Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "./chatglm2_6b/",
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "ChatGLMModel"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "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,
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "original_rope": true,
+  "pad_token_id": 2,
+  "padded_vocab_size": 65024,
+  "post_layer_norm": true,
+  "quantization_bit": 0,
+  "rmsnorm": true,
+  "seq_length": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true
+}

gptq_model-4bit-32g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838b9c1292544c26b51b4fac10b39b7edbac8ae6dd40ffbec194493ddfe15d3a
+size 4372627929

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}