Update config.json

config.json

@@ -1,31 +1,26 @@
 {
-  "bias": false,
-  "block_size": 2048,
-  "gelu_approximate": "none",
-  "head_size": 64,
-  "hf_config": {
-    "name": "TinyLlama-1.1B-intermediate-step-1431k-3T",
-    "org": "TinyLlama"
-  },
-  "intermediate_size": 5632,
-  "lm_head_bias": false,
-  "mlp_class_name": "LLaMAMLP",
-  "n_embd": 2048,
-  "n_expert": 0,
-  "n_expert_per_token": 0,
-  "n_head": 32,
-  "n_layer": 22,
-  "n_query_groups": 4,
-  "name": "tiny-llama-1.1b",
-  "norm_class_name": "RMSNorm",
-  "norm_eps": 1.0e-05,
-  "padded_vocab_size": 32000,
-  "padding_multiple": 64,
-  "parallel_residual": false,
-  "rope_base": 10000,
-  "rope_condense_ratio": 1,
-  "rotary_percentage": 1.0,
-  "scale_embeddings": false,
-  "shared_attention_norm": false,
+  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "architectures": [
+    "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": 4096,
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
   "vocab_size": 32000
-}
+}