Initial GPTQ model commit

config.json

@@ -0,0 +1,25 @@
+{
+    "_name_or_path": "/workspace/llama-13b-hf",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 4096,
+    "max_sequence_len": 4096,
+    "max_sequence_length": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "pad_token_id": -1,
+    "rms_norm_eps": 1e-06,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.29.2",
+    "use_cache": true,
+    "vocab_size": 32000
+}