Duplicate from C4IR-RW/kinyabert

Co-authored-by: Antoine Nzeyi <nzeyi@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,304 @@
+---
+datasets:
+- C4IR-RW/kinya-ag-retrieval
+language:
+- rw
+metrics:
+- accuracy
+tags:
+- kinyarwanda
+- kinyabert
+- bert
+- colbert
+- rag
+- retrieval
+license: cc-by-4.0
+---
+
+# Kinyarwanda BERT and ColBERT models
+
+In Rwanda, many farmers struggle to access timely, personalized agricultural information. Traditional channels - like radio, TV, and online sources - offer limited reach and interactivity, while extension services and a national call center, staffed by only two agents for over two million farmers, face capacity constraints. To address these gaps, we developed a 24/7 AI-enabled Interactive Voice Response (IVR) tool. Accessible via a Kinyarwanda-speaking hotline, this tool provides advisory on topics such as pest and disease diagnosis and agro-climatic practices, as well as information on MINAGRI’s support programs for farmers, e.g. crop insurances. By utilizing AI and IVR technology, this project will make agricultural advisories more accessible, timely, and responsive to farmers’ needs. For more information, please reach out to [C4IR](https://c4ir.rw/).
+
+Implemented by: [C4IR Rwanda](https://c4ir.rw/) & [KiNLP](https://kinlp.com/); Supported by [GIZ](https://www.giz.de/); Financed by: [BMZ](https://www.bmz.de/en).
+
+## Introduction
+
+This repository Pre-trained foundational models for Kinyarwanda passage retrieval/ranking. Running these models requires using [DeepKIN-AgAI](https://github.com/c4ir-rw/ac-ai-models/tree/main/DeepKIN-AgAI) package.
+
+## Example uses:
+
+### 1. Fine-tuning a pretrained KinyaBERT model into a KinyaColBERT retrieval model
+
+The following example uses a pre-trained KinyaBERT base model (107M paremeters).
+
+The training data for agricultural retrieval (i.e. ["C4IR-RW/kinya-ag-retrieval"](https://huggingface.co/datasets/C4IR-RW/kinya-ag-retrieval) on Hugging Face) has been morphologically parsed already, but for other datasets, [MorphoKIN](https://github.com/anzeyimana/morphokin) parsing will be performed first.
+
+```shell
+
+# 1. Copy "kinya-ag-retrieval" dataset from Hugging face into a local directory, e.g. /home/ubuntu/DATA/kinya-ag-retrieval/
+
+# 2. Copy "kinyabert_base_pretrained.pt" model into a local directory, e.g. /home/ubuntu/DATA/kinyabert_base_pretrained.pt
+
+# 3. Run the following training script from DeepKIN-AgAI package:
+
+python3 DeepKIN-AgAI/deepkin/train/flex_trainer.py  \
+    --model_variant="kinya_colbert:base" \
+    --colbert_embedding_dim=512 \
+    --gpus=1 \
+    --batch_size=12  \
+    --accumulation_steps=10  \
+    --dataloader_num_workers=4  \
+    --dataloader_persistent_workers=True  \
+    --dataloader_pin_memory=True  \
+    --use_ddp=False \
+    --use_mtl_optimizer=False \
+    --warmup_iter=2000 \
+    --peak_lr=1e-5  \
+    --lr_decay_style="cosine" \
+    --num_iters=152630  \
+    --dataset_max_seq_len=512  \
+    --use_iterable_dataset=False  \
+    --train_log_steps=1  \
+    --checkpoint_steps=1000 \
+    --pretrained_bert_model_file="/home/ubuntu/DATA/kinyabert_base_pretrained.pt" \
+    --qa_train_query_id="/home/ubuntu/DATA/kinya-ag-retrieval/rw_ag_retrieval_query_id.txt" \
+    --qa_train_query_text="/home/ubuntu/DATA/kinya-ag-retrieval/parsed_rw_ag_retrieval_query_text.txt" \
+    --qa_train_passage_id="/home/ubuntu/DATA/kinya-ag-retrieval/rw_ag_retrieval_passage_id.txt" \
+    --qa_train_passage_text="/home/ubuntu/DATA/kinya-ag-retrieval/parsed_rw_ag_retrieval_passage_text.txt" \
+    --qa_train_qpn_triples="/home/ubuntu/DATA/kinya-ag-retrieval/rw_ag_retrieval_qpntriplets_all.tsv" \
+    --qa_dev_query_id="/home/ubuntu/DATA/kinya-ag-retrieval/rw_ag_retrieval_query_id.txt" \
+    --qa_dev_query_text="/home/ubuntu/DATA/kinya-ag-retrieval/parsed_rw_ag_retrieval_query_text.txt" \
+    --qa_dev_passage_id="/home/ubuntu/DATA/kinya-ag-retrieval/rw_ag_retrieval_passage_id.txt" \
+    --qa_dev_passage_text="/home/ubuntu/DATA/kinya-ag-retrieval/parsed_rw_ag_retrieval_passage_text.txt" \
+    --qa_dev_qpn_triples="/home/ubuntu/DATA/kinya-ag-retrieval/rw_ag_retrieval_qpntriplets_dev.tsv" \
+    --load_saved_model=True  \
+    --model_save_path="/home/ubuntu/DATA/kinya_colbert_base_rw_ag_retrieval_new.pt"
+  
+
+```
+
+### 2. Running an API server for KinyaColBERT agricultural retrieval
+
+1. First, run [MorphoKIN](https://github.com/anzeyimana/morphokin) server on Unix domain socket:
+
+```shell
+
+# Launch a daemon container
+
+docker run -d -v /home/ubuntu/MORPHODATA:/MORPHODATA \
+  --gpus all morphokin:latest morphokin \
+  --morphokin_working_dir /MORPHODATA \
+  --morphokin_config_file /MORPHODATA/data/analysis_config_file.conf  \
+  --task RMS \
+  --kinlp_license /MORPHODATA/licenses/KINLP_LICENSE_FILE.dat  \
+  --ca_roots_pem_file /MORPHODATA/data/roots.pem \
+  --morpho_socket /MORPHODATA/run/morpho.sock
+
+
+```
+
+2. Wait for MorphoKIN socket server to be ready by monitoring the container logs.
+
+```shell
+
+docker container ls
+
+docker logs -f <CONTAINER ID>
+
+# MorphoKIN server is ready once you see a message like this: MorphoKin server listening on UNIX SOCKET: /MORPHODATA/run/morpho.sock
+
+```
+
+3. Then, run the retrieval API server:
+
+```shell
+
+mkdir -p /home/ubuntu/DATA/agai_index
+
+python3 DeepKIN-AgAI/deepkin/production/agai_backend.py
+
+```
+
+### 3. Evaluating KinyaColBERT pre-trained model on ["C4IR-RW/kinya-ag-retrieval"](https://huggingface.co/datasets/C4IR-RW/kinya-ag-retrieval)
+
+
+```python
+import progressbar
+import torch
+import torch.nn.functional as F
+
+from deepkin.clib.libkinlp.kinlpy import ParsedFlexSentence
+from deepkin.data.morpho_qa_triple_data import DOCUMENT_TYPE_ID, QUESTION_TYPE_ID
+from deepkin.models.kinyabert import KinyaColBERT
+from deepkin.utils.misc_functions import read_lines
+
+DATA_DIR = '/home/ubuntu/DATA'
+rank = 0
+pretrained_model_file = f'{DATA_DIR}/kinya_colbert_large_rw_ag_retrieval_finetuned_512D.pt'
+keyword = f'kinya_colbert_large'
+
+qa_query_id = f'{DATA_DIR}/kinya-ag-retrieval/rw_ag_retrieval_query_id.txt'
+qa_query_text = f'{DATA_DIR}/kinya-ag-retrieval/parsed_rw_ag_retrieval_query_text.txt'
+qa_passage_id = f'{DATA_DIR}/kinya-ag-retrieval/rw_ag_retrieval_passage_id.txt'
+qa_passage_text = f'{DATA_DIR}/kinya-ag-retrieval/parsed_rw_ag_retrieval_passage_text.txt'
+
+all_queries = {idx: ParsedFlexSentence(txt) for idx, txt in zip(read_lines(qa_query_id), read_lines(qa_query_text))}
+all_passages = {idx: ParsedFlexSentence(txt) for idx, txt in zip(read_lines(qa_passage_id), read_lines(qa_passage_text))}
+
+print(f'Got: {len(all_queries)} queries, {len(all_passages)} passages', flush=True)
+
+device = torch.device('cuda:%d' % rank)
+
+model, args = KinyaColBERT.from_pretrained(device, pretrained_model_file, ret_args=True)
+model.float()
+model.eval()
+
+passage_embeddings = dict()
+DocPool = None
+QueryPool = None
+with torch.no_grad():
+    print(f'{keyword} Embedding passages ...', flush=True)
+    with progressbar.ProgressBar(max_value=len(all_passages), redirect_stdout=True) as bar:
+        for itr, (passage_id, passage) in enumerate(all_passages.items()):
+            if (itr % 100) == 0:
+                bar.update(itr)
+            passage.trim(508)
+            with torch.no_grad():
+                D = model.get_colbert_embeddings([passage], DOCUMENT_TYPE_ID)
+            DocPool = D.view(-1,D.size(-1)) if DocPool is None else torch.cat((DocPool, D.view(-1,D.size(-1))))
+            passage_embeddings[passage_id] = D
+
+    query_embeddings = dict()
+    Doc_Mean = DocPool.mean(dim=0)
+    Doc_Stdev = DocPool.std(dim=0)
+    del DocPool
+    print(f'{keyword} Embedding queries ...', flush=True)
+    with progressbar.ProgressBar(max_value=len(all_queries), redirect_stdout=True) as bar:
+        for itr, (query_id, query) in enumerate(all_queries.items()):
+            if (itr % 1000) == 0:
+                bar.update(itr)
+            query.trim(508)
+            with torch.no_grad():
+                Q = model.get_colbert_embeddings([query], QUESTION_TYPE_ID)
+            QueryPool = Q.view(-1, Q.size(-1)) if QueryPool is None else torch.cat((QueryPool, Q.view(-1, Q.size(-1))))
+            query_embeddings[query_id] = Q
+
+    Query_Mean = QueryPool.mean(dim=0)
+    Query_Stdev = QueryPool.std(dim=0)
+    del QueryPool
+
+    dev_triples = f'{DATA_DIR}/kinya-ag-retrieval/rw_ag_retrieval_qpntriplets_dev.tsv'
+    test_triples = f'{DATA_DIR}/kinya-ag-retrieval/rw_ag_retrieval_qpntriplets_test.tsv'
+
+    EVAL_SETS = [('DEV', dev_triples),
+                 ('TEST', test_triples)]
+
+for eval_set_name, eval_qpn_triples in EVAL_SETS:
+    eval_query_to_passage_ids = {(line.split('\t')[0]): (line.split('\t')[1]) for line in read_lines(eval_qpn_triples)}
+    Top = [1, 5, 10, 20, 30]
+    TopAcc = [0.0 for _ in Top]
+    MTop = [5, 10, 20, 30]
+    MRR = [0.0 for _ in MTop]
+    Total = 0.0
+    for itr,(query_id,target_doc_id) in enumerate(eval_query_to_passage_ids.items()):
+        query = all_queries[query_id]
+        with torch.no_grad():
+            Q = model.get_colbert_embeddings([query], QUESTION_TYPE_ID)
+        Q = (Q - Query_Mean) / Query_Stdev
+        Q = F.normalize(Q, p=2, dim=2)
+        results = []
+        for doc_id,D in passage_embeddings.items():
+            D = (D - Doc_Mean) / Doc_Stdev
+            D = F.normalize(D, p=2, dim=2)
+            with torch.no_grad():
+                score = model.pairwise_score(Q,D).squeeze().item()
+            score = score / Q.size(1)
+            results.append((score, doc_id))
+        Total += 1.0
+        results = sorted(results, key=lambda x: x[0], reverse=True)
+        for i, t in enumerate(Top):
+            TopAcc[i] += (1.0 if (target_doc_id in {idx for sc, idx in results[:t]}) else 0.0)
+        for i, t in enumerate(MTop):
+            top_rr = [(1 / (i + 1)) for i, (sc, idx) in enumerate(results[:t]) if idx == target_doc_id]
+            MRR[i] += (top_rr[0] if (len(top_rr) > 0) else 0.0)
+    print(f'-------------------------------------------------------------------------------------------------')
+    for i, t in enumerate(Top):
+        print(f'@{eval_set_name} Final {keyword}-{args.colbert_embedding_dim} kinya-ag-retrieval {eval_set_name} Set Top#{t} Accuracy:',
+              f'{(100.0 * TopAcc[i] / Total): .1f}% ({TopAcc[i]:.0f} / {Total:.0f})')
+    for i, t in enumerate(MTop):
+        print(f'@{eval_set_name} Final {keyword}-{args.colbert_embedding_dim} kinya-ag-retrieval {eval_set_name} Set MRR@{t}:',
+              f'{(100.0 * MRR[i] / Total): .1f}% ({MRR[i]:.0f} / {Total:.0f})')
+    print(f'-------------------------------------------------------------------------------------------------', flush=True)
+
+
+```
+
+
+### 4. Evaluating pre-trained RAGatouille ColBERT model on ["C4IR-RW/kinya-ag-retrieval"](https://huggingface.co/datasets/C4IR-RW/kinya-ag-retrieval)
+
+
+```python
+from deepkin.utils.misc_functions import read_lines
+from ragatouille import RAGPretrainedModel
+
+keyword = 'agai-colbert-10000'
+print(f'Evaluating {keyword} ...', flush=True)
+qa_query_id = 'kinya-ag-retrieval/rw_ag_retrieval_query_id.txt'
+qa_query_text = 'kinya-ag-retrieval/rw_ag_retrieval_query_text.txt'
+
+all_queries = {idx: txt for idx, txt in zip(read_lines(qa_query_id), read_lines(qa_query_text))}
+
+print(f'Got: {len(all_queries)} queries', flush=True)
+
+RAG = RAGPretrainedModel.from_index(f'ragatouille-kinya-colbert/indexes/agai-colbert-10000/')
+
+dev_triples = 'kinya-ag-retrieval/rw_ag_retrieval_qpntriplets_dev.tsv'
+test_triples = 'kinya-ag-retrieval/rw_ag_retrieval_qpntriplets_test.tsv'
+
+EVAL_SETS = [('DEV', dev_triples),
+             ('TEST', test_triples)]
+
+for eval_set_name, eval_qpn_triples in EVAL_SETS:
+    eval_query_to_passage_ids = {(line.split('\t')[0]): (line.split('\t')[1]) for line in
+                                 read_lines(eval_qpn_triples)}
+    Top = [1, 5, 10, 20, 30]
+    TopAcc = [0.0 for _ in Top]
+    MTop = [5, 10, 20, 30]
+    MRR = [0.0 for _ in MTop]
+    Total = 0.0
+    for itr, (query_id, target_doc_id) in enumerate(eval_query_to_passage_ids.items()):
+        query = all_queries[query_id]
+        results = RAG.search(query=query, k=max(max(50, max(Top)), max(MTop)))
+        results = [(d['score'],d['document_id']) for d in results]
+        Total += 1.0
+        results = sorted(results, key=lambda x: x[0], reverse=True)
+        for i, t in enumerate(Top):
+            TopAcc[i] += (1.0 if (target_doc_id in {idx for sc, idx in results[:t]}) else 0.0)
+        for i, t in enumerate(MTop):
+            top_rr = [(1 / (i + 1)) for i, (sc, idx) in enumerate(results[:t]) if idx == target_doc_id]
+            MRR[i] += (top_rr[0] if (len(top_rr) > 0) else 0.0)
+    print(f'-------------------------------------------------------------------------------------------------')
+    for i, t in enumerate(Top):
+        print(f'@{eval_set_name} Final {keyword} kinya-ag-retrieval {eval_set_name} Set Top#{t} Accuracy:',
+              f'{(100.0 * TopAcc[i] / Total): .1f}% ({TopAcc[i]:.0f} / {Total:.0f})')
+    for i, t in enumerate(MTop):
+        print(f'@{eval_set_name} Final {keyword} kinya-ag-retrieval {eval_set_name} Set MRR@{t}:',
+              f'{(100.0 * MRR[i] / Total): .1f}% ({MRR[i]:.0f} / {Total:.0f})')
+    print(f'-------------------------------------------------------------------------------------------------',
+          flush=True)
+
+
+```
+
+## References
+
+[1] Antoine Nzeyimana and Andre Niyongabo Rubungo. 2022. [KinyaBERT: a Morphology-aware Kinyarwanda Language Model](https://aclanthology.org/2022.acl-long.367/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5347–5363, Dublin, Ireland. Association for Computational Linguistics.
+
+[2] Antoine Nzeyimana, and Andre Niyongabo Rubungo. 2025. [KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation](https://arxiv.org/abs/2507.03241). arXiv preprint arXiv:2507.03241.
+
+
+## License
+
+This model is licensed under the [Creative Commons Attribution 4.0 International License (CC-BY 4.0)](https://creativecommons.org/licenses/by/4.0/). 
+
+**Attribution:** Please attribute this work to C4IR Rwanda and KiNLP.

kinya_colbert_large_rw_ag_retrieval_finetuned_512D.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd66f10c8b11480a6453d21adc9d0b77977ca638b762c4b78d5767af7e7b4a34
+size 1460919402

kinyabert_base_pretrained.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5273a0dcbd2b8d533aecd269af167528bf4d40ead8d75909401b73866273a29a
+size 1288602328

kinyabert_large_pretrained.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a6539d9b1a5bdd9408980c2cc6c38da5f7993bfcc5f41768d10021c2341acc
+size 4402338492

ragatouille-kinya-colbert/checkpoints/colbert-10000/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": 8,
+    "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": 5941,
+    "warmup": 5941,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 2,
+    "use_ib_negatives": true,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": "AfroColBERT",
+    "query_maxlen": 32,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 1024,
+    "doc_maxlen": 512,
+    "mask_punctuation": true,
+    "checkpoint": "Davlan\/bert-base-multilingual-cased-finetuned-kinyarwanda",
+    "triples": "\/mnt\/DATA\/AfroColBERT\/data\/triples.train.colbert.jsonl",
+    "collection": "\/mnt\/DATA\/AfroColBERT\/data\/corpus.train.colbert.tsv",
+    "queries": "\/mnt\/DATA\/AfroColBERT\/data\/queries.train.colbert.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": ".ragatouille\/",
+    "experiment": "colbert",
+    "index_root": null,
+    "name": "2025-05\/23\/11.52.12",
+    "rank": 0,
+    "nranks": 2,
+    "amp": true,
+    "gpus": 2,
+    "avoid_fork_if_possible": false,
+    "meta": {
+        "hostname": "nzeyi-x670e-e",
+        "current_datetime": "May 23, 2025 ; 12:47PM EDT (-0400)",
+        "cmd": "\/home\/nzeyi\/projects\/nzeyi\/kinlp\/flexkin\/scripts\/flex\/train\/colbert\/ragatouille_ag_train.py",
+        "version": "colbert-v0.4"
+    }
+}

ragatouille-kinya-colbert/checkpoints/colbert-10000/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Davlan/bert-base-multilingual-cased-finetuned-kinyarwanda",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "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",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

ragatouille-kinya-colbert/checkpoints/colbert-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34757553ef11e93fad8b6fcfaf4794bf59e87a3cfbecddf1be37337aac062f61
+size 714582952

ragatouille-kinya-colbert/checkpoints/colbert-10000/special_tokens_map.json

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

ragatouille-kinya-colbert/checkpoints/colbert-10000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": false,
+  "extra_special_tokens": {},
+  "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]"
+}

ragatouille-kinya-colbert/indexes/agai-colbert-10000/0.codes.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567d4c3eddf91b66651c8346d9acbbd0015c8b25aa7c13bcb5331791e5531bbb
+size 345308

ragatouille-kinya-colbert/indexes/agai-colbert-10000/0.metadata.json

@@ -0,0 +1,6 @@
+{
+    "passage_offset": 0,
+    "num_passages": 493,
+    "num_embeddings": 86043,
+    "embedding_offset": 0
+}

ragatouille-kinya-colbert/indexes/agai-colbert-10000/0.residuals.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a63ee080fa49edc681773664bc192f30902201d556b19d4d8eb64448b0fb74
+size 44055216

ragatouille-kinya-colbert/indexes/agai-colbert-10000/1.codes.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8bc06c78f227ce6eb8f98e1625118209b2291daab0faa0aec2064539266c5b
+size 427996

ragatouille-kinya-colbert/indexes/agai-colbert-10000/1.metadata.json

@@ -0,0 +1,6 @@
+{
+    "passage_offset": 493,
+    "num_passages": 491,
+    "num_embeddings": 106705,
+    "embedding_offset": 86043
+}

ragatouille-kinya-colbert/indexes/agai-colbert-10000/1.residuals.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ced4a7b272d593ea2c3994292fc138b6471e3aae0053e723f7135721f87af1
+size 54634160

ragatouille-kinya-colbert/indexes/agai-colbert-10000/avg_residual.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f441f55a6baeb9c35624e114de8554e464147a266f9dace6b240592dbf5fab3
+size 1205

ragatouille-kinya-colbert/indexes/agai-colbert-10000/buckets.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5067854deaf83ee47a09e91163bc26a09a7b2f69ad114bcbe9d3172ec64df4
+size 1432

ragatouille-kinya-colbert/indexes/agai-colbert-10000/centroids.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d6d097c1ed2b23816f2c1992c4a974d94d098de7221082cb44ce693dc27adb
+size 8389798

ragatouille-kinya-colbert/indexes/agai-colbert-10000/doclens.0.json

@@ -0,0 +1 @@
+[134,456,454,450,127,318,46,181,195,352,127,353,46,280,66,164,74,91,435,122,171,108,356,186,73,97,128,126,101,50,64,83,160,107,73,84,85,17,56,17,112,70,17,83,17,118,114,117,117,56,47,98,179,107,153,146,24,64,319,445,253,98,337,272,98,344,85,101,471,87,112,123,172,131,104,97,472,384,168,195,92,18,23,167,233,70,180,77,132,135,66,202,208,375,186,173,391,211,83,294,122,59,422,92,213,62,58,32,98,118,107,66,431,98,122,39,178,245,139,73,138,222,270,87,109,180,187,213,282,343,308,275,470,289,28,82,91,305,117,76,215,31,41,70,61,196,95,32,131,206,125,130,137,117,183,238,132,147,65,109,109,77,76,122,158,159,164,44,89,106,83,73,142,66,131,198,146,46,163,147,73,164,191,54,154,129,94,85,189,71,166,128,69,66,100,44,99,106,163,135,109,194,61,36,74,95,117,25,40,53,278,48,40,87,130,67,91,110,62,106,114,91,131,134,57,96,56,50,260,184,203,469,137,173,130,298,225,75,107,161,116,235,418,122,65,129,338,168,420,156,43,464,465,246,454,463,380,323,479,474,127,129,114,107,426,315,431,353,162,237,52,50,78,22,77,118,260,206,283,78,125,256,101,465,276,169,215,230,266,160,95,358,277,129,468,249,221,81,31,42,84,188,95,189,158,124,153,204,145,158,102,427,287,76,162,430,242,344,135,129,121,132,120,155,48,81,470,420,300,400,166,118,112,66,187,186,228,314,153,116,208,138,132,54,83,469,316,240,279,95,338,280,335,263,227,294,271,99,169,90,116,160,120,299,113,330,401,212,130,252,271,345,260,299,269,314,54,395,138,218,105,246,88,453,122,116,98,80,191,58,164,124,140,87,149,183,104,147,325,16,70,189,197,36,106,37,26,67,162,76,121,132,71,138,278,216,208,208,87,79,16,91,73,92,252,123,167,67,54,119,173,333,200,85,319,142,226,216,237,366,311,366,315,259,193,218,119,232,346,94,155,93,442,243,198,149,270,190,386,199,207,292,287,138,162,226,205,179,105,105,230,69,91,74,76,332,144,221,133,75,467,285,196,96,101,366,331,443,99,383,181,45,176]

ragatouille-kinya-colbert/indexes/agai-colbert-10000/doclens.1.json

@@ -0,0 +1 @@
+[196,116,210,274,205,285,379,179,176,166,110,217,199,200,290,111,376,198,113,255,196,283,198,226,214,218,197,241,80,380,170,198,185,354,238,320,259,280,94,62,161,265,296,76,196,342,260,207,291,135,237,233,77,309,364,486,138,124,177,52,164,184,218,173,201,193,72,150,230,235,379,196,322,351,384,171,284,29,111,196,24,178,266,232,23,362,73,173,37,195,421,246,360,204,326,390,278,146,142,188,433,305,278,280,84,36,17,55,159,69,111,257,147,327,359,339,344,17,275,287,242,156,210,327,159,125,213,54,170,160,310,436,165,76,162,197,480,65,275,220,269,140,131,186,167,305,136,21,258,90,13,16,102,155,208,265,74,362,94,180,201,23,49,20,21,14,128,56,23,141,33,14,263,179,103,427,205,174,229,238,306,274,205,167,116,483,86,403,84,242,321,477,19,214,252,466,435,85,231,185,313,129,314,77,81,474,449,475,370,154,462,394,245,139,88,86,118,121,19,200,148,38,82,104,146,71,143,421,174,151,94,125,180,218,256,71,343,271,69,481,44,126,36,86,140,84,102,249,25,55,94,153,190,114,304,123,61,137,243,407,90,34,37,14,36,32,36,32,35,32,47,58,55,48,47,22,143,478,79,129,85,221,162,294,77,92,103,66,224,76,339,94,24,68,234,77,116,100,304,148,236,86,450,111,84,205,122,255,462,246,245,345,211,460,172,118,185,14,106,201,173,18,144,97,96,27,376,169,411,476,456,212,222,221,243,448,479,482,363,210,201,134,212,238,224,230,192,169,347,460,465,87,285,391,288,311,320,245,389,444,460,472,312,355,316,196,387,84,95,198,165,404,481,223,161,147,223,471,86,206,366,197,467,414,351,417,215,203,278,453,396,295,277,162,148,282,252,149,452,326,72,84,329,304,383,474,232,447,429,195,150,190,373,83,119,106,34,178,112,118,236,142,124,225,252,256,359,159,52,63,61,109,29,137,131,186,126,197,476,139,74,451,84,124,101,467,474,475,467,471,276,474,473,463,314,180,243,288,469,416,202,399,450,455,480,140,339,344,331,241,160,270,225,212,318,97,275,290,340,358,272,312,146,201,486,435,289,170,293,188,340]

ragatouille-kinya-colbert/indexes/agai-colbert-10000/ivf.pid.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a654d8022b9bb5721f0e30696ed494b8dd538e19e6eb02b9a9e83251569ba0c
+size 127896

ragatouille-kinya-colbert/indexes/agai-colbert-10000/metadata.json

@@ -0,0 +1,73 @@
+{
+  "config":{
+    "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":32,
+    "nbits":4,
+    "kmeans_niters":20,
+    "resume":false,
+    "pool_factor":1,
+    "clustering_mode":"hierarchical",
+    "protected_tokens":0,
+    "similarity":"cosine",
+    "bsize":64,
+    "accumsteps":1,
+    "lr":0.000005,
+    "maxsteps":500000,
+    "save_every":5941,
+    "warmup":5941,
+    "warmup_bert":null,
+    "relu":false,
+    "nway":2,
+    "use_ib_negatives":true,
+    "reranker":false,
+    "distillation_alpha":1.0,
+    "ignore_scores":false,
+    "model_name":"AfroColBERT",
+    "query_maxlen":32,
+    "attend_to_mask_tokens":false,
+    "interaction":"colbert",
+    "dim":1024,
+    "doc_maxlen":512,
+    "mask_punctuation":true,
+    "checkpoint":"/mnt/DATA/AfroColBERT/.ragatouille/colbert/none/2025-05/23/11.52.12/checkpoints/colbert-10000/",
+    "triples":"/mnt/DATA/AfroColBERT/data/triples.train.colbert.jsonl",
+    "collection":[
+      "list with 984 elements starting with...",
+      [
+        "Inkoko irwaye irangwa n' ibi bikurikira : Iyo indwara yateye mu nkoko , ibigaragaza ubuzima bwazo bwiza birabura cyangwa bigahinduka . Usanga inkoko zigunze , zikonje , zisinzira , ndetse zimwe zahiniye amajosi mu mababa . Amababa n' ibirokoroko byijimye . Akenshi ntizirya cyangwa ugasanga ari imwe imwe itoratora . Hari ubwo usanga zose zihitwa ; hakaba n' ubwo zihitwa amaraso .",
+        "Uburyo indwara y' ubushita yandura mu nkoko : Ino ndwara iboneka mu nkoko zose ( into n' inkuru ) . Ni indwara mbi cyane iterwa na virusi . Inkoko zirwaye zanduza izindi . Ibikoresho byanduye nabyo bishobora kwanduza inkoko ino ndwara . Ibimenyetso by' indwara y' ubushita ( Fowl pox ) mu nkoko : Kugagara amaguru , ijosi n' amababa . Utubyimba duto kumaguru ; Igisunzu mumaso ; Kugira umuriro ; Udusebe mu kanwa no mu muhogo ; Gutakaza ibiro ( kunanuka / guhorota ) Kubyimba kwaho amababa atereye ; Ubuhumyi ; Guhombana kw' agatorero ; Kutarya no kutanywa ; Igabanuka ry' amagi ndetse n' impfu za hato nahato ; Ni iki wakora ngo ukumire indwara y' ubushita ( Fowl pox ) mu nkoko ; Kubera ko urukingo rw' iyi ndwara rutangwa ku mishwi ikivuka ( umunsi umwe ) ; umworozi asabwa kugura imishwi mu ituragiro ryizewe azi ko zayikingiwe ( akanahabwa icyemezo cyuko zakingiwe ) . Nta bundi buryo buhari bwo kuyirinda . Kwirinda no kuvura indwara y' Ubushita ( Fowl pox ) mu nkoko : Iyi ndwara nta muti igira . Kuyirinda ukurikiza amabwiriza yose y' isuku nicyo gisubizo cyonyine . Irinde kujya mu biraro by' inkoko bifite iyi ndwara . Mu gihe uguze izindi nkoko ugomba kuzishyira mu kato byibuze mu gihe cy' amezi 2 kugira ngo urebe niba nta burwayi zifite . Irinde imibu n' amasazi kuko bishobora kwanduza inkoko iyi ndwara .",
+        "Gukingira inkoko z' inyama ; Igihe inkoko zimaze iminsi 2 : Inkoko zikorerwa urukingo rwa Umuraramo ( New Castle ) . Igipimo cy' umuti ni New Castle HB 1 : agacupa k' inkingo 1000 bashyira muri litiro 20 z' amazi meza . Igihe inkoko zimaze iminsi 1 kugeza kuri 4 : Inkoko zihabwa Vitamine ( Anti - stress ) . Igipimo cy' umuti ni AMINOVIT : garama 1 bayivanga na litiro 1 y' amazi meza . Igihe inkoko zimaze iminsi 5 - 7 : Inkoko zikorerwa gukumira Kogusidiyoze . Igipimo cy' umuti ni VETACOX : garama 1 bayivanga na litiro 2 z' amazi meza . Igihe inkoko zimaze iminsi 7 : Inkoko zikorerwa urukingo rwa GUMBORO . Igipimo cy' umuti ni Cevac Gumbo L : agacupa k' inkingo 1000 bashyira muri litiro 20 z' amazi meza . Igihe inkoko zimaze iminsi 14 : Inkoko zikorerwa urukingo rwa Umuraramo ( New Castle ) . Igipimo cy' umuti ni Newcastle La sota : agacupa ka doze 1000 bashyira muri litiro 20 z' amazi meza . 6 . Igihe inkoko zimaze iminsi 17 - 19 : Inkoko zikorerwa gukumira Kogusidiyoze . Igipimo cy' umuti ni Amprolium : garama 1 bayivanga na litiro 1 y' amazi meza . 7 . Igihe inkoko zimaze iminsi 21 : Inkoko zikorerwa urukingo rwa GUMBORO . Igipimo cy' umuti ni Cevac Gumbo L : agacupa ka doze 1000 bashyira muri litiro 20 z' amazi meza ; Icyitonderwa : Igihe indwara igaragaye mu nkoko , umworozi agomba guhita ahamagara umuganga w' amatungo uri hafi wemewe . Ubutabazi bw' ibanze : Mu gihe ugitegereje umuganga w' amatungo nibyiza kuziha amavitamine , imyunyungugu , amazi meza n' indyo yuzuye no kuzitaho ."
+      ]
+    ],
+    "queries":"/mnt/DATA/AfroColBERT/data/queries.train.colbert.tsv",
+    "index_name":"agai-colbert-10000",
+    "overwrite":false,
+    "root":".ragatouille/",
+    "experiment":"colbert",
+    "index_root":null,
+    "name":"2025-05/23/18.01.47",
+    "rank":0,
+    "nranks":2,
+    "amp":true,
+    "gpus":2,
+    "avoid_fork_if_possible":false
+  },
+  "num_chunks":2,
+  "num_partitions":4096,
+  "num_embeddings":192748,
+  "avg_doclen":195.8821138211,
+  "RAGatouille":{
+    "index_config":{
+      "index_type":"PLAID",
+      "index_name":"agai-colbert-10000"
+    }
+  }
+}

ragatouille-kinya-colbert/indexes/agai-colbert-10000/pid_docid_map.json

@@ -0,0 +1,986 @@
+{
+  "0":"A000T639",
+  "1":"A001T643",
+  "2":"A002T641",
+  "3":"A003T640",
+  "4":"A004T637",
+  "5":"A005T636",
+  "6":"A006T634",
+  "7":"A007T633",
+  "8":"A008T632",
+  "9":"A009T628",
+  "10":"A010T627",
+  "11":"A011T624",
+  "12":"A012T621",
+  "13":"A013T619",
+  "14":"A014T618",
+  "15":"A015T614",
+  "16":"A016T612",
+  "17":"A017T611",
+  "18":"A018T610",
+  "19":"A019T620",
+  "20":"A020T001",
+  "21":"A021T563",
+  "22":"A022T565",
+  "23":"A023T580",
+  "24":"A024T578",
+  "25":"A025T602",
+  "26":"A026T603",
+  "27":"A027T575",
+  "28":"A028T002",
+  "29":"A029T003",
+  "30":"A030T004",
+  "31":"A031T005",
+  "32":"A032T006",
+  "33":"A033T007",
+  "34":"A034T008",
+  "35":"A035T009",
+  "36":"A036T011",
+  "37":"A037T014",
+  "38":"A038T023",
+  "39":"A039T033",
+  "40":"A040T026",
+  "41":"A041T027",
+  "42":"A042T030",
+  "43":"A043T025",
+  "44":"A044T010",
+  "45":"A045T017",
+  "46":"A046T018",
+  "47":"A047T020",
+  "48":"A048T021",
+  "49":"A049T022",
+  "50":"A050T024",
+  "51":"A051T035",
+  "52":"A052T036",
+  "53":"A053T037",
+  "54":"A054T040",
+  "55":"A055T041",
+  "56":"A056T043",
+  "57":"A057T044",
+  "58":"A058T046",
+  "59":"A059T047",
+  "60":"A060T048",
+  "61":"A061T049",
+  "62":"A062T063",
+  "63":"A063T052",
+  "64":"A064T053",
+  "65":"A065T050",
+  "66":"A066T054",
+  "67":"A067T056",
+  "68":"A068T055",
+  "69":"A069T057",
+  "70":"A070T058",
+  "71":"A071T059",
+  "72":"A072T060",
+  "73":"A073T061",
+  "74":"A074T062",
+  "75":"A075T064",
+  "76":"A076T066",
+  "77":"A077T067",
+  "78":"A078T068",
+  "79":"A079T069",
+  "80":"A080T045",
+  "81":"A081T644",
+  "82":"A082T645",
+  "83":"A083T070",
+  "84":"A084T646",
+  "85":"A085T647",
+  "86":"A086T648",
+  "87":"A087T071",
+  "88":"A088T649",
+  "89":"A089T072",
+  "90":"A090T650",
+  "91":"A091T073",
+  "92":"A092T074",
+  "93":"A093T075",
+  "94":"A094T076",
+  "95":"A095T077",
+  "96":"A096T078",
+  "97":"A097T079",
+  "98":"A098T080",
+  "99":"A099T651",
+  "100":"A100T652",
+  "101":"A101T081",
+  "102":"A102T082",
+  "103":"A103T084",
+  "104":"A104T085",
+  "105":"A105T086",
+  "106":"A106T087",
+  "107":"A107T653",
+  "108":"A108T654",
+  "109":"A109T019",
+  "110":"A110T088",
+  "111":"A111T089",
+  "112":"A112T090",
+  "113":"A113T091",
+  "114":"A114T092",
+  "115":"A115T093",
+  "116":"A116T094",
+  "117":"A117T095",
+  "118":"A118T096",
+  "119":"A119T097",
+  "120":"A120T098",
+  "121":"A121T100",
+  "122":"A122T102",
+  "123":"A123T103",
+  "124":"A124T104",
+  "125":"A125T105",
+  "126":"A126T106",
+  "127":"A127T107",
+  "128":"A128T108",
+  "129":"A129T109",
+  "130":"A130T110",
+  "131":"A131T111",
+  "132":"A132T112",
+  "133":"A133T113",
+  "134":"A134T114",
+  "135":"A135T115",
+  "136":"A136T116",
+  "137":"A137T117",
+  "138":"A138T118",
+  "139":"A139T119",
+  "140":"A140T120",
+  "141":"A141T121",
+  "142":"A142T123",
+  "143":"A143T125",
+  "144":"A144T124",
+  "145":"A145T126",
+  "146":"A146T127",
+  "147":"A147T099",
+  "148":"A148T128",
+  "149":"A149T129",
+  "150":"A150T130",
+  "151":"A151T131",
+  "152":"A152T132",
+  "153":"A153T133",
+  "154":"A154T134",
+  "155":"A155T135",
+  "156":"A156T136",
+  "157":"A157T137",
+  "158":"A158T138",
+  "159":"A159T139",
+  "160":"A160T140",
+  "161":"A161T141",
+  "162":"A162T143",
+  "163":"A163T144",
+  "164":"A164T145",
+  "165":"A165T146",
+  "166":"A166T147",
+  "167":"A167T148",
+  "168":"A168T149",
+  "169":"A169T150",
+  "170":"A170T151",
+  "171":"A171T152",
+  "172":"A172T153",
+  "173":"A173T154",
+  "174":"A174T155",
+  "175":"A175T156",
+  "176":"A176T157",
+  "177":"A177T158",
+  "178":"A178T159",
+  "179":"A179T160",
+  "180":"A180T161",
+  "181":"A181T162",
+  "182":"A182T163",
+  "183":"A183T164",
+  "184":"A184T165",
+  "185":"A185T166",
+  "186":"A186T167",
+  "187":"A187T168",
+  "188":"A188T169",
+  "189":"A189T170",
+  "190":"A190T171",
+  "191":"A191T172",
+  "192":"A192T173",
+  "193":"A193T174",
+  "194":"A194T175",
+  "195":"A195T176",
+  "196":"A196T177",
+  "197":"A197T178",
+  "198":"A198T179",
+  "199":"A199T180",
+  "200":"A200T181",
+  "201":"A201T182",
+  "202":"A202T183",
+  "203":"A203T184",
+  "204":"A204T186",
+  "205":"A205T187",
+  "206":"A206T185",
+  "207":"A207T188",
+  "208":"A208T189",
+  "209":"A209T190",
+  "210":"A210T191",
+  "211":"A211T192",
+  "212":"A212T193",
+  "213":"A213T194",
+  "214":"A214T195",
+  "215":"A215T196",
+  "216":"A216T197",
+  "217":"A217T198",
+  "218":"A218T199",
+  "219":"A219T200",
+  "220":"A220T201",
+  "221":"A221T202",
+  "222":"A222T203",
+  "223":"A223T204",
+  "224":"A224T206",
+  "225":"A225T207",
+  "226":"A226T208",
+  "227":"A227T209",
+  "228":"A228T210",
+  "229":"A229T655",
+  "230":"A230T656",
+  "231":"A231T657",
+  "232":"A232T658",
+  "233":"A233T659",
+  "234":"A234T660",
+  "235":"A235T661",
+  "236":"A236T662",
+  "237":"A237T663",
+  "238":"A238T664",
+  "239":"A239T665",
+  "240":"A240T667",
+  "241":"A241T668",
+  "242":"A242T669",
+  "243":"A243T670",
+  "244":"A244T671",
+  "245":"A245T672",
+  "246":"A246T673",
+  "247":"A247T674",
+  "248":"A248T675",
+  "249":"A249T676",
+  "250":"A250T677",
+  "251":"A251T678",
+  "252":"A252T683",
+  "253":"A253T684",
+  "254":"A254T685",
+  "255":"A255T686",
+  "256":"A256T687",
+  "257":"A257T688",
+  "258":"A258T689",
+  "259":"A259T690",
+  "260":"A260T691",
+  "261":"A261T692",
+  "262":"A262T693",
+  "263":"A263T694",
+  "264":"A264T695",
+  "265":"A265T696",
+  "266":"A266T697",
+  "267":"A267T698",
+  "268":"A268T699",
+  "269":"A269T700",
+  "270":"A270T701",
+  "271":"A271T702",
+  "272":"A272T703",
+  "273":"A273T704",
+  "274":"A274T705",
+  "275":"A275T706",
+  "276":"A276T707",
+  "277":"A277T708",
+  "278":"A278T709",
+  "279":"A279T710",
+  "280":"A280T711",
+  "281":"A281T712",
+  "282":"A282T713",
+  "283":"A283T714",
+  "284":"A284T715",
+  "285":"A285T716",
+  "286":"A286T717",
+  "287":"A287T718",
+  "288":"A288T719",
+  "289":"A289T720",
+  "290":"A290T721",
+  "291":"A291T722",
+  "292":"A292T723",
+  "293":"A293T724",
+  "294":"A294T725",
+  "295":"A295T726",
+  "296":"A296T727",
+  "297":"A297T728",
+  "298":"A298T729",
+  "299":"A299T730",
+  "300":"A300T731",
+  "301":"A301T732",
+  "302":"A302T733",
+  "303":"A303T734",
+  "304":"A304T735",
+  "305":"A305T736",
+  "306":"A306T737",
+  "307":"A307T738",
+  "308":"A308T739",
+  "309":"A309T740",
+  "310":"A310T741",
+  "311":"A311T742",
+  "312":"A312T743",
+  "313":"A313T744",
+  "314":"A314T745",
+  "315":"A315T746",
+  "316":"A316T747",
+  "317":"A317T748",
+  "318":"A318T749",
+  "319":"A319T750",
+  "320":"A320T751",
+  "321":"A321T752",
+  "322":"A322T753",
+  "323":"A323T754",
+  "324":"A324T755",
+  "325":"A325T756",
+  "326":"A326T757",
+  "327":"A327T758",
+  "328":"A328T759",
+  "329":"A329T760",
+  "330":"A330T761",
+  "331":"A331T762",
+  "332":"A332T763",
+  "333":"A333T764",
+  "334":"A334T765",
+  "335":"A335T766",
+  "336":"A336T767",
+  "337":"A337T768",
+  "338":"A338T769",
+  "339":"A339T770",
+  "340":"A340T771",
+  "341":"A341T772",
+  "342":"A342T773",
+  "343":"A343T774",
+  "344":"A344T775",
+  "345":"A345T776",
+  "346":"A346T777",
+  "347":"A347T778",
+  "348":"A348T779",
+  "349":"A349T780",
+  "350":"A350T781",
+  "351":"A351T782",
+  "352":"A352T783",
+  "353":"A353T784",
+  "354":"A354T785",
+  "355":"A355T786",
+  "356":"A356T787",
+  "357":"A357T788",
+  "358":"A358T789",
+  "359":"A359T790",
+  "360":"A360T791",
+  "361":"A361T792",
+  "362":"A362T793",
+  "363":"A363T794",
+  "364":"A364T795",
+  "365":"A365T796",
+  "366":"A366T797",
+  "367":"A367T798",
+  "368":"A368T799",
+  "369":"A369T800",
+  "370":"A370T801",
+  "371":"A371T802",
+  "372":"A372T803",
+  "373":"A373T804",
+  "374":"A374T805",
+  "375":"A375T806",
+  "376":"A376T807",
+  "377":"A377T808",
+  "378":"A378T809",
+  "379":"A379T810",
+  "380":"A380T811",
+  "381":"A381T812",
+  "382":"A382T813",
+  "383":"A383T814",
+  "384":"A384T815",
+  "385":"A385T816",
+  "386":"A386T817",
+  "387":"A387T818",
+  "388":"A388T819",
+  "389":"A389T820",
+  "390":"A390T821",
+  "391":"A391T823",
+  "392":"A392T824",
+  "393":"A393T825",
+  "394":"A394T827",
+  "395":"A395T828",
+  "396":"A396T829",
+  "397":"A397T830",
+  "398":"A398T831",
+  "399":"A399T832",
+  "400":"A400T833",
+  "401":"A401T834",
+  "402":"A402T835",
+  "403":"A403T211",
+  "404":"A404T212",
+  "405":"A405T213",
+  "406":"A406T214",
+  "407":"A407T215",
+  "408":"A408T216",
+  "409":"A409T217",
+  "410":"A410T218",
+  "411":"A411T219",
+  "412":"A412T220",
+  "413":"A413T221",
+  "414":"A414T223",
+  "415":"A415T224",
+  "416":"A416T225",
+  "417":"A417T226",
+  "418":"A418T227",
+  "419":"A419T228",
+  "420":"A420T229",
+  "421":"A421T230",
+  "422":"A422T231",
+  "423":"A423T232",
+  "424":"A424T233",
+  "425":"A425T234",
+  "426":"A426T235",
+  "427":"A427T236",
+  "428":"A428T237",
+  "429":"A429T238",
+  "430":"A430T239",
+  "431":"A431T240",
+  "432":"A432T241",
+  "433":"A433T242",
+  "434":"A434T243",
+  "435":"A435T245",
+  "436":"A436T244",
+  "437":"A437T246",
+  "438":"A438T247",
+  "439":"A439T248",
+  "440":"A440T249",
+  "441":"A441T250",
+  "442":"A442T251",
+  "443":"A443T252",
+  "444":"A444T253",
+  "445":"A445T254",
+  "446":"A446T255",
+  "447":"A447T256",
+  "448":"A448T257",
+  "449":"A449T258",
+  "450":"A450T259",
+  "451":"A451T260",
+  "452":"A452T261",
+  "453":"A453T262",
+  "454":"A454T263",
+  "455":"A455T264",
+  "456":"A456T265",
+  "457":"A457T266",
+  "458":"A458T267",
+  "459":"A459T268",
+  "460":"A460T269",
+  "461":"A461T270",
+  "462":"A462T271",
+  "463":"A463T272",
+  "464":"A464T273",
+  "465":"A465T274",
+  "466":"A466T275",
+  "467":"A467T276",
+  "468":"A468T277",
+  "469":"A469T278",
+  "470":"A470T279",
+  "471":"A471T280",
+  "472":"A472T281",
+  "473":"A473T282",
+  "474":"A474T283",
+  "475":"A475T284",
+  "476":"A476T285",
+  "477":"A477T286",
+  "478":"A478T287",
+  "479":"A479T288",
+  "480":"A480T289",
+  "481":"A481T291",
+  "482":"A482T293",
+  "483":"A483T292",
+  "484":"A484T294",
+  "485":"A485T295",
+  "486":"A486T296",
+  "487":"A487T297",
+  "488":"A488T299",
+  "489":"A489T300",
+  "490":"A490T301",
+  "491":"A491T302",
+  "492":"A492T303",
+  "493":"A493T304",
+  "494":"A494T305",
+  "495":"A495T306",
+  "496":"A496T307",
+  "497":"A497T308",
+  "498":"A498T309",
+  "499":"A499T310",
+  "500":"A500T311",
+  "501":"A501T312",
+  "502":"A502T313",
+  "503":"A503T314",
+  "504":"A504T315",
+  "505":"A505T316",
+  "506":"A506T317",
+  "507":"A507T318",
+  "508":"A508T319",
+  "509":"A509T320",
+  "510":"A510T321",
+  "511":"A511T322",
+  "512":"A512T323",
+  "513":"A513T324",
+  "514":"A514T325",
+  "515":"A515T326",
+  "516":"A516T327",
+  "517":"A517T328",
+  "518":"A518T329",
+  "519":"A519T330",
+  "520":"A520T331",
+  "521":"A521T332",
+  "522":"A522T333",
+  "523":"A523T334",
+  "524":"A524T335",
+  "525":"A525T336",
+  "526":"A526T337",
+  "527":"A527T338",
+  "528":"A528T339",
+  "529":"A529T340",
+  "530":"A530T341",
+  "531":"A531T342",
+  "532":"A532T343",
+  "533":"A533T344",
+  "534":"A534T345",
+  "535":"A535T346",
+  "536":"A536T347",
+  "537":"A537T349",
+  "538":"A538T350",
+  "539":"A539T351",
+  "540":"A540T352",
+  "541":"A541T353",
+  "542":"A542T354",
+  "543":"A543T355",
+  "544":"A544T356",
+  "545":"A545T357",
+  "546":"A546T358",
+  "547":"A547T359",
+  "548":"A548T360",
+  "549":"A549T361",
+  "550":"A550T362",
+  "551":"A551T363",
+  "552":"A552T364",
+  "553":"A553T365",
+  "554":"A554T366",
+  "555":"A555T367",
+  "556":"A556T368",
+  "557":"A557T369",
+  "558":"A558T370",
+  "559":"A559T371",
+  "560":"A560T372",
+  "561":"A561T373",
+  "562":"A562T374",
+  "563":"A563T375",
+  "564":"A564T376",
+  "565":"A565T377",
+  "566":"A566T378",
+  "567":"A567T379",
+  "568":"A568T380",
+  "569":"A569T381",
+  "570":"A570T382",
+  "571":"A571T383",
+  "572":"A572T384",
+  "573":"A573T385",
+  "574":"A574T386",
+  "575":"A575T387",
+  "576":"A576T388",
+  "577":"A577T389",
+  "578":"A578T390",
+  "579":"A579T391",
+  "580":"A580T392",
+  "581":"A581T393",
+  "582":"A582T394",
+  "583":"A583T395",
+  "584":"A584T396",
+  "585":"A585T397",
+  "586":"A586T398",
+  "587":"A587T399",
+  "588":"A588T400",
+  "589":"A589T401",
+  "590":"A590T402",
+  "591":"A591T403",
+  "592":"A592T404",
+  "593":"A593T405",
+  "594":"A594T406",
+  "595":"A595T407",
+  "596":"A596T408",
+  "597":"A597T409",
+  "598":"A598T410",
+  "599":"A599T411",
+  "600":"A600T412",
+  "601":"A601T413",
+  "602":"A602T414",
+  "603":"A603T415",
+  "604":"A604T416",
+  "605":"A605T417",
+  "606":"A606T418",
+  "607":"A607T419",
+  "608":"A608T420",
+  "609":"A609T421",
+  "610":"A610T422",
+  "611":"A611T423",
+  "612":"A612T424",
+  "613":"A613T425",
+  "614":"A614T426",
+  "615":"A615T427",
+  "616":"A616T428",
+  "617":"A617T429",
+  "618":"A618T430",
+  "619":"A619T431",
+  "620":"A620T433",
+  "621":"A621T434",
+  "622":"A622T435",
+  "623":"A623T436",
+  "624":"A624T437",
+  "625":"A625T438",
+  "626":"A626T439",
+  "627":"A627T440",
+  "628":"A628T441",
+  "629":"A629T442",
+  "630":"A630T443",
+  "631":"A631T444",
+  "632":"A632T445",
+  "633":"A633T446",
+  "634":"A634T447",
+  "635":"A635T448",
+  "636":"A636T449",
+  "637":"A637T450",
+  "638":"A638T451",
+  "639":"A639T452",
+  "640":"A640T453",
+  "641":"A641T454",
+  "642":"A642T455",
+  "643":"A643T456",
+  "644":"A644T457",
+  "645":"A645T458",
+  "646":"A646T459",
+  "647":"A647T460",
+  "648":"A648T461",
+  "649":"A649T463",
+  "650":"A650T464",
+  "651":"A651T462",
+  "652":"A652T465",
+  "653":"A653T466",
+  "654":"A654T467",
+  "655":"A655T468",
+  "656":"A656T470",
+  "657":"A657T469",
+  "658":"A658T471",
+  "659":"A659T472",
+  "660":"A660T473",
+  "661":"A661T474",
+  "662":"A662T475",
+  "663":"A663T476",
+  "664":"A664T477",
+  "665":"A665T479",
+  "666":"A666T480",
+  "667":"A667T481",
+  "668":"A668T482",
+  "669":"A669T483",
+  "670":"A670T484",
+  "671":"A671T478",
+  "672":"A672T502",
+  "673":"A673T492",
+  "674":"A674T498",
+  "675":"A675T485",
+  "676":"A676T486",
+  "677":"A677T488",
+  "678":"A678T490",
+  "679":"A679T489",
+  "680":"A680T495",
+  "681":"A681T487",
+  "682":"A682T497",
+  "683":"A683T491",
+  "684":"A684T499",
+  "685":"A685T496",
+  "686":"A686T493",
+  "687":"A687T503",
+  "688":"A688T494",
+  "689":"A689T500",
+  "690":"A690T509",
+  "691":"A691T510",
+  "692":"A692T511",
+  "693":"A693T512",
+  "694":"A694T513",
+  "695":"A695T514",
+  "696":"A696T515",
+  "697":"A697T516",
+  "698":"A698T517",
+  "699":"A699T501",
+  "700":"A700T504",
+  "701":"A701T505",
+  "702":"A702T506",
+  "703":"A703T507",
+  "704":"A704T508",
+  "705":"A705T518",
+  "706":"A706T519",
+  "707":"A707T520",
+  "708":"A708T521",
+  "709":"A709T522",
+  "710":"A710T524",
+  "711":"A711T525",
+  "712":"A712T526",
+  "713":"A713T527",
+  "714":"A714T528",
+  "715":"A715T529",
+  "716":"A716T530",
+  "717":"A717T531",
+  "718":"A718T532",
+  "719":"A719T533",
+  "720":"A720T534",
+  "721":"A721T535",
+  "722":"A722T536",
+  "723":"A723T537",
+  "724":"A724T538",
+  "725":"A725T539",
+  "726":"A726T540",
+  "727":"A727T541",
+  "728":"A728T543",
+  "729":"A729T544",
+  "730":"A730T545",
+  "731":"A731T546",
+  "732":"A732T547",
+  "733":"A733T548",
+  "734":"A734T549",
+  "735":"A735T550",
+  "736":"A736T551",
+  "737":"A737T553",
+  "738":"A738T554",
+  "739":"A739T555",
+  "740":"A740T556",
+  "741":"A741T557",
+  "742":"A742T558",
+  "743":"A743T560",
+  "744":"A744T561",
+  "745":"A745T562",
+  "746":"A746T564",
+  "747":"A747T566",
+  "748":"A748T572",
+  "749":"A749T573",
+  "750":"A750T574",
+  "751":"A751T576",
+  "752":"A752T577",
+  "753":"A753T579",
+  "754":"A754T582",
+  "755":"A755T584",
+  "756":"A756T583",
+  "757":"A757T585",
+  "758":"A758T586",
+  "759":"A759T587",
+  "760":"A760T588",
+  "761":"A761T589",
+  "762":"A762T590",
+  "763":"A763T591",
+  "764":"A764T592",
+  "765":"A765T593",
+  "766":"A766T594",
+  "767":"A767T595",
+  "768":"A768T596",
+  "769":"A769T597",
+  "770":"A770T598",
+  "771":"A771T599",
+  "772":"A772T600",
+  "773":"A773T604",
+  "774":"A774T542",
+  "775":"A775T607",
+  "776":"A776T606",
+  "777":"A777T608",
+  "778":"A778T609",
+  "779":"A779T615",
+  "780":"A780T617",
+  "781":"A781T622",
+  "782":"A782T623",
+  "783":"A783T625",
+  "784":"A784T626",
+  "785":"A785T629",
+  "786":"A786T630",
+  "787":"A787T631",
+  "788":"A788T635",
+  "789":"A789T638",
+  "790":"A790T568",
+  "791":"A791T571",
+  "792":"A792T570",
+  "793":"A793T569",
+  "794":"A794T567",
+  "795":"A795T581",
+  "796":"A796T605",
+  "797":"A797T523",
+  "798":"A798T836",
+  "799":"A799T837",
+  "800":"A800T838",
+  "801":"A801T839",
+  "802":"A802T840",
+  "803":"A803T841",
+  "804":"A804T842",
+  "805":"A805T843",
+  "806":"A806T844",
+  "807":"A807T845",
+  "808":"A808T846",
+  "809":"A809T847",
+  "810":"A810T848",
+  "811":"A811T849",
+  "812":"A812T850",
+  "813":"A813T851",
+  "814":"A814T852",
+  "815":"A815T853",
+  "816":"A816T854",
+  "817":"A817T855",
+  "818":"A818T856",
+  "819":"A819T857",
+  "820":"A820T858",
+  "821":"A821T859",
+  "822":"A822T860",
+  "823":"A823T861",
+  "824":"A824T862",
+  "825":"A825T863",
+  "826":"A826T864",
+  "827":"A827T865",
+  "828":"A828T866",
+  "829":"A829T867",
+  "830":"A830T868",
+  "831":"A831T869",
+  "832":"A832T870",
+  "833":"A833T871",
+  "834":"A834T872",
+  "835":"A835T873",
+  "836":"A836T874",
+  "837":"A837T875",
+  "838":"A838T876",
+  "839":"A839T877",
+  "840":"A840T878",
+  "841":"A841T879",
+  "842":"A842T880",
+  "843":"A843T881",
+  "844":"A844T882",
+  "845":"A845T883",
+  "846":"A846T885",
+  "847":"A847T886",
+  "848":"A848T887",
+  "849":"A849T888",
+  "850":"A850T889",
+  "851":"A851T890",
+  "852":"A852T891",
+  "853":"A853T892",
+  "854":"A854T894",
+  "855":"A855T895",
+  "856":"A856T896",
+  "857":"A857T897",
+  "858":"A858T898",
+  "859":"A859T899",
+  "860":"A860T900",
+  "861":"A861T901",
+  "862":"A862T902",
+  "863":"A863T903",
+  "864":"A864T904",
+  "865":"A865T905",
+  "866":"A866T906",
+  "867":"A867T907",
+  "868":"A868T908",
+  "869":"A869T909",
+  "870":"A870T910",
+  "871":"A871T911",
+  "872":"A872T912",
+  "873":"A873T913",
+  "874":"A874T914",
+  "875":"A875T915",
+  "876":"A876T916",
+  "877":"A877T917",
+  "878":"A878T918",
+  "879":"A879T919",
+  "880":"A880T920",
+  "881":"A881T921",
+  "882":"A882T922",
+  "883":"A883T923",
+  "884":"A884T924",
+  "885":"A885T925",
+  "886":"A886T927",
+  "887":"A887T928",
+  "888":"A888T929",
+  "889":"A889T930",
+  "890":"A890T931",
+  "891":"A891T932",
+  "892":"A892T933",
+  "893":"A893T935",
+  "894":"A894T937",
+  "895":"A895T938",
+  "896":"A896T939",
+  "897":"A897T940",
+  "898":"A898T941",
+  "899":"A899T942",
+  "900":"A900T943",
+  "901":"A901T944",
+  "902":"A902T945",
+  "903":"A903T946",
+  "904":"A904T947",
+  "905":"A905T948",
+  "906":"A906T949",
+  "907":"A907T950",
+  "908":"A908T951",
+  "909":"A909T952",
+  "910":"A910T953",
+  "911":"A911T954",
+  "912":"A912T955",
+  "913":"A913T956",
+  "914":"A914T958",
+  "915":"A915T957",
+  "916":"A916T959",
+  "917":"A917T961",
+  "918":"A918T962",
+  "919":"A919T963",
+  "920":"A920T964",
+  "921":"A921T965",
+  "922":"A922T966",
+  "923":"A923T967",
+  "924":"A924T968",
+  "925":"A925T969",
+  "926":"A926T970",
+  "927":"A927T971",
+  "928":"A928T972",
+  "929":"A929T973",
+  "930":"A930T974",
+  "931":"A931T975",
+  "932":"A932T976",
+  "933":"A933T977",
+  "934":"A934T978",
+  "935":"A935T979",
+  "936":"A936T980",
+  "937":"A937T981",
+  "938":"A938T982",
+  "939":"A939T983",
+  "940":"A940T984",
+  "941":"A941T985",
+  "942":"A942T986",
+  "943":"A943T987",
+  "944":"A944T988",
+  "945":"A945T990",
+  "946":"A946T991",
+  "947":"A947T992",
+  "948":"A948T993",
+  "949":"A949T994",
+  "950":"A950T995",
+  "951":"A951T996",
+  "952":"A952T997",
+  "953":"A953T999",
+  "954":"A954T1000",
+  "955":"A955T1002",
+  "956":"A956T1003",
+  "957":"A957T1004",
+  "958":"A958T1005",
+  "959":"A959T1006",
+  "960":"A960T1007",
+  "961":"A961T1008",
+  "962":"A962T1009",
+  "963":"A963T1010",
+  "964":"A964T1012",
+  "965":"A965T1011",
+  "966":"A966T1013",
+  "967":"A967T1014",
+  "968":"A968T1015",
+  "969":"A969T1016",
+  "970":"A970T1017",
+  "971":"A971T1018",
+  "972":"A972T1019",
+  "973":"A973T1020",
+  "974":"A974T1021",
+  "975":"A975T1022",
+  "976":"A976T1023",
+  "977":"A977T1024",
+  "978":"A978T1025",
+  "979":"A979T1026",
+  "980":"A980T1027",
+  "981":"A981T1028",
+  "982":"A982T1029",
+  "983":"A983T348"
+}

ragatouille-kinya-colbert/indexes/agai-colbert-10000/plan.json

@@ -0,0 +1,67 @@
+{
+    "config": {
+        "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": 32,
+        "nbits": 4,
+        "kmeans_niters": 20,
+        "resume": false,
+        "pool_factor": 1,
+        "clustering_mode": "hierarchical",
+        "protected_tokens": 0,
+        "similarity": "cosine",
+        "bsize": 64,
+        "accumsteps": 1,
+        "lr": 5e-6,
+        "maxsteps": 500000,
+        "save_every": 5941,
+        "warmup": 5941,
+        "warmup_bert": null,
+        "relu": false,
+        "nway": 2,
+        "use_ib_negatives": true,
+        "reranker": false,
+        "distillation_alpha": 1.0,
+        "ignore_scores": false,
+        "model_name": "AfroColBERT",
+        "query_maxlen": 32,
+        "attend_to_mask_tokens": false,
+        "interaction": "colbert",
+        "dim": 1024,
+        "doc_maxlen": 512,
+        "mask_punctuation": true,
+        "checkpoint": "\/mnt\/DATA\/AfroColBERT\/.ragatouille\/colbert\/none\/2025-05\/23\/11.52.12\/checkpoints\/colbert-10000\/",
+        "triples": "\/mnt\/DATA\/AfroColBERT\/data\/triples.train.colbert.jsonl",
+        "collection": [
+            "list with 984 elements starting with...",
+            [
+                "Inkoko irwaye irangwa n' ibi bikurikira : Iyo indwara yateye mu nkoko , ibigaragaza ubuzima bwazo bwiza birabura cyangwa bigahinduka . Usanga inkoko zigunze , zikonje , zisinzira , ndetse zimwe zahiniye amajosi mu mababa . Amababa n' ibirokoroko byijimye . Akenshi ntizirya cyangwa ugasanga ari imwe imwe itoratora . Hari ubwo usanga zose zihitwa ; hakaba n' ubwo zihitwa amaraso .",
+                "Uburyo indwara y' ubushita yandura mu nkoko : Ino ndwara iboneka mu nkoko zose ( into n' inkuru ) . Ni indwara mbi cyane iterwa na virusi . Inkoko zirwaye zanduza izindi . Ibikoresho byanduye nabyo bishobora kwanduza inkoko ino ndwara . Ibimenyetso by' indwara y' ubushita ( Fowl pox ) mu nkoko : Kugagara amaguru , ijosi n' amababa . Utubyimba duto kumaguru ; Igisunzu mumaso ; Kugira umuriro ; Udusebe mu kanwa no mu muhogo ; Gutakaza ibiro ( kunanuka \/ guhorota ) Kubyimba kwaho amababa atereye ; Ubuhumyi ; Guhombana kw' agatorero ; Kutarya no kutanywa ; Igabanuka ry' amagi ndetse n' impfu za hato nahato ; Ni iki wakora ngo ukumire indwara y' ubushita ( Fowl pox ) mu nkoko ; Kubera ko urukingo rw' iyi ndwara rutangwa ku mishwi ikivuka ( umunsi umwe ) ; umworozi asabwa kugura imishwi mu ituragiro ryizewe azi ko zayikingiwe ( akanahabwa icyemezo cyuko zakingiwe ) . Nta bundi buryo buhari bwo kuyirinda . Kwirinda no kuvura indwara y' Ubushita ( Fowl pox ) mu nkoko : Iyi ndwara nta muti igira . Kuyirinda ukurikiza amabwiriza yose y' isuku nicyo gisubizo cyonyine . Irinde kujya mu biraro by' inkoko bifite iyi ndwara . Mu gihe uguze izindi nkoko ugomba kuzishyira mu kato byibuze mu gihe cy' amezi 2 kugira ngo urebe niba nta burwayi zifite . Irinde imibu n' amasazi kuko bishobora kwanduza inkoko iyi ndwara .",
+                "Gukingira inkoko z' inyama ; Igihe inkoko zimaze iminsi 2 : Inkoko zikorerwa urukingo rwa Umuraramo ( New Castle ) . Igipimo cy' umuti ni New Castle HB 1 : agacupa k' inkingo 1000 bashyira muri litiro 20 z' amazi meza . Igihe inkoko zimaze iminsi 1 kugeza kuri 4 : Inkoko zihabwa Vitamine ( Anti - stress ) . Igipimo cy' umuti ni AMINOVIT : garama 1 bayivanga na litiro 1 y' amazi meza . Igihe inkoko zimaze iminsi 5 - 7 : Inkoko zikorerwa gukumira Kogusidiyoze . Igipimo cy' umuti ni VETACOX : garama 1 bayivanga na litiro 2 z' amazi meza . Igihe inkoko zimaze iminsi 7 : Inkoko zikorerwa urukingo rwa GUMBORO . Igipimo cy' umuti ni Cevac Gumbo L : agacupa k' inkingo 1000 bashyira muri litiro 20 z' amazi meza . Igihe inkoko zimaze iminsi 14 : Inkoko zikorerwa urukingo rwa Umuraramo ( New Castle ) . Igipimo cy' umuti ni Newcastle La sota : agacupa ka doze 1000 bashyira muri litiro 20 z' amazi meza . 6 . Igihe inkoko zimaze iminsi 17 - 19 : Inkoko zikorerwa gukumira Kogusidiyoze . Igipimo cy' umuti ni Amprolium : garama 1 bayivanga na litiro 1 y' amazi meza . 7 . Igihe inkoko zimaze iminsi 21 : Inkoko zikorerwa urukingo rwa GUMBORO . Igipimo cy' umuti ni Cevac Gumbo L : agacupa ka doze 1000 bashyira muri litiro 20 z' amazi meza ; Icyitonderwa : Igihe indwara igaragaye mu nkoko , umworozi agomba guhita ahamagara umuganga w' amatungo uri hafi wemewe . Ubutabazi bw' ibanze : Mu gihe ugitegereje umuganga w' amatungo nibyiza kuziha amavitamine , imyunyungugu , amazi meza n' indyo yuzuye no kuzitaho ."
+            ]
+        ],
+        "queries": "\/mnt\/DATA\/AfroColBERT\/data\/queries.train.colbert.tsv",
+        "index_name": "agai-colbert-10000",
+        "overwrite": false,
+        "root": ".ragatouille\/",
+        "experiment": "colbert",
+        "index_root": null,
+        "name": "2025-05\/23\/18.01.47",
+        "rank": 0,
+        "nranks": 2,
+        "amp": true,
+        "gpus": 2,
+        "avoid_fork_if_possible": false
+    },
+    "num_chunks": 2,
+    "num_partitions": 4096,
+    "num_embeddings_est": 192790.78857421875,
+    "avg_doclen_est": 195.92559814453125
+}