diff options
| author | Shintarou Okada <kokuzen@gmail.com> | 2023-12-24 22:35:49 +0900 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-12-24 15:35:49 +0200 |
| commit | 753be377b69bda2d65a7e089f2b7f0c53ef3495e (patch) | |
| tree | b32ae0b6fb10db974322edeeb22021bc43d1e210 /gguf-py/gguf/constants.py | |
| parent | 5bf3953d7e9831ea22b0bc017ce97409b801ccf1 (diff) | |
llama : add PLaMo model (#3557)
* add plamo mock
* add tensor loading
* plamo convert
* update norm
* able to compile
* fix norm_rms_eps hparam
* runnable
* use inp_pos
* seems ok
* update kqv code
* remove develop code
* update README
* shuffle attn_q.weight and attn_output.weight for broadcasting
* remove plamo_llm_build_kqv and use llm_build_kqv
* fix style
* update
* llama : remove obsolete KQ_scale
* plamo : fix tensor names for correct GPU offload
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'gguf-py/gguf/constants.py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 390dca04..4cd87cdd 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -96,6 +96,7 @@ class MODEL_ARCH(IntEnum): STABLELM = auto() QWEN = auto() PHI2 = auto() + PLAMO = auto() class MODEL_TENSOR(IntEnum): @@ -142,6 +143,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = { MODEL_ARCH.STABLELM: "stablelm", MODEL_ARCH.QWEN: "qwen", MODEL_ARCH.PHI2: "phi2", + MODEL_ARCH.PLAMO: "plamo", } TENSOR_NAMES: dict[MODEL_TENSOR, str] = { @@ -349,6 +351,21 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_UP, ], + MODEL_ARCH.PLAMO: [ + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.OUTPUT, + MODEL_TENSOR.ROPE_FREQS, + MODEL_TENSOR.ATTN_NORM, + MODEL_TENSOR.ATTN_Q, + MODEL_TENSOR.ATTN_K, + MODEL_TENSOR.ATTN_V, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.ATTN_ROT_EMBD, + MODEL_TENSOR.FFN_GATE, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, + ], MODEL_ARCH.GPT2: [ # TODO ], |