Initial GPTQ model commit

config.json

@@ -0,0 +1,46 @@
+{
+    "_name_or_path": "/fsx/proj-trlx/conceptofmind/scaled-rope-private/save_model/final/yarn-llama-2-13b-3e-5-64k-400steps",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "auto_map": {
+        "AutoConfig": "configuration_llama.LlamaConfig",
+        "AutoModelForCausalLM": "modeling_llama_together_yarn.LlamaForCausalLM"
+    },
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 65536,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 40,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 16.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn",
+        "finetuned": true
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.32.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "bits": 4,
+        "group_size": 128,
+        "damp_percent": 0.1,
+        "desc_act": false,
+        "sym": true,
+        "true_sequential": true,
+        "model_name_or_path": null,
+        "model_file_base_name": "model",
+        "quant_method": "gptq"
+    }
+}