Upload config.json with huggingface_hub

config.json

@@ -2,29 +2,29 @@
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 46303,
-  "head_dim": 128,
-  "hidden_act": "silu",
+  "model_type": "llama",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 32000,
   "hidden_size": 4096,
-  "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 0,
+  "num_attention_heads": 32,
+  "hidden_act": "silu",
+  "max_position_embeddings": 2048,
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "pad_token_id": null,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.54.1",
-  "use_cache": false,
-  "vocab_size": 46305
-}
+  "rope_theta": 10000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "hidden_dropout": 0.0,
+  "model_max_length": 2048
+}