diff options
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 11 | ||||
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 10 |
2 files changed, 19 insertions, 2 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index c9be2111..ae62cc57 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -370,7 +370,16 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.FFN_UP, ], MODEL_ARCH.GPT2: [ - # TODO + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.POS_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.OUTPUT, + MODEL_TENSOR.ATTN_NORM, + MODEL_TENSOR.ATTN_QKV, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_NORM, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, ], MODEL_ARCH.PHI2: [ MODEL_TENSOR.TOKEN_EMBD, diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 0b8f7041..80c1d544 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -17,6 +17,7 @@ class TensorNameMap: "tok_embeddings", # llama-pth "embeddings.word_embeddings", # bert "language_model.embedding.word_embeddings", # persimmon + "wte", # gpt2 "transformer.embd.wte", # phi2 ), @@ -34,6 +35,7 @@ class TensorNameMap: MODEL_TENSOR.POS_EMBD: ( "transformer.wpe", # gpt2 "embeddings.position_embeddings", # bert + "wpe", # gpt2 ), # Output @@ -53,7 +55,7 @@ class TensorNameMap: "norm", # llama-pth "embeddings.LayerNorm", # bert "transformer.norm_f", # mpt - "ln_f", # refact bloom qwen + "ln_f", # refact bloom qwen gpt2 "language_model.encoder.final_layernorm", # persimmon "lm_head.ln", # phi2 ), @@ -78,6 +80,7 @@ class TensorNameMap: "encoder.layer.{bid}.attention.output.LayerNorm", # bert "language_model.encoder.layers.{bid}.input_layernorm", # persimmon "model.layers.{bid}.ln1", # yi + "h.{bid}.ln_1", # gpt2 "transformer.h.{bid}.ln", # phi2 "model.layers.layers.{bid}.norm", # plamo ), @@ -95,6 +98,7 @@ class TensorNameMap: "transformer.h.{bid}.self_attention.query_key_value", # falcon "h.{bid}.self_attention.query_key_value", # bloom "language_model.encoder.layers.{bid}.self_attention.query_key_value", # persimmon + "h.{bid}.attn.c_attn", # gpt2 "transformer.h.{bid}.mixer.Wqkv", # phi2 ), @@ -137,6 +141,7 @@ class TensorNameMap: "encoder.layer.{bid}.attention.output.dense", # bert "transformer.h.{bid}.attn.out_proj", # gpt-j "language_model.encoder.layers.{bid}.self_attention.dense", # persimmon + "h.{bid}.attn.c_proj", # gpt2 "transformer.h.{bid}.mixer.out_proj", # phi2 "model.layers.layers.{bid}.self_attn.o_proj", # plamo ), @@ -159,6 +164,7 @@ class TensorNameMap: "encoder.layer.{bid}.output.LayerNorm", # bert "language_model.encoder.layers.{bid}.post_attention_layernorm", # persimmon "model.layers.{bid}.ln2", # yi + "h.{bid}.ln_2", # gpt2 ), MODEL_TENSOR.FFN_GATE_INP: ( @@ -179,6 +185,7 @@ class TensorNameMap: "transformer.h.{bid}.mlp.fc_in", # gpt-j "language_model.encoder.layers.{bid}.mlp.dense_h_to_4h", # persimmon "transformer.h.{bid}.mlp.w1", # qwen + "h.{bid}.mlp.c_fc", # gpt2 "transformer.h.{bid}.mlp.fc1", # phi2 "model.layers.layers.{bid}.mlp.up_proj", # plamo ), @@ -218,6 +225,7 @@ class TensorNameMap: "encoder.layer.{bid}.output.dense", # bert "transformer.h.{bid}.mlp.fc_out", # gpt-j "language_model.encoder.layers.{bid}.mlp.dense_4h_to_h", # persimmon + "h.{bid}.mlp.c_proj", # gpt2 "transformer.h.{bid}.mlp.fc2", # phi2 "model.layers.layers.{bid}.mlp.down_proj", # plamo ), |