Upload config.json with huggingface_hub

config.json

@@ -1,52 +1,39 @@
 {
-    "architectures": [
-        "OpenModelAdvanced"
-    ],
-    "attention_dropout": 0.0,
-    "auto_map": {
-        "AutoConfig": "configuration.OpenModelConfig",
-        "AutoModel": "modeling.OpenModelModel",
-        "AutoModelForCausalLM": "modeling.OpenModelForCausalLM"
-    },
-    "num_hidden_layers": 80,
-    "hidden_size": 8192,
-    "intermediate_size": 18432,
-    "eos_token_id": 156892,
-    "pad_token_id": 156892,
-    "first_k_dense_replace": 4,
-    "hidden_act": "silu",
-    "max_position_embeddings": 32768,
-    "model_type": "openmodel",
-    "moe_intermediate_size": 2048,
-    "norm_topk_prob": true,
-    "num_experts_per_tok": 8,
-    "num_attention_heads": 64,
-    "norm_head": false,
-    "num_experts": 256,
-    "num_key_value_heads": 8,
-    "rope_theta": 600000,
-    "rope_scaling": null,
-    "tie_word_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.52.3",
-    "use_bias": false,
-    "use_rmsnorm": true,
-    "rms_norm_eps": 1e-06,
-    "head_dim": 128,
-    "num_shared_experts": 1,
-    "use_cache": true,
-    "use_qkv_bias": false,
-    "embedding_dropout": 0.0,
-    "norm_softmax": false,
-    "output_dropout": 0.0,
-    "vocab_size": 157184,
-    "rotary_dim": 64,
-    "using_split_qkv_in_self_attention": false,
-    "router_dtype": "fp32",
-    "moe_router_enable_expert_bias": true,
-    "routed_scaling_factor": 2.5,
-    "n_group": 8,
-    "topk_group": 4,
-    "use_qk_norm": true,
-    "score_function": "sigmoid"
+  "_name_or_path": "mlabonne/BigLlama-3.1-681B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 16384,
+  "initializer_range": 0.02,
+  "intermediate_size": 53248,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 128,
+  "num_hidden_layers": 315,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 128256
 }