upload

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "vivym/chatglm2-6b-int4",
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "ChatGLMForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "eos_token_id": 2,
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1e-05,
+  "model_type": "chatglm",
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "original_rope": true,
+  "pad_token_id": 0,
+  "padded_vocab_size": 65024,
+  "post_layer_norm": true,
+  "pre_seq_len": null,
+  "prefix_projection": false,
+  "quantization_bit": 4,
+  "rmsnorm": true,
+  "seq_length": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ba56dee3f408f47c8a65769961f655927a5cd922a1f5e3993f4b694d0f7ba7
+size 958872488

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ec57b061788f0c1a36bca3b2c9b72bff4ee253aec716423acf630e9c7dbb41
+size 974886624

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96061c02af03e51003ed626ba716cff234121159a7e9ba192d6bc9b868ee51d5
+size 964660392

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdbcd5ee3eebb7a8b8e7f2875792f24290a4ef77c6b5c25b3289db2674611f4
+size 492545720

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d97ec1050542b69ae81f6b73e5f93a472a6d84d3195fb1ae6de3f2ff5a14cf
+size 532676752

model.safetensors.index.json

@@ -0,0 +1,319 @@
+{
+  "metadata": {
+    "total_size": 3923601472
+  },
+  "weight_map": {
+    "transformer.embedding.word_embeddings.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.final_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight_scale": "model-00003-of-00005.safetensors",
+    "transformer.encoder.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight_scale": "model-00004-of-00005.safetensors",
+    "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight_scale": "model-00001-of-00005.safetensors",
+    "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight_scale": "model-00002-of-00005.safetensors",
+    "transformer.output_layer.weight": "model-00005-of-00005.safetensors",
+    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
+size 1018370

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ChatGLMTokenizer"
+}