From 593cc8653dac4b08ae72405882ee376bc81e7ac5 Mon Sep 17 00:00:00 2001
From: liyuhang <yuhang.li@aminer.cn>
Date: Sun, 26 Jan 2025 12:53:59 +0800
Subject: [PATCH] fix ci err

---
 src/llama-model.cpp | 3 ---
 src/llama.cpp       | 1 -
 2 files changed, 4 deletions(-)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index e27169ca1..7026c009f 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -3068,7 +3068,6 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                 } break;
             case LLM_ARCH_CHATGLM:
                 {
-                    printf("Loading ChatGLM model...\n");
                     tok_embd   = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD,      "weight"), {n_embd, n_vocab}, 0);
 
                     // output
@@ -3077,14 +3076,12 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
 
                     for (int i = 0; i < n_layer; ++i) {
                         auto & layer = layers[i];
-                        printf("Loading layer %d...\n",i);
 
                         layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
                         layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, llama_model_loader::TENSOR_NOT_REQUIRED);
                         layer.bqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "bias", i),   {n_embd + 2*n_embd_gqa}, llama_model_loader::TENSOR_NOT_REQUIRED);
 
                         if(layer.wqkv == nullptr){
-                            printf("Loading W q k v %d...\n",i);
                             layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
                             layer.wk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_k_gqa}, 0);
                             layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_v_gqa}, 0);
diff --git a/src/llama.cpp b/src/llama.cpp
index 826b627da..6e6949f92 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -7189,7 +7189,6 @@ struct llm_build_context {
         const int64_t n_embd_head = hparams.n_embd_head_v;
         const int64_t n_embd_gqa  = hparams.n_embd_v_gqa();
         GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
-        bool is_lite = (hparams.n_layer == 27);
 
         struct ggml_tensor * cur;
         struct ggml_tensor * inpL;