auto_gptq format

config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d045f30d7d09714fecd0e63423e8814b66abb164aa7df9583f62276c26b0b322
-size 2601
+oid sha256:09cbfe58c9b2c463fec785cb44ffdc67ebe53f29356b7d3045076d19fe3e2813
+size 2581

model.safetensors.index.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee10f5b8e52d2a0ee2e6795c9ea649b8101ad81b1a0108de772e54fccb41d76
-size 210876
+oid sha256:fd3587e0f4a4dc04b1b1a10b307b5dda785716817956c7815436bac85e573862
+size 237410

quantization_config.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4814a2340cd541089354239396e9262cb662339634594b62948f122c8d18d812
-size 1381

quantize_config.json

@@ -0,0 +1,60 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "enable_quanted_input": true,
+  "enable_minmax_tuning": true,
+  "seqlen": 512,
+  "batch_size": 8,
+  "scale_dtype": "torch.float16",
+  "lr": 1.0,
+  "minmax_lr": 1.0,
+  "gradient_accumulate_steps": 1,
+  "iters": 1,
+  "amp": true,
+  "nsamples": 512,
+  "low_gpu_mem_usage": false,
+  "to_quant_block_names": [
+    [
+      "model.layers.0",
+      "model.layers.1",
+      "model.layers.2",
+      "model.layers.3",
+      "model.layers.4",
+      "model.layers.5",
+      "model.layers.6",
+      "model.layers.7",
+      "model.layers.8",
+      "model.layers.9",
+      "model.layers.10",
+      "model.layers.11",
+      "model.layers.12",
+      "model.layers.13",
+      "model.layers.14",
+      "model.layers.15",
+      "model.layers.16",
+      "model.layers.17",
+      "model.layers.18",
+      "model.layers.19",
+      "model.layers.20",
+      "model.layers.21",
+      "model.layers.22",
+      "model.layers.23",
+      "model.layers.24",
+      "model.layers.25",
+      "model.layers.26",
+      "model.layers.27",
+      "model.layers.28",
+      "model.layers.29",
+      "model.layers.30",
+      "model.layers.31"
+    ]
+  ],
+  "enable_norm_bias_tuning": false,
+  "autoround_version": "0.4.2.dev",
+  "quant_method": "gptq",
+  "desc_act": false,
+  "true_sequential": false,
+  "damp_percent": 0.01
+}