vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

adding missing files

Browse source
This commit is contained in:
mike dupont 2023-12-06 10:05:12 -05:00
parent 7eb27b3443
commit d6244ff813
3 changed files with 41 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -102,3 +102,5 @@ tests/test-tokenizer-1-bpe
/#llama.cpp#
#*
\\#*
\\#
#

38
llama-layer.hpp Normal file
View file

@ -0,0 +1,38 @@
struct llama_layer {
// normalization
struct ggml_tensor * attn_norm;
struct ggml_tensor * attn_norm_b;
struct ggml_tensor * attn_norm_2;
struct ggml_tensor * attn_norm_2_b;
struct ggml_tensor * attn_q_norm;
struct ggml_tensor * attn_q_norm_b;
struct ggml_tensor * attn_k_norm;
struct ggml_tensor * attn_k_norm_b;
// attention
struct ggml_tensor * wq;
struct ggml_tensor * wk;
struct ggml_tensor * wv;
struct ggml_tensor * wo;
struct ggml_tensor * wqkv;
// attention bias
struct ggml_tensor * bq;
struct ggml_tensor * bk;
struct ggml_tensor * bv;
struct ggml_tensor * bo;
struct ggml_tensor * bqkv;
// normalization
struct ggml_tensor * ffn_norm;
struct ggml_tensor * ffn_norm_b;
// ff
struct ggml_tensor * ffn_gate; // w1
struct ggml_tensor * ffn_down; // w2
struct ggml_tensor * ffn_up; // w3
// ff bias
struct ggml_tensor * ffn_down_b; // b2
struct ggml_tensor * ffn_up_b; // b3
};

1
plugin_python.hpp Normal file
View file

@ -0,0 +1 @@
std::string process_output_plugin(const std::string input);