diff options
| author | Michael Podvitskiy <podvitskiymichael@gmail.com> | 2024-03-14 17:21:56 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-14 18:21:56 +0200 |
| commit | 69ff61397d2b7b550dcdda4a35b35128892408b0 (patch) | |
| tree | 70b5bac95a58dcf734e8035c5fd47b92ceb510a1 /gguf-py | |
| parent | 044ec4b2a567f649459ccd20af2f387c784faa51 (diff) | |
llama : support models without vocabulary (#5798)
* additional methods to read model and ctx parameters
* vocab size as a part of a model metadata
* models without vocabulary, convert.py part
* models without vocabulary, llama.cpp part
* PR clean up
* converter scrypt fixes
* llama_vocab_type update (renamed the new key)
* pr review fixes
* revert function renaming
* one more NoVocab assert
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 2 | ||||
| -rw-r--r-- | gguf-py/gguf/gguf_writer.py | 3 |
2 files changed, 5 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 99f71f0a..2d7cf16c 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -32,6 +32,7 @@ class Keys: FILE_TYPE = "general.file_type" class LLM: + VOCAB_SIZE = "{arch}.vocab_size" CONTEXT_LENGTH = "{arch}.context_length" EMBEDDING_LENGTH = "{arch}.embedding_length" BLOCK_COUNT = "{arch}.block_count" @@ -752,6 +753,7 @@ KEY_GENERAL_SOURCE_HF_REPO = Keys.General.SOURCE_HF_REPO KEY_GENERAL_FILE_TYPE = Keys.General.FILE_TYPE # LLM +KEY_VOCAB_SIZE = Keys.LLM.VOCAB_SIZE KEY_CONTEXT_LENGTH = Keys.LLM.CONTEXT_LENGTH KEY_EMBEDDING_LENGTH = Keys.LLM.EMBEDDING_LENGTH KEY_BLOCK_COUNT = Keys.LLM.BLOCK_COUNT diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py index 4d389be9..81b2eb88 100644 --- a/gguf-py/gguf/gguf_writer.py +++ b/gguf-py/gguf/gguf_writer.py @@ -321,6 +321,9 @@ class GGUFWriter: self.data_alignment = alignment self.add_uint32(Keys.General.ALIGNMENT, alignment) + def add_vocab_size(self, size: int) -> None: + self.add_uint32(Keys.LLM.VOCAB_SIZE.format(arch=self.arch), size) + def add_context_length(self, length: int) -> None: self.add_uint32(Keys.LLM.CONTEXT_LENGTH.format(arch=self.arch), length) |