whitespace cleanup

Author: CISC

convert_hf_to_gguf.py

@@ -7186,11 +7186,12 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None):
 
         return super().modify_tensors(data_torch, name, bid)
 
+
 @ModelBase.register("PanguEmbeddedForCausalLM")
 class PanguEmbeddedModel(TextModel):
     model_arch = gguf.MODEL_ARCH.PANGU_EMBED
-    
-    def set_vocab(self):  
+
+    def set_vocab(self):
         self._set_vocab_sentencepiece()
 
         tokenizer_config_file = self.dir_model / 'tokenizer_config.json'

src/llama-chat.cpp

@@ -820,7 +820,7 @@ int32_t llm_chat_apply_template(
         // [unused9]系统：xxx[unused10]
         // [unused9]用户：xxx[unused10]
         // [unused9]助手：xxx[unused10]
-        // ... 
+        // ...
         for (size_t i = 0; i < chat.size(); ++i) {
             const auto & msg = chat[i];
             const std::string & role = msg->role;

src/llama-model.cpp

@@ -6279,7 +6279,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                     // output
                     output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
                     output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
-                    
+
                     // if output is NULL, init from the input tok embed
                     if (output == NULL) {
                         output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);

src/models/pangu-embedded.cpp

@@ -53,16 +53,16 @@ llm_build_pangu_embedded::llm_build_pangu_embedded(const llama_model & model, co
                     ext_factor, attn_factor, beta_fast, beta_slow
                     );
 
-            Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, nullptr, 
-                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, 
+            Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, nullptr,
+                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
                     ext_factor, attn_factor, beta_fast, beta_slow
                     );
 
             cb(Qcur, "Qcur", il);
             cb(Kcur, "Kcur", il);
             cb(Vcur, "Vcur", il);
 
-            cur = build_attn(inp_attn, 
+            cur = build_attn(inp_attn,
                     model.layers[il].wo, model.layers[il].bo,
                     Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
         }
@@ -75,7 +75,7 @@ llm_build_pangu_embedded::llm_build_pangu_embedded(const llama_model & model, co
         ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
         cb(ffn_inp, "ffn_inp", il);
 
-        // feed-forward network 
+        // feed-forward network
         cur = build_norm(ffn_inp,
                 model.layers[il].ffn_norm, NULL,
                 LLM_NORM_RMS, il);