diff options
| author | liuwei-git <14815172+liuwei-git@users.noreply.github.com> | 2024-05-22 04:28:32 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-21 23:28:32 +0300 |
| commit | 201cc11afa0a1950e1f632390b2ac6c937a0d8f0 (patch) | |
| tree | 440fb7ecd80b48772a955a80855db29677d172a2 /gguf-py/gguf/gguf_writer.py | |
| parent | 6369bf04336ab60e5c892dd77a3246df91015147 (diff) | |
llama : add phi3 128K model support (#7225)
* add phi3 128k support in convert-hf-to-gguf
* add phi3 128k support in cuda
* address build warnings on llama.cpp
* adjust index value in cuda long rope freq factors
* add long rope support in ggml cpu backend
* make freq factors only depend on ctx size
* remove unused rope scaling type 'su' frin gguf converter
* fix flint warnings on convert-hf-to-gguf.py
* set to the short freq factor when context size is small than trained context size
* add one line of comments
* metal : support rope freq_factors
* ggml : update ggml_rope_ext API to support freq. factors
* backends : add dev messages to support rope freq. factors
* minor : style
* tests : update to use new rope API
* backends : fix pragma semicolons
* minor : cleanup
* llama : move rope factors from KV header to tensors
* llama : remove tmp assert
* cuda : fix compile warning
* convert : read/write n_head_kv
* llama : fix uninitialized tensors
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'gguf-py/gguf/gguf_writer.py')
| -rw-r--r-- | gguf-py/gguf/gguf_writer.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py index d5e323a5..8b41b54e 100644 --- a/gguf-py/gguf/gguf_writer.py +++ b/gguf-py/gguf/gguf_writer.py @@ -433,6 +433,9 @@ class GGUFWriter: def add_rope_scaling_factor(self, value: float) -> None: self.add_float32(Keys.Rope.SCALING_FACTOR.format(arch=self.arch), value) + def add_rope_scaling_attn_factors(self, value: Sequence[float]) -> None: + self.add_float32(Keys.Rope.SCALING_ATTN_FACTOR.format(arch=self.arch), value) + def add_rope_scaling_orig_ctx_len(self, value: int) -> None: self.add_uint32(Keys.Rope.SCALING_ORIG_CTX_LEN.format(arch=self.arch), value) |