Upload ColBERT fine-tuned checkpoint

colbert/artifact.metadata

@@ -0,0 +1,60 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "index_bsize": 64,
+    "nbits": 4,
+    "kmeans_niters": 4,
+    "resume": false,
+    "pool_factor": 1,
+    "clustering_mode": "hierarchical",
+    "protected_tokens": 0,
+    "similarity": "cosine",
+    "bsize": 16,
+    "accumsteps": 1,
+    "lr": 5e-6,
+    "maxsteps": 500000,
+    "save_every": 33,
+    "warmup": 33,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "ClinicalBERT-ColBERT",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 256,
+    "mask_punctuation": true,
+    "checkpoint": "medicalai\/ClinicalBERT",
+    "triples": "data\/triples.train.colbert.jsonl",
+    "collection": "data\/corpus.train.colbert.tsv",
+    "queries": "data\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2025-06\/14\/01.24.47",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "7d6ba65c9f2d",
+        "current_datetime": "Jun 14, 2025 ;  2:05AM UTC (+0000)",
+        "cmd": "\/usr\/local\/lib\/python3.11\/dist-packages\/colab_kernel_launcher.py -f \/root\/.local\/share\/jupyter\/runtime\/kernel-74d99a55-9600-475d-bed1-588f2bf3fd1a.json",
+        "version": "colbert-v0.4"
+    }
+}

colbert/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "medicalai/ClinicalBERT",
+  "activation": "gelu",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_dropout": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dim": 3072,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

colbert/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb83300b61f5bfef241583c15682e647454007402e1d69d003167191a39a6a67
+size 711830440

colbert/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

colbert/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}