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 | 16 | ||||
| -rw-r--r-- | gguf-py/pyproject.toml | 2 |
3 files changed, 10 insertions, 14 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 27eaf723..f468802d 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -221,9 +221,9 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = { MODEL_TENSOR.FFN_DOWN: "blk.{bid}.ffn_down", MODEL_TENSOR.FFN_UP: "blk.{bid}.ffn_up", MODEL_TENSOR.FFN_ACT: "blk.{bid}.ffn", - MODEL_TENSOR.FFN_GATE_EXP: "blk.{bid}.ffn_gate.{xid}", - MODEL_TENSOR.FFN_DOWN_EXP: "blk.{bid}.ffn_down.{xid}", - MODEL_TENSOR.FFN_UP_EXP: "blk.{bid}.ffn_up.{xid}", + 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", MODEL_TENSOR.LAYER_OUT_NORM: "blk.{bid}.layer_output_norm", MODEL_TENSOR.SSM_IN: "blk.{bid}.ssm_in", MODEL_TENSOR.SSM_CONV1D: "blk.{bid}.ssm_conv1d", diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 11fd34b8..93a5a455 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -231,9 +231,8 @@ class TensorNameMap: ), MODEL_TENSOR.FFN_UP_EXP: ( - "layers.{bid}.feed_forward.experts.{xid}.w3", # mixtral - "model.layers.{bid}.block_sparse_moe.experts.{xid}.w3", # mixtral - "transformer.decoder_layer.{bid}.moe.{xid}.linear_v", # Grok + "layers.{bid}.feed_forward.experts.w3", # mixtral (merged) + "transformer.decoder_layer.{bid}.moe.linear_v", # Grok (merged) ), # AWQ-activation gate @@ -252,9 +251,8 @@ class TensorNameMap: ), MODEL_TENSOR.FFN_GATE_EXP: ( - "layers.{bid}.feed_forward.experts.{xid}.w1", # mixtral - "model.layers.{bid}.block_sparse_moe.experts.{xid}.w1", # mixtral - "transformer.decoder_layer.{bid}.moe.{xid}.linear" # Grok + "layers.{bid}.feed_forward.experts.w1", # mixtral (merged) + "transformer.decoder_layer.{bid}.moe.linear" # Grok (merged) ), # Feed-forward down @@ -280,10 +278,8 @@ class TensorNameMap: ), MODEL_TENSOR.FFN_DOWN_EXP: ( - "layers.{bid}.feed_forward.experts.{xid}.w2", # mixtral - "model.layers.{bid}.block_sparse_moe.experts.{xid}.w2", # mixtral - "transformer.decoder_layer.{bid}.moe.{xid}.linear_1", # Grok - + "layers.{bid}.feed_forward.experts.w2", # mixtral (merged) + "transformer.decoder_layer.{bid}.moe.linear_1", # Grok (merged) ), MODEL_TENSOR.ATTN_Q_NORM: ( diff --git a/gguf-py/pyproject.toml b/gguf-py/pyproject.toml index 96396e04..13cbfffb 100644 --- a/gguf-py/pyproject.toml +++ b/gguf-py/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "gguf" -version = "0.8.0" +version = "0.9.0" description = "Read and write ML models in GGUF for GGML" authors = ["GGML <ggml@ggml.ai>"] packages = [ |