README.md

@@ -9,7 +9,7 @@ tags:
 ---
 # ChatGLM-6B-INT4
 <p align="center">
-    👋 Join our <a href="https://join.slack.com/t/chatglm/shared_invite/zt-1udqapmrr-ocT1DS_mxWe6dDY8ahRWzg" target="_blank">Slack</a> and <a href="https://github.com/THUDM/ChatGLM-6B/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
+    👋 Join our <a href="https://join.slack.com/t/chatglm/shared_invite/zt-1t4a8evfn-vduo2hhNcYqBUnZ71IXiqQ" target="_blank">Slack</a> and <a href="https://github.com/THUDM/ChatGLM-6B/blob/main/resources/WECHAT.md" target="_blank">WeChat</a>
 </p>
 
 ## 介绍

config.json

@@ -10,16 +10,16 @@
   },
   "bos_token_id": 130004,
   "eos_token_id": 130005,
-  "mask_token_id": 130000,
   "gmask_token_id": 130001,
-  "pad_token_id": 3,
   "hidden_size": 4096,
   "inner_hidden_size": 16384,
   "layernorm_epsilon": 1e-05,
+  "mask_token_id": 130000,
   "max_sequence_length": 2048,
   "model_type": "chatglm",
   "num_attention_heads": 32,
   "num_layers": 28,
+  "pad_token_id": 3,
   "position_encoding_2d": true,
   "quantization_bit": 4,
   "quantization_embeddings": false,

modeling_chatglm.py

@@ -918,7 +918,7 @@ class ChatGLMModel(ChatGLMPreTrainedModel):
         elif input_ids is not None:
             batch_size, seq_length = input_ids.shape[:2]
         elif inputs_embeds is not None:
-            batch_size, seq_length = inputs_embeds.shape[:2]
+            batch_size, seq_length, _ = inputs_embeds.shape[:2]
         else:
             raise ValueError("You have to specify either input_ids or inputs_embeds")
 
@@ -972,8 +972,9 @@ class ChatGLMModel(ChatGLMPreTrainedModel):
 
         if attention_mask is None:
             attention_mask = torch.zeros(1, 1, device=input_ids.device).bool()
+
         else:
-            attention_mask = attention_mask.to(hidden_states.device)
+            attention_mask = attention_mask.to(input_ids.device)
 
         for i, layer in enumerate(self.layers):
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245786435bde9f4593c105ea846fa461fe42bc63c12b738d0272fcaed6276645
+oid sha256:35828b49cf23cbae4c27788d4b04fc68c79a276300e09f14d72a49b0b738b4a9
 size 3893083075

tokenization_chatglm.py

@@ -31,9 +31,6 @@ class TextTokenizer:
     def tokenize(self, text):
         return self.sp.EncodeAsPieces(text)
 
-    def convert_tokens_to_string(self, tokens):
-        return self.sp.DecodePieces(tokens)
-
     def convert_tokens_to_ids(self, tokens):
         return [self.sp.PieceToId(token) for token in tokens]
 
@@ -114,23 +111,14 @@ class SPTokenizer:
         tokens = [x + self.num_image_tokens for x in tmp]
         return tokens if add_dummy_prefix else tokens[2:]
 
-    def postprocess(self, text):
-        text = text.replace("<n>", "\n")
-        text = text.replace(SPTokenizer.get_tab_token(), "\t")
-        for i in range(2, self.max_blank_length + 1):
-            text = text.replace(self.get_blank_token(i), " " * i)
-        return text
-
     def decode(self, text_ids: List[int]) -> str:
         ids = [int(_id) - self.num_image_tokens for _id in text_ids]
         ids = [_id for _id in ids if _id >= 0]
         text = self._get_text_tokenizer().decode(ids)
-        text = self.postprocess(text)
+        text = text.replace("<n>", "\n")
-        return text
+        text = text.replace(SPTokenizer.get_tab_token(), "\t")
-
+        for i in range(2, self.max_blank_length + 1):
-    def decode_tokens(self, tokens: List[str]) -> str:
+            text = text.replace(self.get_blank_token(i), " " * i)
-        text = self._get_text_tokenizer().convert_tokens_to_string(tokens)
-        text = self.postprocess(text)
         return text
 
     def tokenize(
@@ -268,12 +256,11 @@ class ChatGLMTokenizer(PreTrainedTokenizer):
 
         return seq
 
-    def convert_tokens_to_string(self, tokens: List[str]) -> str:
-        return self.sp_tokenizer.decode_tokens(tokens)
-
     def _decode(
             self,
             token_ids: Union[int, List[int]],
+            skip_special_tokens: bool = False,
+            clean_up_tokenization_spaces: bool = True,
             **kwargs
     ) -> str:
         if isinstance(token_ids, int):
@@ -282,7 +269,7 @@ class ChatGLMTokenizer(PreTrainedTokenizer):
             return ""
         if self.pad_token_id in token_ids:  # remove pad
             token_ids = list(filter((self.pad_token_id).__ne__, token_ids))
-        return super()._decode(token_ids, **kwargs)
+        return self.sp_tokenizer.decode(token_ids)
 
     def _convert_token_to_id(self, token):
         """ Converts a token (str) in an id using the vocab. """