diff options
| author | Shintarou Okada <kokuzen@gmail.com> | 2023-12-24 22:35:49 +0900 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-12-24 15:35:49 +0200 |
| commit | 753be377b69bda2d65a7e089f2b7f0c53ef3495e (patch) | |
| tree | b32ae0b6fb10db974322edeeb22021bc43d1e210 /gguf-py/gguf/tensor_mapping.py | |
| parent | 5bf3953d7e9831ea22b0bc017ce97409b801ccf1 (diff) | |
llama : add PLaMo model (#3557)
* add plamo mock
* add tensor loading
* plamo convert
* update norm
* able to compile
* fix norm_rms_eps hparam
* runnable
* use inp_pos
* seems ok
* update kqv code
* remove develop code
* update README
* shuffle attn_q.weight and attn_output.weight for broadcasting
* remove plamo_llm_build_kqv and use llm_build_kqv
* fix style
* update
* llama : remove obsolete KQ_scale
* plamo : fix tensor names for correct GPU offload
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'gguf-py/gguf/tensor_mapping.py')
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 37 |
1 files changed, 23 insertions, 14 deletions
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: ( |