add questions all

config.json

@@ -1,24 +1,30 @@
 {
+  "_name_or_path": "THUDM/chatglm-6b-int4",
   "architectures": [
-    "RobertaForQuestionAnswering"
+    "ChatGLMModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "language": "english",
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "name": "Roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "type_vocab_size": 1,
-  "vocab_size": 50265
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "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,
+  "max_sequence_length": 2048,
+  "model_type": "chatglm",
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "position_encoding_2d": true,
+  "quantization_bit": 4,
+  "quantization_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.1",
+  "use_cache": true,
+  "vocab_size": 130528
 }

demo_call_api.py

@@ -0,0 +1,8 @@
+
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4")
+
+model = AutoModelForQuestionAnswering.from_pretrained("THUDM/chatglm-6b-int4")
+
+

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
-  "name_or_path": "NewBreaker/chatglm-6b-int4",
+  "name_or_path": "THUDM/chatglm-6b-int4",
   "bos_token": "<sop>",
   "eos_token": "<eop>",
   "end_token": "</s>",