AutoGPTQ model for mistralai/Mistral-7B-v0.3: 4bits, gr128, desc_act=False

config.json

@@ -16,6 +16,19 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "group_size": 128,
+    "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-05,
   "rope_theta": 1000000.0,
   "sliding_window": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e32da462993acadd3128119160a3015dbdc2e618755707c1849929e707b66a
-size 4171245128
+oid sha256:55f1c2e111e27c4322a743eeb609e3455e93d8617b0562738d0b678b1822dec0
+size 4168468392

quantize_config.json

@@ -7,5 +7,7 @@
   "sym": true,
   "true_sequential": true,
   "model_name_or_path": null,
-  "model_file_base_name": null
+  "model_file_base_name": null,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq"
 }