初始化项目，由ModelHub XC社区提供模型

Model: TheBloke/Yarn-Llama-2-7B-64K-AWQ
Source: Original Platform

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "/fsx/proj-trlx/conceptofmind/scaled-rope-private/save_model/final/yarn-llama-2-7b-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": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 65536,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "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": {
+    "quant_method": "awq",
+    "zero_point": true,
+    "group_size": 128,
+    "bits": 4,
+    "version": "gemm"
+  }
+}