Upload of AutoGPTQ quantized model

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "sparse_llama/Llama-3.2-1B-Instruct-SparseGPT-INT4",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -23,6 +24,19 @@
   "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.1,
+    "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-05,
   "rope_scaling": {
     "factor": 32.0,
@@ -33,7 +47,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 128256

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb30078d3b42663d1da0742d8ef6ea1ae40f7a38d9de6d19a27f3a37a2edbfb1
+size 1558482936

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "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"
+}