diff options
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 6 | ||||
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 8 |
2 files changed, 14 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 90d5efec..037837da 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -274,6 +274,8 @@ class MODEL_TENSOR(IntEnum): ATTN_Q_B = auto() ATTN_KV_A_MQA = auto() ATTN_KV_B = auto() + ATTN_K_B = auto() + ATTN_V_B = auto() ATTN_Q_A_NORM = auto() ATTN_KV_A_NORM = auto() FFN_SUB_NORM = auto() @@ -403,6 +405,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = { MODEL_TENSOR.ATTN_Q_B: "blk.{bid}.attn_q_b", MODEL_TENSOR.ATTN_KV_A_MQA: "blk.{bid}.attn_kv_a_mqa", MODEL_TENSOR.ATTN_KV_B: "blk.{bid}.attn_kv_b", + MODEL_TENSOR.ATTN_K_B: "blk.{bid}.attn_k_b", + MODEL_TENSOR.ATTN_V_B: "blk.{bid}.attn_v_b", MODEL_TENSOR.ATTN_Q_A_NORM: "blk.{bid}.attn_q_a_norm", MODEL_TENSOR.ATTN_KV_A_NORM: "blk.{bid}.attn_kv_a_norm", MODEL_TENSOR.ATTN_SUB_NORM: "blk.{bid}.attn_sub_norm", @@ -967,6 +971,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.ATTN_Q_B, MODEL_TENSOR.ATTN_KV_A_MQA, MODEL_TENSOR.ATTN_KV_B, + MODEL_TENSOR.ATTN_K_B, + MODEL_TENSOR.ATTN_V_B, MODEL_TENSOR.ATTN_Q_A_NORM, MODEL_TENSOR.ATTN_KV_A_NORM, MODEL_TENSOR.ATTN_OUT, diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index a70b69c5..e8725426 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -446,6 +446,14 @@ class TensorNameMap: "model.layers.{bid}.self_attn.kv_b_proj", # deepseek2 ), + MODEL_TENSOR.ATTN_K_B: ( + "model.layers.{bid}.self_attn.k_b_proj", # deepseek2 + ), + + MODEL_TENSOR.ATTN_V_B: ( + "model.layers.{bid}.self_attn.v_b_proj", # deepseek2 + ), + MODEL_TENSOR.ATTN_Q_A_NORM: ( "model.layers.{bid}.self_attn.q_a_layernorm", # deepseek2 ), |