diff options
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 17 | ||||
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 37 |
2 files changed, 40 insertions, 14 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 ], diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 6fcbdbc1..446c6b68 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -79,6 +79,7 @@ class TensorNameMap: "language_model.encoder.layers.{bid}.input_layernorm", # persimmon "model.layers.{bid}.ln1", # yi "transformer.h.{bid}.ln", # phi2 + "model.layers.layers.{bid}.norm", # plamo ), # Attention norm 2 @@ -99,26 +100,29 @@ class TensorNameMap: # Attention query MODEL_TENSOR.ATTN_Q: ( - "model.layers.{bid}.self_attn.q_proj", # llama-hf - "layers.{bid}.attention.wq", # llama-pth - "encoder.layer.{bid}.attention.self.query", # bert - "transformer.h.{bid}.attn.q_proj", # gpt-j + "model.layers.{bid}.self_attn.q_proj", # llama-hf + "layers.{bid}.attention.wq", # llama-pth + "encoder.layer.{bid}.attention.self.query", # bert + "transformer.h.{bid}.attn.q_proj", # gpt-j + "model.layers.layers.{bid}.self_attn.q_proj", # plamo ), # Attention key MODEL_TENSOR.ATTN_K: ( - "model.layers.{bid}.self_attn.k_proj", # llama-hf - "layers.{bid}.attention.wk", # llama-pth - "encoder.layer.{bid}.attention.self.key", # bert - "transformer.h.{bid}.attn.k_proj", # gpt-j + "model.layers.{bid}.self_attn.k_proj", # llama-hf + "layers.{bid}.attention.wk", # llama-pth + "encoder.layer.{bid}.attention.self.key", # bert + "transformer.h.{bid}.attn.k_proj", # gpt-j + "model.layers.layers.{bid}.self_attn.k_proj", # plamo ), # Attention value MODEL_TENSOR.ATTN_V: ( - "model.layers.{bid}.self_attn.v_proj", # llama-hf - "layers.{bid}.attention.wv", # llama-pth - "encoder.layer.{bid}.attention.self.value", # bert - "transformer.h.{bid}.attn.v_proj", # gpt-j + "model.layers.{bid}.self_attn.v_proj", # llama-hf + "layers.{bid}.attention.wv", # llama-pth + "encoder.layer.{bid}.attention.self.value", # bert + "transformer.h.{bid}.attn.v_proj", # gpt-j + "model.layers.layers.{bid}.self_attn.v_proj", # plamo ), # Attention output @@ -134,12 +138,14 @@ class TensorNameMap: "transformer.h.{bid}.attn.out_proj", # gpt-j "language_model.encoder.layers.{bid}.self_attention.dense", # persimmon "transformer.h.{bid}.mixer.out_proj", # phi2 + "model.layers.layers.{bid}.self_attn.o_proj", # plamo ), # Rotary embeddings MODEL_TENSOR.ATTN_ROT_EMBD: ( - "model.layers.{bid}.self_attn.rotary_emb.inv_freq", # llama-hf - "layers.{bid}.attention.inner_attention.rope.freqs", # llama-pth + "model.layers.{bid}.self_attn.rotary_emb.inv_freq", # llama-hf + "layers.{bid}.attention.inner_attention.rope.freqs", # llama-pth + "model.layers.layers.{bid}.self_attn.rotary_emb.inv_freq", # plamo ), # Feed-forward norm @@ -174,6 +180,7 @@ class TensorNameMap: "language_model.encoder.layers.{bid}.mlp.dense_h_to_4h", # persimmon "transformer.h.{bid}.mlp.w1", # qwen "transformer.h.{bid}.mlp.fc1", # phi2 + "model.layers.layers.{bid}.mlp.up_proj", # plamo ), MODEL_TENSOR.FFN_UP_EXP: ( @@ -186,6 +193,7 @@ class TensorNameMap: "model.layers.{bid}.mlp.gate_proj", # llama-hf refact "layers.{bid}.feed_forward.w1", # llama-pth "transformer.h.{bid}.mlp.w2", # qwen + "model.layers.layers.{bid}.mlp.gate_proj", # plamo ), MODEL_TENSOR.FFN_GATE_EXP: ( @@ -206,6 +214,7 @@ class TensorNameMap: "transformer.h.{bid}.mlp.fc_out", # gpt-j "language_model.encoder.layers.{bid}.mlp.dense_4h_to_h", # persimmon "transformer.h.{bid}.mlp.fc2", # phi2 + "model.layers.layers.{bid}.mlp.down_proj", # plamo ), MODEL_TENSOR.FFN_DOWN_EXP: ( |