cont

ggml-ci

ci/run.sh

@@ -287,7 +287,7 @@ function gg_run_open_llama_7b_v2 {
     (time cmake -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} -DGGML_CUDA=1 .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
     (time make -j                                                           ) 2>&1 | tee -a $OUT/${ci}-make.log
 
-    python3 ../examples/convert-legacy-llama.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
+    python3 ../examples/convert_legacy_llama.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
 
     model_f16="${path_models}/ggml-model-f16.gguf"
     model_q8_0="${path_models}/ggml-model-q8_0.gguf"

convert_hf_to_gguf.py

@@ -1161,7 +1161,7 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         # So we rearrange them here,, so that we have n_head query weights
         # followed by n_head_kv key weights followed by n_head_kv value weights,
         # in contiguous fashion.
-        # ref: https://github.com/jploski/ggml/blob/falcon40b/examples/falcon/convert_hf_to_gguf.py
+        # ref: https://github.com/jploski/ggml/blob/falcon40b/examples/falcon/convert-hf-to-gguf.py
 
         if "query_key_value" in name:
             n_head = self.find_hparam(["num_attention_heads", "n_head"])

convert_hf_to_gguf_update.py

@@ -15,7 +15,7 @@
 # - Add a new model to the "models" list
 # - Run the script with your huggingface token:
 #
-#   python3 convert_hf_to_gguf-update.py <huggingface_token>
+#   python3 convert_hf_to_gguf_update.py <huggingface_token>
 #
 # - Copy-paste the generated get_vocab_base_pre() function into convert_hf_to_gguf.py
 # - Update llama.cpp with the new pre-tokenizer if necessary
@@ -37,7 +37,7 @@
 from transformers import AutoTokenizer
 
 logging.basicConfig(level=logging.DEBUG)
-logger = logging.getLogger("convert_hf_to_gguf-update")
+logger = logging.getLogger("convert_hf_to_gguf_update")
 sess = requests.Session()
 
 
@@ -56,10 +56,10 @@ class TOKENIZER_TYPE(IntEnum):
     token = sys.argv[1]
     if not token.startswith("hf_"):
         logger.info("Huggingface token seems invalid")
-        logger.info("Usage: python convert_hf_to_gguf-update.py <huggingface_token>")
+        logger.info("Usage: python convert_hf_to_gguf_update.py <huggingface_token>")
         sys.exit(1)
 else:
-    logger.info("Usage: python convert_hf_to_gguf-update.py <huggingface_token>")
+    logger.info("Usage: python convert_hf_to_gguf_update.py <huggingface_token>")
     sys.exit(1)
 
 # TODO: add models here, base models preferred
@@ -201,7 +201,7 @@ def get_vocab_base_pre(self, tokenizer) -> str:
 
         res = None
 
-        # NOTE: if you get an error here, you need to update the convert_hf_to_gguf-update.py script
+        # NOTE: if you get an error here, you need to update the convert_hf_to_gguf_update.py script
         #       or pull the latest version of the model from Huggingface
         #       don't edit the hashes manually!
 {src_ifs}

docs/HOWTO-add-model.md

@@ -17,7 +17,7 @@ Also, it is important to check that the examples and main ggml backends (CUDA, M
 ### 1. Convert the model to GGUF
 
 This step is done in python with a `convert` script using the [gguf](https://pypi.org/project/gguf/) library.
-Depending on the model architecture, you can use either [convert_hf_to_gguf.py](../convert_hf_to_gguf.py) or [examples/convert-legacy-llama.py](../examples/convert-legacy-llama.py) (for `llama/llama2` models in `.pth` format).
+Depending on the model architecture, you can use either [convert_hf_to_gguf.py](../convert_hf_to_gguf.py) or [examples/convert_legacy_llama.py](../examples/convert_legacy_llama.py) (for `llama/llama2` models in `.pth` format).
 
 The convert script reads the model configuration, tokenizer, tensor names+data and converts them to GGUF metadata and tensors.