diff options
| author | Ben Harris <mail@bharr.is> | 2025-04-29 16:02:08 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-04-29 10:02:08 +0200 |
| commit | 1064f5bc312f61e5a1b7ef3fef918be300f74641 (patch) | |
| tree | bdcb5b56d509ec24395c8c4a18af48634d91a8b8 /gguf-py | |
| parent | 99b87a375fdf8cc409c4a95cf451f0462f56f71b (diff) | |
Apply Qwen3 PR from llama.cpp (#355)
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 6e03f9a4..4f0681b4 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -331,6 +331,8 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = { MODEL_ARCH.QWEN: "qwen", MODEL_ARCH.QWEN2: "qwen2", MODEL_ARCH.QWEN2MOE: "qwen2moe", + MODEL_ARCH.QWEN3: "qwen3", + MODEL_ARCH.QWEN3MOE: "qwen3moe", MODEL_ARCH.PHI2: "phi2", MODEL_ARCH.PHI3: "phi3", MODEL_ARCH.PLAMO: "plamo", @@ -701,6 +703,40 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_DOWN_SHEXP, MODEL_TENSOR.FFN_UP_SHEXP, ], + MODEL_ARCH.QWEN3: [ + 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_Q_NORM, + MODEL_TENSOR.ATTN_K, + MODEL_TENSOR.ATTN_K_NORM, + MODEL_TENSOR.ATTN_V, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_NORM, + MODEL_TENSOR.FFN_GATE, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, + ], + MODEL_ARCH.QWEN3MOE: [ + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.OUTPUT, + MODEL_TENSOR.ATTN_NORM, + MODEL_TENSOR.ATTN_Q, + MODEL_TENSOR.ATTN_Q_NORM, + MODEL_TENSOR.ATTN_K, + MODEL_TENSOR.ATTN_K_NORM, + MODEL_TENSOR.ATTN_V, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_NORM, + MODEL_TENSOR.FFN_GATE_INP, + MODEL_TENSOR.FFN_GATE_EXP, + MODEL_TENSOR.FFN_DOWN_EXP, + MODEL_TENSOR.FFN_UP_EXP, + ], MODEL_ARCH.PLAMO: [ MODEL_TENSOR.TOKEN_EMBD, MODEL_TENSOR.OUTPUT_NORM, |