Upload config.json

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "nicolinho/QRM-Llama3.1-8B",
+  "architectures": [
+    "LlamaForRewardModelWithGating"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModelForSequenceClassification": "modeling_custom.LlamaForRewardModelWithGating"
+  },
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "gating_hidden_dim": 1024,
+  "gating_n_hidden": 3,
+  "gating_newtork": true,
+  "gating_temperature": 5.0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "loss": "quantile_regression",
+  "max_position_embeddings": 131072,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_objectives": 19,
+  "num_quantiles": 19,
+  "pad_token_id": 128256,
+  "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",
+  "attn_implementation": "flash_attention_2",
+  "transformers_version": "4.43.1",
+  "use_cache": false,
+  "vocab_size": 128257
+}