AutoGPTQ model for Alibaba-NLP/gte-Qwen2-1.5B-instruct: 8bits, gr128, desc_act=True

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "Alibaba-NLP/gte-Qwen2-1.5B-instruct--modeling_qwen.Qwen2Model",
+    "AutoModelForCausalLM": "Alibaba-NLP/gte-Qwen2-1.5B-instruct--modeling_qwen.Qwen2ForCausalLM",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/gte-Qwen2-1.5B-instruct--modeling_qwen.Qwen2ForSequenceClassification"
+  },
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "quantization_config": {
+    "bits": 8,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "group_size": 128,
+    "is_marlin_format": false,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

gptq_model-8bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34549d9685d8dff12afa590112fa0e6d02b2849f8623cd8b374b27526047be6
+size 2276232552

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 8,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "is_marlin_format": false,
+  "quant_method": "gptq"
+}