Merge commit 'c05e8c9934' into concedo_experimental

convert_hf_to_gguf.py

@@ -478,6 +478,11 @@ class Model:
             return modelcls
         return func
 
+    @classmethod
+    def print_registered_models(cls):
+        for name in sorted(cls._model_classes.keys()):
+            logger.error(f"- {name}")
+
     @classmethod
     def from_model_architecture(cls, arch: str) -> type[Model]:
         try:
@@ -4929,6 +4934,7 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "model", type=Path,
         help="directory containing model file",
+        nargs="?",
     )
     parser.add_argument(
         "--use-temp-file", action="store_true",
@@ -4966,8 +4972,15 @@ def parse_args() -> argparse.Namespace:
         "--metadata", type=Path,
         help="Specify the path for an authorship metadata override file"
     )
+    parser.add_argument(
+        "--print-supported-models", action="store_true",
+        help="Print the supported models"
+    )
 
-    return parser.parse_args()
+    args = parser.parse_args()
+    if not args.print_supported_models and args.model is None:
+        parser.error("the following arguments are required: model")
+    return args
 
 
 def split_str_to_n_bytes(split_str: str) -> int:
@@ -4991,6 +5004,11 @@ def split_str_to_n_bytes(split_str: str) -> int:
 def main() -> None:
     args = parse_args()
 
+    if args.print_supported_models:
+        logger.error("Supported models:")
+        Model.print_registered_models()
+        sys.exit(0)
+
     if args.verbose:
         logging.basicConfig(level=logging.DEBUG)
     else:

examples/tts/README.md

@@ -0,0 +1,80 @@
+# llama.cpp/example/tts
+This example demonstrates the Text To Speech feature. It uses a
+[model](https://www.outeai.com/blog/outetts-0.2-500m) from
+[outeai](https://www.outeai.com/).
+
+## Quickstart
+If you have built llama.cpp with `-DLLAMA_CURL=ON` you can simply run the
+following command and the required models will be downloaded automatically:
+```console
+$ build/bin/llama-tts --tts-oute-default -p "Hello world" && aplay output.wav
+```
+For details about the models and how to convert them to the required format
+see the following sections.
+
+### Model conversion
+Checkout or download the model that contains the LLM model:
+```console
+$ pushd models
+$ git clone --branch main --single-branch --depth 1 https://huggingface.co/OuteAI/OuteTTS-0.2-500M
+$ cd OuteTTS-0.2-500M && git lfs install && git lfs pull
+$ popd
+```
+Convert the model to .gguf format:
+```console
+(venv) python convert_hf_to_gguf.py models/OuteTTS-0.2-500M \
+    --outfile models/outetts-0.2-0.5B-f16.gguf --outtype f16
+```
+The generated model will be `models/outetts-0.2-0.5B-f16.gguf`.
+
+We can optionally quantize this to Q8_0 using the following command:
+```console
+$ build/bin/llama-quantize models/outetts-0.2-0.5B-f16.gguf \
+    models/outetts-0.2-0.5B-q8_0.gguf q8_0
+```
+The quantized model will be `models/outetts-0.2-0.5B-q8_0.gguf`.
+
+Next we do something simlar for the audio decoder. First download or checkout
+the model for the voice decoder:
+```console
+$ pushd models
+$ git clone --branch main --single-branch --depth 1 https://huggingface.co/novateur/WavTokenizer-large-speech-75token
+$ cd WavTokenizer-large-speech-75token && git lfs install && git lfs pull
+$ popd
+```
+This model file is PyTorch checkpoint (.ckpt) and we first need to convert it to
+huggingface format:
+```console
+(venv) python examples/tts/convert_pt_to_hf.py \
+    models/WavTokenizer-large-speech-75token/wavtokenizer_large_speech_320_24k.ckpt
+...
+Model has been successfully converted and saved to models/WavTokenizer-large-speech-75token/model.safetensors
+Metadata has been saved to models/WavTokenizer-large-speech-75token/index.json
+Config has been saved to models/WavTokenizer-large-speech-75tokenconfig.json
+```
+Then we can convert the huggingface format to gguf:
+```console
+(venv) python convert_hf_to_gguf.py models/WavTokenizer-large-speech-75token \
+    --outfile models/wavtokenizer-large-75-f16.gguf --outtype f16
+...
+INFO:hf-to-gguf:Model successfully exported to models/wavtokenizer-large-75-f16.gguf
+```
+
+### Running the example
+
+With both of the models generated, the LLM model and the voice decoder model,
+we can run the example:
+```console
+$ build/bin/llama-tts -m  ./models/outetts-0.2-0.5B-q8_0.gguf \
+    -mv ./models/wavtokenizer-large-75-f16.gguf \
+    -p "Hello world"
+...
+main: audio written to file 'output.wav'
+```
+The output.wav file will contain the audio of the prompt. This can be heard
+by playing the file with a media player. On Linux the following command will
+play the audio:
+```console
+$ aplay output.wav
+```
+

gguf-py/README.md

@@ -15,6 +15,8 @@ pip install gguf
 
 [examples/writer.py](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/examples/writer.py) — Generates `example.gguf` in the current directory to demonstrate generating a GGUF file. Note that this file cannot be used as a model.
 
+[examples/reader.py](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/examples/reader.py) — Extracts and displays key-value pairs and tensor details from a GGUF file in a readable format.
+
 [gguf/scripts/gguf_dump.py](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/gguf/scripts/gguf_dump.py) — Dumps a GGUF file's metadata to the console.
 
 [gguf/scripts/gguf_set_metadata.py](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/gguf/scripts/gguf_set_metadata.py) — Allows changing simple metadata values in a GGUF file by key.

gguf-py/gguf/scripts/gguf_convert_endian.py

@@ -11,8 +11,8 @@ from pathlib import Path
 import numpy as np
 
 # Necessary to load the local gguf package
-if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
-    sys.path.insert(0, str(Path(__file__).parent.parent))
+if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
+    sys.path.insert(0, str(Path(__file__).parent.parent.parent))
 
 import gguf
 

gguf-py/gguf/scripts/gguf_dump.py

@@ -12,8 +12,8 @@ from typing import Any
 import numpy as np
 
 # Necessary to load the local gguf package
-if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
-    sys.path.insert(0, str(Path(__file__).parent.parent))
+if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
+    sys.path.insert(0, str(Path(__file__).parent.parent.parent))
 
 from gguf import GGUFReader, GGUFValueType, ReaderTensor  # noqa: E402
 

gguf-py/gguf/scripts/gguf_hash.py

@@ -13,8 +13,8 @@ from pathlib import Path
 from tqdm import tqdm
 
 # Necessary to load the local gguf package
-if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
-    sys.path.insert(0, str(Path(__file__).parent.parent))
+if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
+    sys.path.insert(0, str(Path(__file__).parent.parent.parent))
 
 from gguf import GGUFReader  # noqa: E402
 

gguf-py/gguf/scripts/gguf_new_metadata.py

@@ -13,8 +13,8 @@ from tqdm import tqdm
 from typing import Any, Sequence, NamedTuple
 
 # Necessary to load the local gguf package
-if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
-    sys.path.insert(0, str(Path(__file__).parent.parent))
+if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
+    sys.path.insert(0, str(Path(__file__).parent.parent.parent))
 
 import gguf
 

gguf-py/gguf/scripts/gguf_set_metadata.py

@@ -6,8 +6,8 @@ import sys
 from pathlib import Path
 
 # Necessary to load the local gguf package
-if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent / 'gguf-py').exists():
-    sys.path.insert(0, str(Path(__file__).parent.parent))
+if "NO_LOCAL_GGUF" not in os.environ and (Path(__file__).parent.parent.parent.parent / 'gguf-py').exists():
+    sys.path.insert(0, str(Path(__file__).parent.parent.parent))
 
 from gguf import GGUFReader  # noqa: E402
 

gguf-py/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gguf"
-version = "0.14.0"
+version = "0.15.0"
 description = "Read and write ML models in GGUF for GGML"
 authors = ["GGML <ggml@ggml.ai>"]
 packages = [