upload params

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "dwdcth/chatglm3-6b-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,
+  "auto_map": {
+    "AutoConfig": "THUDM/chatglm3-6b--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForSequenceClassification"
+  },
+  "bias_dropout_fusion": true,
+  "classifier_dropout": null,
+  "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": 8192,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "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": "4.37.2"
+}

model-001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25c7b1e2182faafe31537b3297f6b2d1c5d4d486c5cbbdc41c41e2378092838
+size 3923643088

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 +1,18 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "dwdcth/chatglm3-6b-int4--tokenization_chatglm.ChatGLMTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "unk_token": "<unk>"
+}