diff options
| author | fairydreaming <166155368+fairydreaming@users.noreply.github.com> | 2024-05-24 14:31:13 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-24 14:31:13 +0200 |
| commit | fbca2f27fc7fa9aa4a8ad0357478fdb908472908 (patch) | |
| tree | 9226fa114f6e0f6578c6946f5a23c7ab76ef0854 /gguf-py/gguf/constants.py | |
| parent | 0df0aa8e43c3378975269a51f9b876c8692e70da (diff) | |
Add support for ArcticForCausalLM (#7020)
* common : increase max number of experts to 128
* common : add tensor LLM_TENSOR_FFN_NORM_EXPS for normalization before MoE that runs in parallel to attention + ffn
* gguf-py : add architecture-specific block mappings that override selected general block mappings
* convert-hf : add model conversion support for ArcticForCausalLM
* convert-hf : use added_tokens_decoder from tokenizer_config.json to redefine tokens from SentencePiece model (only for ArcticForCausalLM)
* llama : add inference support for LLM_ARCH_ARCTIC
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Diffstat (limited to 'gguf-py/gguf/constants.py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 25 |
1 files changed, 25 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 67e23dcc..c9ae259e 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -139,6 +139,7 @@ class MODEL_ARCH(IntEnum): COMMAND_R = auto() DBRX = auto() OLMO = auto() + ARCTIC = auto() class MODEL_TENSOR(IntEnum): @@ -167,6 +168,7 @@ class MODEL_TENSOR(IntEnum): FFN_DOWN = auto() FFN_UP = auto() FFN_ACT = auto() + FFN_NORM_EXP = auto() FFN_GATE_EXP = auto() FFN_DOWN_EXP = auto() FFN_UP_EXP = auto() @@ -218,6 +220,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = { MODEL_ARCH.COMMAND_R: "command-r", MODEL_ARCH.DBRX: "dbrx", MODEL_ARCH.OLMO: "olmo", + MODEL_ARCH.ARCTIC: "arctic", } TENSOR_NAMES: dict[MODEL_TENSOR, str] = { @@ -251,6 +254,7 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = { MODEL_TENSOR.FFN_DOWN_SHEXP: "blk.{bid}.ffn_down_shexp", MODEL_TENSOR.FFN_UP_SHEXP: "blk.{bid}.ffn_up_shexp", MODEL_TENSOR.FFN_ACT: "blk.{bid}.ffn", + MODEL_TENSOR.FFN_NORM_EXP: "blk.{bid}.ffn_norm_exps", MODEL_TENSOR.FFN_GATE_EXP: "blk.{bid}.ffn_gate_exps", MODEL_TENSOR.FFN_DOWN_EXP: "blk.{bid}.ffn_down_exps", MODEL_TENSOR.FFN_UP_EXP: "blk.{bid}.ffn_up_exps", @@ -732,6 +736,27 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_UP, ], + MODEL_ARCH.ARCTIC: [ + 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_INP, + MODEL_TENSOR.FFN_NORM, + MODEL_TENSOR.FFN_GATE, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, + MODEL_TENSOR.FFN_NORM_EXP, + MODEL_TENSOR.FFN_GATE_EXP, + MODEL_TENSOR.FFN_DOWN_EXP, + MODEL_TENSOR.FFN_UP_EXP, + ], # TODO } |