public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-21 09:41:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-08-18 20:30:45 +03:00
parent 33c3c2fe2e
commit fc45bb8625
28 changed files with 1877 additions and 255 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-model.h
+25 -4
View File
@@ -39,6 +39,7 @@ enum llm_type {
LLM_TYPE_410M,
LLM_TYPE_450M,
LLM_TYPE_475M,
LLM_TYPE_537M,
LLM_TYPE_700M,
LLM_TYPE_770M,
LLM_TYPE_780M,
@@ -101,8 +102,10 @@ enum llm_type {
LLM_TYPE_A13B,
LLM_TYPE_21B_A3B, // Ernie MoE small
LLM_TYPE_30B_A3B,
LLM_TYPE_106B_A12B, // GLM-4.5-Air
LLM_TYPE_235B_A22B,
LLM_TYPE_300B_A47B, // Ernie MoE big
LLM_TYPE_355B_A32B, // GLM-4.5
LLM_TYPE_E2B,
LLM_TYPE_E4B,
};
@@ -166,6 +169,15 @@ struct llama_layer_shortconv {
struct ggml_tensor * out_proj = nullptr;
};
struct llama_layer_nextn {
struct ggml_tensor * eh_proj = nullptr;
struct ggml_tensor * embed_tokens = nullptr;
struct ggml_tensor * enorm = nullptr;
struct ggml_tensor * hnorm = nullptr;
struct ggml_tensor * shared_head_head = nullptr;
struct ggml_tensor * shared_head_norm = nullptr;
};
struct llama_layer {
// normalization
struct ggml_tensor * attn_norm = nullptr;
@@ -241,10 +253,14 @@ struct llama_layer {
struct ggml_tensor * ffn_up_enc = nullptr;
// ff MoE
struct ggml_tensor * ffn_gate_inp = nullptr;
struct ggml_tensor * ffn_gate_exps = nullptr;
struct ggml_tensor * ffn_down_exps = nullptr;
struct ggml_tensor * ffn_up_exps = nullptr;
struct ggml_tensor * ffn_gate_inp = nullptr;
struct ggml_tensor * ffn_gate_exps = nullptr;
struct ggml_tensor * ffn_down_exps = nullptr;
struct ggml_tensor * ffn_up_exps = nullptr;
struct ggml_tensor * ffn_gate_inp_b = nullptr;
struct ggml_tensor * ffn_gate_exps_b = nullptr;
struct ggml_tensor * ffn_down_exps_b = nullptr;
struct ggml_tensor * ffn_up_exps_b = nullptr;
// ff shared expert (shexp)
struct ggml_tensor * ffn_gate_inp_shexp = nullptr;
@@ -349,11 +365,16 @@ struct llama_layer {
struct ggml_tensor * laurel_r = nullptr;
struct ggml_tensor * laurel_post_norm = nullptr;
// openai-moe
struct ggml_tensor * attn_sinks = nullptr;
struct llama_layer_posnet posnet;
struct llama_layer_convnext convnext;
struct llama_layer_shortconv shortconv;
struct llama_layer_nextn nextn;
};
struct llama_model {