update model json

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "scutcyr/BianQue-2.0",
+  "architectures": [
+    "ChatGLMForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "bos_token_id": 130004,
+  "eos_token_id": 130005,
+  "gmask_token_id": 130001,
+  "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,
+  "pre_seq_len": null,
+  "prefix_projection": false,
+  "quantization_bit": 0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 130528
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 130004,
+  "eos_token_id": 130005,
+  "pad_token_id": 3,
+  "transformers_version": "4.29.0.dev0"
+}

pytorch_model.bin.index.json

@@ -0,0 +1,375 @@
+{
+  "metadata": {
+    "total_size": 13415859968
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.final_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.final_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<sop>",
+  "eos_token": "<eop>",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLMTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<sop>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "end_token": "</s>",
+  "eos_token": "<eop>",
+  "gmask_token": "[gMASK]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "num_image_tokens": 0,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "unk_token": "<unk>"
+}