提交完善

chatglm_export.py

@@ -23,8 +23,8 @@ fastllm_weight_type_dict = {
     "embedding": 2
 }
 
-v = np.random.randint(-127, 127, [10, 20]);
-temp = v;
+v = np.random.randint(-127, 127, [10, 20])
+temp = v
 c_max = np.expand_dims(np.abs(v).max(axis = -1), -1)
 c_scale = c_max / 127.0
 v = (v / c_scale + 128.5).clip(1, 255).astype(np.uint8)
@@ -36,8 +36,8 @@ def write_int8(fo, v):
     fo.write(struct.pack('i', 3))
     fo.write(struct.pack('i', 0))
     for i in range(c_max.shape[0]):
-        fo.write(struct.pack('f', -c_max[i][0]));
-        fo.write(struct.pack('f', c_max[i][0]));
+        fo.write(struct.pack('f', -c_max[i][0]))
+        fo.write(struct.pack('f', c_max[i][0]))
     fo.write(v.data)
 
 def write_int4(fo, v):
@@ -51,8 +51,8 @@ def write_int4(fo, v):
     fo.write(struct.pack('i', 8))
     fo.write(struct.pack('i', 0))
     for i in range(c_min.shape[0]):
-        fo.write(struct.pack('f', c_min[i][0]));
-        fo.write(struct.pack('f', c_max[i][0]));
+        fo.write(struct.pack('f', c_min[i][0]))
+        fo.write(struct.pack('f', c_max[i][0]))
     fo.write(v.data)
 
 def tofile(exportPath,

cli_demo.py

@@ -21,9 +21,9 @@ if __name__ == "__main__":
             history = []
             print("输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
             continue
-        print("AI:", end = "");
-        curResponse = "";
+        print("AI:", end = "")
+        curResponse = ""
         for response in model.stream_response(query, history = history):
-            curResponse += response;
+            curResponse += response
             print(response, flush = True, end = "")
         history.append((query, curResponse))
\ No newline at end of file