Copying answerdotai/answerai-colbert-small-v1 for demo purposes

README.md

@@ -1,3 +1,188 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+tags:
+- ColBERT
+- RAGatouille
+- passage-retrieval
+---
+
+# answerai-colbert-small-v1
+
+**answerai-colbert-small-v1** is a new, proof-of-concept model by [Answer.AI](https://answer.ai), showing the strong performance multi-vector models with the new [JaColBERTv2.5 training recipe](https://arxiv.org/abs/2407.20750) and some extra tweaks can reach, even with just **33 million parameters**.
+
+While being MiniLM-sized, it outperforms all previous similarly-sized models on common benchmarks, and even outperforms much larger popular models such as e5-large-v2 or bge-base-en-v1.5.
+
+For more information about this model or how it was trained, head over to the [announcement blogpost](https://www.answer.ai/posts/2024-08-13-small-but-mighty-colbert.html).
+
+## Architecture
+
+<iframe
+  src="https://brianronan-netron-docker.hf.space?repo_id=brianronan/answerai-colbert-small&filename=model.safetensors"
+  style="width: 95%; height: 70vh; border: none;"
+></iframe>
+
+
+## Usage
+
+### Installation
+
+This model was designed with the upcoming RAGatouille overhaul in mind. However, it's compatible with all recent ColBERT implementations!
+
+To use it, you can either use the Stanford ColBERT library, or RAGatouille. You can install both or either by simply running.
+
+```sh
+pip install --upgrade ragatouille
+pip install --upgrade colbert-ai
+```
+
+If you're interested in using this model as a re-ranker (it vastly outperforms cross-encoders its size!), you can do so via the [rerankers](https://github.com/AnswerDotAI/rerankers) library:
+```sh
+pip install --upgrade rerankers[transformers]
+```
+
+### Rerankers
+
+```python
+from rerankers import Reranker
+
+ranker = Reranker("answerdotai/answerai-colbert-small-v1", model_type='colbert')
+docs = ['Hayao Miyazaki is a Japanese director, born on [...]', 'Walt Disney is an American author, director and [...]', ...]
+query = 'Who directed spirited away?'
+ranker.rank(query=query, docs=docs)
+```
+
+### RAGatouille
+
+```python
+from ragatouille import RAGPretrainedModel
+
+RAG = RAGPretrainedModel.from_pretrained("answerdotai/answerai-colbert-small-v1")
+
+docs = ['Hayao Miyazaki is a Japanese director, born on [...]', 'Walt Disney is an American author, director and [...]', ...]
+
+RAG.index(documents, index_name="ghibli")
+
+query = 'Who directed spirited away?'
+results = RAG.search(query)
+```
+
+### Stanford ColBERT
+
+#### Indexing
+
+```python
+from colbert import Indexer
+from colbert.infra import Run, RunConfig, ColBERTConfig
+
+INDEX_NAME = "DEFINE_HERE" 
+
+if __name__ == "__main__":
+    config = ColBERTConfig(
+        doc_maxlen=512,
+        nbits=2
+    )
+    indexer = Indexer(
+        checkpoint="answerdotai/answerai-colbert-small-v1",
+        config=config,
+    )
+    docs = ['Hayao Miyazaki is a Japanese director, born on [...]', 'Walt Disney is an American author, director and [...]', ...]
+
+    indexer.index(name=INDEX_NAME, collection=docs)
+```
+
+#### Querying
+
+```python
+from colbert import Searcher
+from colbert.infra import Run, RunConfig, ColBERTConfig
+
+INDEX_NAME = "THE_INDEX_YOU_CREATED" 
+k = 10 
+
+if __name__ == "__main__":
+    config = ColBERTConfig(
+        query_maxlen=32 # Adjust as needed, we recommend the nearest higher multiple of 16 to your query
+    )
+    searcher = Searcher(
+        index=index_name, 
+        config=config
+    ) 
+    query = 'Who directed spirited away?'
+    results = searcher.search(query, k=k)
+```
+
+
+#### Extracting Vectors
+
+Finally, if you want to extract individula vectors, you can use the model this way:
+
+
+```python
+from colbert.modeling.checkpoint import Checkpoint
+
+ckpt = Checkpoint("answerdotai/answerai-colbert-small-v1", colbert_config=ColBERTConfig())
+embedded_query = ckpt.queryFromText(["Who dubs Howl's in English?"], bsize=16)
+```
+
+
+## Results
+
+### Against single-vector models
+
+![](https://www.answer.ai/posts/images/minicolbert/small_results.png)
+
+
+| Dataset / Model | answer-colbert-s | snowflake-s | bge-small-en | bge-base-en |
+|:-----------------|:-----------------:|:-------------:|:-------------:|:-------------:|
+| **Size**        |     33M (1x)     |   33M (1x)   |   33M (1x)   | **109M (3.3x)** |
+| **BEIR AVG**    |      **53.79**       |    51.99     |    51.68     |    53.25      |
+| **FiQA2018**    |      **41.15**       |    40.65     |    40.34     |    40.65      |
+| **HotpotQA**    |    **76.11**     |    66.54     |    69.94     |    72.6       |
+| **MSMARCO**     |    **43.5**      |    40.23     |    40.83     |    41.35      |
+| **NQ**          |      **59.1**        |    50.9      |    50.18     |    54.15      |
+| **TRECCOVID**   |    **84.59**     |    80.12     |    75.9      |    78.07      |
+| **ArguAna**     |      50.09       |    57.59     |    59.55     |  **63.61**    |
+| **ClimateFEVER**|      33.07       |    **35.2**      |    31.84     |    31.17      |
+| **CQADupstackRetrieval** |  38.75  |    39.65     |    39.05     |    **42.35**      |
+| **DBPedia**     |    **45.58**     |    41.02     |    40.03     |    40.77      |
+| **FEVER**       |    **90.96**     |    87.13     |    86.64     |    86.29      |
+| **NFCorpus**    |    37.3      |    34.92     |    34.3      |    **37.39**      |
+| **QuoraRetrieval** |    87.72      |    88.41     |  88.78   |    **88.9**       |
+| **SCIDOCS**     |      18.42       |  **21.82**   |    20.52     |    21.73      |
+| **SciFact**     |    **74.77**     |    72.22     |    71.28     |    74.04      |
+| **Touche2020**  |      25.69       |    23.48     |    **26.04**     |    25.7       |
+
+### Against ColBERTv2.0
+
+| Dataset / Model | answerai-colbert-small-v1 | ColBERTv2.0 |
+|:-----------------|:-----------------------:|:------------:|
+| **BEIR AVG**    |      **53.79**       |   50.02 |
+| **DBPedia**     |    **45.58**     |    44.6     |
+| **FiQA2018**    |    **41.15**     |    35.6     |
+| **NQ**          |    **59.1**      |    56.2     |
+| **HotpotQA**    |    **76.11**     |    66.7     |
+| **NFCorpus**    |    **37.3**      |    33.8     |
+| **TRECCOVID**   |    **84.59**     |    73.3     |
+| **Touche2020**  |      25.69       |  **26.3**   |
+| **ArguAna**     |    **50.09**     |    46.3     |
+| **ClimateFEVER**|    **33.07**     |    17.6     |
+| **FEVER**       |    **90.96**     |    78.5     |
+| **QuoraRetrieval** |    **87.72**     |  85.2   |
+| **SCIDOCS**     |    **18.42**     |    15.4     |
+| **SciFact**     |    **74.77**     |    69.3     |
+
+
+## Referencing
+
+We'll most likely eventually release a technical report. In the meantime, if you use this model or other models following the JaColBERTv2.5 recipe and would like to give us credit, please cite the JaColBERTv2.5 journal pre-print:
+
+```
+@article{clavie2024jacolbertv2,
+  title={JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources},
+  author={Clavi{\'e}, Benjamin},
+  journal={arXiv preprint arXiv:2407.20750},
+  year={2024}
+}
+```

artifact.metadata

@@ -0,0 +1,75 @@
+{
+    "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": 1,
+    "kmeans_niters": 4,
+    "resume": false,
+    "pool_factor": 1,
+    "clustering_mode": "hierarchical",
+    "protected_tokens": 0,
+    "similarity": "cosine",
+    "bsize": 32,
+    "accumsteps": 1,
+    "lr": 1e-5,
+    "maxsteps": 15626,
+    "save_every": null,
+    "warmup": 781,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 32,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "answerdotai/AnswerAI-ColBERTv2.5-small",
+    "schedule_free": false,
+    "schedule_free_wd": 0.0,
+    "kldiv_loss": true,
+    "marginmse_loss": false,
+    "kldiv_weight": 1.0,
+    "marginmse_weight": 0.05,
+    "ib_loss_weight": 1.0,
+    "normalise_training_scores": true,
+    "normalization_method": "minmax",
+    "quant_aware": false,
+    "highest_quant_level": 8,
+    "lowest_quant_level": 2,
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "cap_padding": 0,
+    "dynamic_query_maxlen": false,
+    "dynamic_querylen_multiples": 32,
+    "dim": 96,
+    "doc_maxlen": 300,
+    "mask_punctuation": true,
+    "checkpoint": "answerdotai/AnswerAI-ColBERTv2.5-small",
+    "triples": "\/home\/bclavie\/colbertv2.5_en\/data\/msmarco\/triplets.jsonl",
+    "collection": "\/home\/bclavie\/colbertv2.5_en\/data\/msmarco\/collection.tsv",
+    "queries": "\/home\/bclavie\/colbertv2.5_en\/data\/msmarco\/queries.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/home\/bclavie\/colbertv2.5_en\/experiments",
+    "experiment": "minicolbertv2.5",
+    "index_root": null,
+    "name": "2024-08\/07\/08.16.20",
+    "rank": 0,
+    "nranks": 4,
+    "amp": true,
+    "gpus": 4,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "a100-80-4x",
+        "current_datetime": "Aug 07, 2024 ; 12:13PM UTC (+0000)",
+        "cmd": "train_v2.5_mini.py",
+        "version": "colbert-v0.4"
+    }
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bclavie/mini-base",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bb6ef696cc88b3d18b7520273dfd25315f6c47d265142ba13bba38678c92b6
+size 133610664

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b078342c7af055851eb25e599c7e362674e266aa52fe2d87d7bd325d3e3420e0
+size 133159107

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b664122c834ea2dfabb3fdc961b7f59ccd51c8bf9d051300cf1e3deb8a8e146
+size 60179566

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2165cdb0057d0812db7c7b248286c4d9a22b292c7beb88282d63a2241a9fac5f
+size 66734665

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250889c5550969a1f0aaf6f9dcc01db39044fe3998fa9c95ef731af23f737b7b
+size 34000578

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8a2fcc60df4d32698aae409fce597b49e46938ef1e79e7489497e3dd4c9620
+size 61506214

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5286e7efbc215bac95dfb42f8c46054ed8d73828dfe69dc59bd0529c82c51d2
+size 36221948

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250889c5550969a1f0aaf6f9dcc01db39044fe3998fa9c95ef731af23f737b7b
+size 34000578

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1967fe95a4e180b4be4174d1c17596dfb932450d730cc599804e540ad1a7c7
+size 34000575

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vespa_colbert.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9161e64cab96fe5a5366782578e20da3409b26bd171a2a8bc6b9168777950903
+size 133257413