diff options
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 2 | ||||
| -rw-r--r-- | gguf-py/gguf/gguf_writer.py | 6 |
2 files changed, 8 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index ae62cc57..f0a1c51f 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -46,6 +46,8 @@ class Keys: HEAD_COUNT_KV = "{arch}.attention.head_count_kv" MAX_ALIBI_BIAS = "{arch}.attention.max_alibi_bias" CLAMP_KQV = "{arch}.attention.clamp_kqv" + KEY_LENGTH = "{arch}.attention.key_length" + VALUE_LENGTH = "{arch}.attention.value_length" LAYERNORM_EPS = "{arch}.attention.layer_norm_epsilon" LAYERNORM_RMS_EPS = "{arch}.attention.layer_norm_rms_epsilon" diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py index 73e02160..d93aaa87 100644 --- a/gguf-py/gguf/gguf_writer.py +++ b/gguf-py/gguf/gguf_writer.py @@ -333,6 +333,12 @@ class GGUFWriter: def add_head_count_kv(self, count: int) -> None: self.add_uint32(Keys.Attention.HEAD_COUNT_KV.format(arch=self.arch), count) + def add_key_length(self, length: int) -> None: + self.add_uint32(Keys.Attention.KEY_LENGTH.format(arch=self.arch), length) + + def add_value_length(self, length: int) -> None: + self.add_uint32(Keys.Attention.VALUE_LENGTH.format(arch=self.arch), length) + def add_max_alibi_bias(self, bias: float) -> None: self.add_float32(Keys.Attention.MAX_ALIBI_BIAS.format(arch=self.arch), bias) |