2025-02-15_specter2_contrastive_fold_0

config.json

@@ -1,28 +1,70 @@
 {
-  "_name_or_path": "BAAI/bge-m3",
+  "_name_or_path": "specter2",
+  "adapters": {
+    "adapters": {
+      "specter2": "9076f36a74755ac4"
+    },
+    "config_map": {
+      "9076f36a74755ac4": {
+        "adapter_residual_before_ln": false,
+        "cross_adapter": false,
+        "dropout": 0.0,
+        "factorized_phm_W": true,
+        "factorized_phm_rule": false,
+        "hypercomplex_nonlinearity": "glorot-uniform",
+        "init_weights": "bert",
+        "inv_adapter": null,
+        "inv_adapter_reduction_factor": null,
+        "is_parallel": false,
+        "learn_phm": true,
+        "leave_out": [],
+        "ln_after": false,
+        "ln_before": false,
+        "mh_adapter": false,
+        "non_linearity": "relu",
+        "original_ln_after": true,
+        "original_ln_before": true,
+        "output_adapter": true,
+        "phm_bias": true,
+        "phm_c_init": "normal",
+        "phm_dim": 4,
+        "phm_init_range": 0.0001,
+        "phm_layer": false,
+        "phm_rank": 1,
+        "reduction_factor": 16,
+        "residual_before_ln": true,
+        "scaling": 1.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "stochastic_depth": 0.0,
+        "use_gating": false
+      }
+    },
+    "fusion_config_map": {},
+    "fusion_name_map": {},
+    "fusions": {}
+  },
   "architectures": [
-    "ContrastiveModelXLMRoberta"
+    "ContrastiveModelBert"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 8194,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "torch_dtype": "bfloat16",
+  "prediction_heads": {},
+  "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 31090
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b39ef760f106013bb83d30527764930fdfd3a0de89f6d6cc7925d8bb8d2fc7
-size 1135554736
+oid sha256:171c93490daa1045bc9cb0ad0950a504654ab2d2fa114173433af55c30719159
+size 439696224