diff options
| author | Jared Van Bortel <jared@nomic.ai> | 2024-02-13 12:03:53 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-13 12:03:53 -0500 |
| commit | ea9c8e11436ad50719987fa23a289c74b7b40d40 (patch) | |
| tree | be96ed8c8de113399a43b4017030a5ed1e1e8e3b /gguf-py/gguf/constants.py | |
| parent | c4e6dd59e45ef7b14f7763fb073b517395dc176c (diff) | |
llama : add support for Nomic Embed (#5468)
Diffstat (limited to 'gguf-py/gguf/constants.py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 56 |
1 files changed, 36 insertions, 20 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 644e1589..5fba0171 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -87,27 +87,28 @@ class Keys: class MODEL_ARCH(IntEnum): - LLAMA = auto() - FALCON = auto() - BAICHUAN = auto() - GPT2 = auto() - GPTJ = auto() - GPTNEOX = auto() - MPT = auto() - STARCODER = auto() - PERSIMMON = auto() - REFACT = auto() - BERT = auto() - BLOOM = auto() - STABLELM = auto() - QWEN = auto() - QWEN2 = auto() - PHI2 = auto() - PLAMO = auto() - CODESHELL = auto() - ORION = auto() + LLAMA = auto() + FALCON = auto() + BAICHUAN = auto() + GPT2 = auto() + GPTJ = auto() + GPTNEOX = auto() + MPT = auto() + STARCODER = auto() + PERSIMMON = auto() + REFACT = auto() + BERT = auto() + NOMIC_BERT = auto() + BLOOM = auto() + STABLELM = auto() + QWEN = auto() + QWEN2 = auto() + PHI2 = auto() + PLAMO = auto() + CODESHELL = auto() + ORION = auto() INTERNLM2 = auto() - MINICPM = auto() + MINICPM = auto() class MODEL_TENSOR(IntEnum): @@ -153,6 +154,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = { MODEL_ARCH.PERSIMMON: "persimmon", MODEL_ARCH.REFACT: "refact", MODEL_ARCH.BERT: "bert", + MODEL_ARCH.NOMIC_BERT: "nomic-bert", MODEL_ARCH.BLOOM: "bloom", MODEL_ARCH.STABLELM: "stablelm", MODEL_ARCH.QWEN: "qwen", @@ -282,6 +284,20 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_UP, MODEL_TENSOR.LAYER_OUT_NORM, ], + MODEL_ARCH.NOMIC_BERT: [ + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.TOKEN_EMBD_NORM, + MODEL_TENSOR.TOKEN_TYPES, + MODEL_TENSOR.POS_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.ATTN_OUT_NORM, + MODEL_TENSOR.ATTN_QKV, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_GATE, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, + MODEL_TENSOR.LAYER_OUT_NORM, + ], MODEL_ARCH.MPT: [ MODEL_TENSOR.TOKEN_EMBD, MODEL_TENSOR.OUTPUT_NORM, |