Push model and config

AutoGPTQ model for meta-llama/Meta-Llama-3-8B-Instruct: 4bits, gr128, desc_act=False,damp_percent=0.1

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/scratch/nbrown9/llama-3-8b-4bit-gptq",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.1,
+    "desc_act": false,
+    "group_size": 128,
+    "is_marlin_format": false,
+    "model_file_base_name": "gptq_model-4bit-128g",
+    "model_name_or_path": "/scratch/nbrown9/llama-3-8b-4bit-gptq",
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "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:a93ae0cb6669213d143e486cb3c76d7820bb1a54e4fe93d400413a323bf66f5f
+size 5735720552

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.1,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "/scratch/nbrown9/llama-3-8b-4bit-gptq",
+  "model_file_base_name": "gptq_model-4bit-128g",
+  "is_marlin_format": false,
+  "quant_method": "gptq"
+}