diff options
| author | Ashish <1856117+ashishdatta@users.noreply.github.com> | 2024-04-16 08:48:35 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-16 18:48:35 +0300 |
| commit | dbceec87c0221ec952e69448df6a71f1372a7487 (patch) | |
| tree | 3c8773f6eccea909c670c16cf5b3bbb8e65fe12c /gguf-py | |
| parent | f4dea7da1841a92d2788b0535063abf2f0e28461 (diff) | |
llama : add StableLM2 12B (#6635)
* StableLM2 12B support for huggingface -> GGUF
* StableLM12 tensormapping and constants
* StableLM-2-12b model support
* fix
* Added 12B support
* Removed autoformatting; resolved bug where model_arch was not selecting StableLM2
* Formatting
* Do QK norm stacking in model conversion step
* Converge StableLM and StableLM2 code to simplify graph construction
* Fix accidental removal
* Removed warnings
* Revert formatter
* Move QK norm stack to private function so it's easier to read
* refactor stablelm graph builder to support 1.6, 3b and 12b more efficiently
* Proper check for None type for new_name to avoid crash; formatting; revert change to base class `write_tensors()`
* Format
* Formatting
* format
Co-authored-by: compilade <git@compilade.net>
* Fix incorrect check for K norm
* space after commas; Keep indentation multiple of 4 spaces
* Flake8 format
* Removed unnecessary conditional branches
* Removed unused comment
* Fixed incorrect tensor passing
* Format
---------
Co-authored-by: compilade <git@compilade.net>
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index df861164..4b0b6c4c 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -455,6 +455,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_GATE, MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_UP, + MODEL_TENSOR.ATTN_Q_NORM, + MODEL_TENSOR.ATTN_K_NORM, ], MODEL_ARCH.QWEN: [ MODEL_TENSOR.TOKEN_EMBD, |