AutoGPTQ model for SeaLLMs/SeaLLM-7B-v2.5: 4bits, gr128, desc_act=False

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "SeaLLMs/SeaLLM-7B-v2.5",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "group_size": 128,
+    "model_file_base_name": "gptq_model-4bit-128g",
+    "model_name_or_path": "SeaLLM-7B-v2.5-4bit",
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 256000
+}

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c088bcd3407de93f33e75678d9f40add4e7c3b42beec8e2b5983738300ea9e9
+size 7178029824

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "SeaLLM-7B-v2.5-4bit",
+  "model_file_base_name": "gptq_model-4bit-128g",
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq"
+}