,7 +364,7 @@ if "gpu_info" in show:
 headers  = [PRETTY_NAMES[p] for p in show]
 headers += ["Test", f"t/s {name_baseline}", f"t/s {name_compare}", "Speedup"]
 
-logger.info(tabulate(
+print(tabulate( # noqa: NP100
     table,
     headers=headers,
     floatfmt=".2f",