Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* 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
+db/main/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
+models/hub/models--BAAI--bge-m3/blobs/21106b6d7dab2952c1d496fb21d5dc9db75c28ed361a05f5020bbba27810dd08 filter=lfs diff=lfs merge=lfs -text
+models/hub/models--BAAI--bge-m3/blobs/993b2248881724788dcab8c644a91dfd63584b6e5604ff2037cb5541e1e38e7e filter=lfs diff=lfs merge=lfs -text
+models/hub/models--BAAI--bge-m3/blobs/cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 filter=lfs diff=lfs merge=lfs -text
+models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/tokenizer.json filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,62 @@
+import os
+import streamlit as st
+
+from embedchain import App
+
+os.environ["HF_HOME"] = "models"
+
+
+@st.cache_resource
+def embedchain_bot():
+    return App.from_config(config_path="./config_main.yaml")
+
+
+st.title("💬 Chatbot")
+st.caption("🚀 An Embedchain app created by Anurag Shukla (IRLP Lab) for DA-IICT!")
+if "messages" not in st.session_state:
+    st.session_state.messages = [
+        {
+            "role": "assistant",
+            "content": """
+        Hi! I'm a chatbot. I can answer questions and learn new things!\n
+        """,
+        }
+    ]
+
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+if prompt := st.chat_input("Ask me anything!"):
+    app = embedchain_bot()
+
+    # if prompt.startswith("/add"):
+    #     with st.chat_message("user"):
+    #         st.markdown(prompt)
+    #         st.session_state.messages.append({"role": "user", "content": prompt})
+    #     prompt = prompt.replace("/add", "").strip()
+    #     with st.chat_message("assistant"):
+    #         message_placeholder = st.empty()
+    #         message_placeholder.markdown("Adding to knowledge base...")
+    #         app.add(prompt)
+    #         message_placeholder.markdown(f"Added {prompt} to knowledge base!")
+    #         st.session_state.messages.append({"role": "assistant", "content": f"Added {prompt} to knowledge base!"})
+    #         st.stop()
+
+    with st.chat_message("user"):
+        st.markdown(prompt)
+        st.session_state.messages.append({"role": "user", "content": prompt})
+
+    with st.chat_message("assistant"):
+        msg_placeholder = st.empty()
+        msg_placeholder.markdown("Thinking...")
+
+        print("Querying the Agent.")
+        full_response = app.query(prompt.lower())
+        full_response = full_response.rpartition("Answer:")[-1].strip()
+        print(f"Answer:\n\n{full_response}")
+
+        msg_placeholder.markdown(full_response)
+        st.session_state.messages.append(
+            {"role": "assistant", "content": full_response}
+        )

config_main.yaml

@@ -0,0 +1,62 @@
+app:
+  config:
+    id: test-main
+    log_level: DEBUG
+llm:
+  provider: huggingface
+  config:
+    model: "mistralai/Mistral-7B-Instruct-v0.2"
+    top_p: 0.40
+    max_tokens: 700
+    number_documents: 10
+    temperature: 0.40
+    prompt: |
+      You are an Legal Expert who provides expert legal analysis and advice, solely based on the relevant context provided to you. Your must show professionalism, knowledge and experience of a highly respected and seasoned legal professional.
+
+      Your responses should reflect a deep and nuanced understanding of case law, statutes, regulations and legal principles across various domains. Analyze all facts objectively, identifying key issues and providing thorough legal assessments. Maintain a strategic mindset, anticipating potential challenges and proactively suggesting courses of action aligned with optimal outcomes for the client's interests.
+      
+      Craft your advice with clarity and precision, explaining complex legal concepts in a manner that is authoritative yet accessible. Tailor your communication style to be appropriate for legal contexts. However, ensure your analysis stems purely from the provided context, and does not introduce any external information or perspective AT ALL!
+      
+      You cannot refer to the context directly or quote from it. Your role is to synthesize and convey the relevant legal guidance as if it were your own deeply studied expertise. If critical details are missing from the context that inhibits a comprehensive response, then gently refuse to answer. Otherwise, provide definitive legal counsel as a leading expert you are.
+      
+      Always adhere to following points:
+        1. You may be provided with chat history of the user in your context. You answer should take this chat history into account while generating answer. The final answer should stay relevant to previous chat.
+        2. At no point you are allwed to refer anything out of context. You cannot cite laws, cases, citations and (or) quotations that are not provided in the context.
+        3. You can only use context to form your answer, you cannot refer to the context or the conversation directly. You must always act as a legal expert who is just giving advice based on the context.
+        4. If you are unable to generate answer based on the context provided them simply decline to answer. Donot try to come up with your own answer.
+        5. Banned phrases:
+          a. "based on the context/information"
+          b. "according to the context/information"
+          c. "in the conversation history"
+          d. "in the context provided"
+          e. "it appears that you"
+          f. "the context/information provided"
+          g. "as a legal expert"
+        6. Do not end your answer with suggesting user to consult legal professional as you are the legal expert they are consulting.
+
+      CONTENXT FOR THE QUERY (STRICTLY ADHERE TO IT)
+      ----------------------
+      $context
+      ----------------------
+      Query: $query
+      
+      Answer:
+
+embedder:
+  provider: huggingface
+  config:
+    model: "BAAI/bge-m3"
+
+chunker:
+  chunk_size: 2550
+  chunk_overlap: 800
+  length_function: 'len'
+  min_chunk_size: 800
+
+vectordb:
+  provider: chroma
+  config:
+    dir: db/main
+    collection_name: 'main'
+
+

db/main/bd18b971-f896-4ead-b74a-ee7e54e9d099/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1e86b236740b50ca592ed791af86ad6bfe9fddc2139423d2ca471602e9b34f
+size 16944000

db/main/bd18b971-f896-4ead-b74a-ee7e54e9d099/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348054d5f2473bf93ca781f2eeb157c15e0f65642121f5f2e6153a08bc96d14c
+size 100

db/main/bd18b971-f896-4ead-b74a-ee7e54e9d099/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e15816eefb593d15faa5c70dc102a7a1c5bd6f7186e7a668fc87b16f13b8ecd
+size 386037

db/main/bd18b971-f896-4ead-b74a-ee7e54e9d099/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112c7dbd485f478c3d18ba08895fafc4820e206e12f32d08710efff3d6d95b92
+size 16000

db/main/bd18b971-f896-4ead-b74a-ee7e54e9d099/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9472c85d1b89dfcff050dd45c171fa3d3b2b099ad6b2392da169d2fd33076905
+size 33748

db/main/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20bb0964aa6b71b7df04866b509c13ee46b9c562d236be3b68e0949567fcc5b3
+size 76857344

embedchain.json

@@ -0,0 +1,4 @@
+{
+    "name": "my-app",
+    "provider": "hf/streamlit.io"
+}

models/hub/models--BAAI--bge-m3/blobs/0140ba1eac83a3c9b857d64baba91969d988624b

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

models/hub/models--BAAI--bge-m3/blobs/1fba91c78a6c8e17227058ab6d4d3acb5d8630a9

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.0",
+    "pytorch": "2.1.2+cu121"
+  }
+}

models/hub/models--BAAI--bge-m3/blobs/21106b6d7dab2952c1d496fb21d5dc9db75c28ed361a05f5020bbba27810dd08

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21106b6d7dab2952c1d496fb21d5dc9db75c28ed361a05f5020bbba27810dd08
+size 17098108

models/hub/models--BAAI--bge-m3/blobs/4019fcbe919ffbca5bf6cc7d8f98a5fb0e34bfa4

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

models/hub/models--BAAI--bge-m3/blobs/9382959dd1bc35d31aadcad28c0129a9e6258969

@@ -0,0 +1,293 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+license: mit
+---
+
+For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding
+
+# BGE-M3 ([paper](https://arxiv.org/pdf/2402.03216.pdf), [code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3))
+
+In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. 
+- Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. 
+- Multi-Linguality: It can support more than 100 working languages. 
+- Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. 
+
+
+
+**Some suggestions for retrieval pipeline in RAG**
+
+We recommend to use the following pipeline: hybrid retrieval + re-ranking. 
+- Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. 
+A classic example: using both embedding retrieval and the BM25 algorithm. 
+Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. 
+This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings.
+To use hybrid retrieval, you can refer to [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb
+) and [Milvus](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py).
+
+- As cross-encoder models, re-ranker demonstrates higher accuracy than bi-encoder embedding model. 
+Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker), [bge-reranker-v2](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker)) after retrieval can further filter the selected text.
+
+
+## News:
+- 2024/3/20: **Thanks Milvus team!** Now you can use hybrid retrieval of bge-m3 in Milvus: [pymilvus/examples
+/hello_hybrid_sparse_dense.py](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py).
+- 2024/3/8: **Thanks for the [experimental results](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05) from @[Yannael](https://huggingface.co/Yannael). In this benchmark, BGE-M3 achieves top performance in both English and other languages, surpassing models such as OpenAI.**
+- 2024/3/2: Release unified fine-tuning [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune) and [data](https://huggingface.co/datasets/Shitao/bge-m3-data) 
+- 2024/2/6: We release the [MLDR](https://huggingface.co/datasets/Shitao/MLDR) (a long document retrieval dataset covering 13 languages) and [evaluation pipeline](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR). 
+- 2024/2/1: **Thanks for the excellent tool from Vespa.** You can easily use multiple modes of BGE-M3 following this [notebook](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb)
+
+
+## Specs
+
+- Model  
+
+| Model Name |  Dimension | Sequence Length | Introduction |
+|:----:|:---:|:---:|:---:|
+| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 | multilingual; unified fine-tuning (dense, sparse, and colbert) from bge-m3-unsupervised|
+| [BAAI/bge-m3-unsupervised](https://huggingface.co/BAAI/bge-m3-unsupervised) | 1024 | 8192 | multilingual; contrastive learning from bge-m3-retromae |
+| [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) | -- | 8192 | multilingual; extend the max_length of [xlm-roberta](https://huggingface.co/FacebookAI/xlm-roberta-large) to 8192 and further pretrained via [retromae](https://github.com/staoxiao/RetroMAE)| 
+| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | English model | 
+| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) |  768 | 512 | English model | 
+| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) |  384 | 512 | English model | 
+
+- Data
+
+|                          Dataset                           |                   Introduction                    |
+|:----------------------------------------------------------:|:-------------------------------------------------:|
+|    [MLDR](https://huggingface.co/datasets/Shitao/MLDR)     | Docuemtn Retrieval Dataset, covering 13 languages |
+| [bge-m3-data](https://huggingface.co/datasets/Shitao/bge-m3-data) |          Fine-tuning data used by bge-m3          |
+
+
+
+## FAQ
+
+**1. Introduction for different retrieval methods**
+
+- Dense retrieval: map the text into a single embedding, e.g., [DPR](https://arxiv.org/abs/2004.04906), [BGE-v1.5](https://github.com/FlagOpen/FlagEmbedding)
+- Sparse retrieval (lexical matching): a vector of size equal to the vocabulary, with the majority of positions set to zero, calculating a weight only for tokens present in the text. e.g., BM25, [unicoil](https://arxiv.org/pdf/2106.14807.pdf), and [splade](https://arxiv.org/abs/2107.05720)
+- Multi-vector retrieval: use multiple vectors to represent a text, e.g., [ColBERT](https://arxiv.org/abs/2004.12832).
+
+
+**2. How to use BGE-M3 in other projects?**
+
+For embedding retrieval, you can employ the BGE-M3 model using the same approach as BGE. 
+The only difference is that the BGE-M3 model no longer requires adding instructions to the queries. 
+
+For hybrid retrieval, you can use [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb
+) and [Milvus](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py).
+
+
+**3. How to fine-tune bge-M3 model?**
+
+You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) 
+to fine-tune the dense embedding.
+
+If you want to fine-tune all embedding function of m3 (dense, sparse and colbert), you can refer to the [unified_fine-tuning example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune)
+
+
+
+
+
+
+## Usage
+
+Install: 
+```
+git clone https://github.com/FlagOpen/FlagEmbedding.git
+cd FlagEmbedding
+pip install -e .
+```
+or: 
+```
+pip install -U FlagEmbedding
+```
+
+
+
+### Generate Embedding for text
+
+- Dense Embedding
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  
+                       use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+embeddings_1 = model.encode(sentences_1, 
+                            batch_size=12, 
+                            max_length=8192, # If you don't need such a long length, you can set a smaller value to speed up the encoding process.
+                            )['dense_vecs']
+embeddings_2 = model.encode(sentences_2)['dense_vecs']
+similarity = embeddings_1 @ embeddings_2.T
+print(similarity)
+# [[0.6265, 0.3477], [0.3499, 0.678 ]]
+```
+You also can use sentence-transformers and huggingface transformers to generate dense embeddings.
+Refer to [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding#usage) for details.
+
+
+- Sparse Embedding (Lexical Weight)
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False)
+output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False)
+
+# you can see the weight for each token:
+print(model.convert_id_to_token(output_1['lexical_weights']))
+# [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092}, 
+#  {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}]
+
+
+# compute the scores via lexical mathcing
+lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0])
+print(lexical_scores)
+# 0.19554901123046875
+
+print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1]))
+# 0.0
+```
+
+- Multi-Vector (ColBERT)
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=True)
+output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=True)
+
+print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][0]))
+print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][1]))
+# 0.7797
+# 0.4620
+```
+
+
+### Compute score for text pairs
+Input a list of text pairs, you can get the scores computed by different methods.
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+sentence_pairs = [[i,j] for i in sentences_1 for j in sentences_2]
+
+print(model.compute_score(sentence_pairs, 
+                          max_passage_length=128, # a smaller max length leads to a lower latency
+                          weights_for_different_modes=[0.4, 0.2, 0.4])) # weights_for_different_modes(w) is used to do weighted sum: w[0]*dense_score + w[1]*sparse_score + w[2]*colbert_score
+
+# {
+#   'colbert': [0.7796499729156494, 0.4621465802192688, 0.4523794651031494, 0.7898575067520142], 
+#   'sparse': [0.195556640625, 0.00879669189453125, 0.0, 0.1802978515625], 
+#   'dense': [0.6259765625, 0.347412109375, 0.349853515625, 0.67822265625], 
+#   'sparse+dense': [0.482503205537796, 0.23454029858112335, 0.2332356721162796, 0.5122477412223816], 
+#   'colbert+sparse+dense': [0.6013619303703308, 0.3255828022956848, 0.32089319825172424, 0.6232916116714478]
+# }
+```
+
+
+
+
+## Evaluation  
+
+We provide the evaluation script for [MKQA](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MKQA) and [MLDR](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR)
+
+### Benchmarks from the open-source community
+  ![avatar](./imgs/others.webp)
+ The BGE-M3 model emerged as the top performer on this benchmark (OAI is short for OpenAI). 
+  For more details, please refer to the [article](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05) and [Github Repo](https://github.com/Yannael/multilingual-embeddings)
+
+
+### Our results
+- Multilingual (Miracl dataset) 
+
+![avatar](./imgs/miracl.jpg)
+
+- Cross-lingual (MKQA dataset)
+
+![avatar](./imgs/mkqa.jpg)
+
+- Long Document Retrieval
+  - MLDR:   
+  ![avatar](./imgs/long.jpg)
+  Please note that [MLDR](https://huggingface.co/datasets/Shitao/MLDR) is a document retrieval dataset we constructed via LLM, 
+  covering 13 languages, including test set, validation set, and training set. 
+  We utilized the training set from MLDR to enhance the model's long document retrieval capabilities. 
+  Therefore, comparing baselines with `Dense w.o.long`(fine-tuning without long document dataset) is more equitable. 
+  Additionally, this long document retrieval dataset will be open-sourced to address the current lack of open-source multilingual long text retrieval datasets.
+  We believe that this data will be helpful for the open-source community in training document retrieval models.
+
+  - NarritiveQA:  
+  ![avatar](./imgs/nqa.jpg)
+
+- Comparison with BM25  
+
+We utilized Pyserini to implement BM25, and the test results can be reproduced by this [script](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR#bm25-baseline).
+We tested BM25 using two different tokenizers: 
+one using Lucene Analyzer and the other using the same tokenizer as M3 (i.e., the tokenizer of xlm-roberta). 
+The results indicate that BM25 remains a competitive baseline, 
+especially in long document retrieval.
+
+![avatar](./imgs/bm25.jpg)
+
+
+
+## Training
+- Self-knowledge Distillation: combining multiple outputs from different 
+retrieval modes as reward signal to enhance the performance of single mode(especially for sparse retrieval and multi-vec(colbert) retrival)
+- Efficient Batching: Improve the efficiency when fine-tuning on long text. 
+The small-batch strategy is simple but effective, which also can used to fine-tune large embedding model.
+- MCLS: A simple method to improve the performance on long text without fine-tuning. 
+If you have no enough resource to fine-tuning model with long text, the method is useful.
+
+Refer to our [report](https://arxiv.org/pdf/2402.03216.pdf) for more details. 
+
+
+
+
+
+
+## Acknowledgement
+
+Thanks to the authors of open-sourced datasets, including Miracl, MKQA, NarritiveQA, etc. 
+Thanks to the open-sourced libraries like [Tevatron](https://github.com/texttron/tevatron), [Pyserini](https://github.com/castorini/pyserini).
+
+
+
+## Citation
+
+If you find this repository useful, please consider giving a star :star: and citation
+
+```
+@misc{bge-m3,
+      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
+      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
+      year={2024},
+      eprint={2402.03216},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

models/hub/models--BAAI--bge-m3/blobs/952a9b81c0bfd99800fabf352f69c7ccd46c5e43

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

models/hub/models--BAAI--bge-m3/blobs/993b2248881724788dcab8c644a91dfd63584b6e5604ff2037cb5541e1e38e7e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993b2248881724788dcab8c644a91dfd63584b6e5604ff2037cb5541e1e38e7e
+size 2271064456

models/hub/models--BAAI--bge-m3/blobs/9bd85925f325e25246d94c4918dc02ab98f2a1b7

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

models/hub/models--BAAI--bge-m3/blobs/b1879d702821e753ffe4245048eee415d54a9385

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/hub/models--BAAI--bge-m3/blobs/cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

models/hub/models--BAAI--bge-m3/blobs/e6eda1c72da8f9dc30fdd9b69c73d35af3b7a7ad

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

models/hub/models--BAAI--bge-m3/refs/main

@@ -0,0 +1 @@
+5a212480c9a75bb651bcb894978ed409e4c47b82

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/README.md

@@ -0,0 +1,293 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+license: mit
+---
+
+For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding
+
+# BGE-M3 ([paper](https://arxiv.org/pdf/2402.03216.pdf), [code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3))
+
+In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. 
+- Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. 
+- Multi-Linguality: It can support more than 100 working languages. 
+- Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. 
+
+
+
+**Some suggestions for retrieval pipeline in RAG**
+
+We recommend to use the following pipeline: hybrid retrieval + re-ranking. 
+- Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. 
+A classic example: using both embedding retrieval and the BM25 algorithm. 
+Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. 
+This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings.
+To use hybrid retrieval, you can refer to [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb
+) and [Milvus](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py).
+
+- As cross-encoder models, re-ranker demonstrates higher accuracy than bi-encoder embedding model. 
+Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker), [bge-reranker-v2](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker)) after retrieval can further filter the selected text.
+
+
+## News:
+- 2024/3/20: **Thanks Milvus team!** Now you can use hybrid retrieval of bge-m3 in Milvus: [pymilvus/examples
+/hello_hybrid_sparse_dense.py](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py).
+- 2024/3/8: **Thanks for the [experimental results](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05) from @[Yannael](https://huggingface.co/Yannael). In this benchmark, BGE-M3 achieves top performance in both English and other languages, surpassing models such as OpenAI.**
+- 2024/3/2: Release unified fine-tuning [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune) and [data](https://huggingface.co/datasets/Shitao/bge-m3-data) 
+- 2024/2/6: We release the [MLDR](https://huggingface.co/datasets/Shitao/MLDR) (a long document retrieval dataset covering 13 languages) and [evaluation pipeline](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR). 
+- 2024/2/1: **Thanks for the excellent tool from Vespa.** You can easily use multiple modes of BGE-M3 following this [notebook](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb)
+
+
+## Specs
+
+- Model  
+
+| Model Name |  Dimension | Sequence Length | Introduction |
+|:----:|:---:|:---:|:---:|
+| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 | multilingual; unified fine-tuning (dense, sparse, and colbert) from bge-m3-unsupervised|
+| [BAAI/bge-m3-unsupervised](https://huggingface.co/BAAI/bge-m3-unsupervised) | 1024 | 8192 | multilingual; contrastive learning from bge-m3-retromae |
+| [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) | -- | 8192 | multilingual; extend the max_length of [xlm-roberta](https://huggingface.co/FacebookAI/xlm-roberta-large) to 8192 and further pretrained via [retromae](https://github.com/staoxiao/RetroMAE)| 
+| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | English model | 
+| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) |  768 | 512 | English model | 
+| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) |  384 | 512 | English model | 
+
+- Data
+
+|                          Dataset                           |                   Introduction                    |
+|:----------------------------------------------------------:|:-------------------------------------------------:|
+|    [MLDR](https://huggingface.co/datasets/Shitao/MLDR)     | Docuemtn Retrieval Dataset, covering 13 languages |
+| [bge-m3-data](https://huggingface.co/datasets/Shitao/bge-m3-data) |          Fine-tuning data used by bge-m3          |
+
+
+
+## FAQ
+
+**1. Introduction for different retrieval methods**
+
+- Dense retrieval: map the text into a single embedding, e.g., [DPR](https://arxiv.org/abs/2004.04906), [BGE-v1.5](https://github.com/FlagOpen/FlagEmbedding)
+- Sparse retrieval (lexical matching): a vector of size equal to the vocabulary, with the majority of positions set to zero, calculating a weight only for tokens present in the text. e.g., BM25, [unicoil](https://arxiv.org/pdf/2106.14807.pdf), and [splade](https://arxiv.org/abs/2107.05720)
+- Multi-vector retrieval: use multiple vectors to represent a text, e.g., [ColBERT](https://arxiv.org/abs/2004.12832).
+
+
+**2. How to use BGE-M3 in other projects?**
+
+For embedding retrieval, you can employ the BGE-M3 model using the same approach as BGE. 
+The only difference is that the BGE-M3 model no longer requires adding instructions to the queries. 
+
+For hybrid retrieval, you can use [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb
+) and [Milvus](https://github.com/milvus-io/pymilvus/blob/master/examples/hello_hybrid_sparse_dense.py).
+
+
+**3. How to fine-tune bge-M3 model?**
+
+You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) 
+to fine-tune the dense embedding.
+
+If you want to fine-tune all embedding function of m3 (dense, sparse and colbert), you can refer to the [unified_fine-tuning example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune)
+
+
+
+
+
+
+## Usage
+
+Install: 
+```
+git clone https://github.com/FlagOpen/FlagEmbedding.git
+cd FlagEmbedding
+pip install -e .
+```
+or: 
+```
+pip install -U FlagEmbedding
+```
+
+
+
+### Generate Embedding for text
+
+- Dense Embedding
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  
+                       use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+embeddings_1 = model.encode(sentences_1, 
+                            batch_size=12, 
+                            max_length=8192, # If you don't need such a long length, you can set a smaller value to speed up the encoding process.
+                            )['dense_vecs']
+embeddings_2 = model.encode(sentences_2)['dense_vecs']
+similarity = embeddings_1 @ embeddings_2.T
+print(similarity)
+# [[0.6265, 0.3477], [0.3499, 0.678 ]]
+```
+You also can use sentence-transformers and huggingface transformers to generate dense embeddings.
+Refer to [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding#usage) for details.
+
+
+- Sparse Embedding (Lexical Weight)
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False)
+output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False)
+
+# you can see the weight for each token:
+print(model.convert_id_to_token(output_1['lexical_weights']))
+# [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092}, 
+#  {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}]
+
+
+# compute the scores via lexical mathcing
+lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0])
+print(lexical_scores)
+# 0.19554901123046875
+
+print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1]))
+# 0.0
+```
+
+- Multi-Vector (ColBERT)
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=True)
+output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=True)
+
+print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][0]))
+print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][1]))
+# 0.7797
+# 0.4620
+```
+
+
+### Compute score for text pairs
+Input a list of text pairs, you can get the scores computed by different methods.
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+sentence_pairs = [[i,j] for i in sentences_1 for j in sentences_2]
+
+print(model.compute_score(sentence_pairs, 
+                          max_passage_length=128, # a smaller max length leads to a lower latency
+                          weights_for_different_modes=[0.4, 0.2, 0.4])) # weights_for_different_modes(w) is used to do weighted sum: w[0]*dense_score + w[1]*sparse_score + w[2]*colbert_score
+
+# {
+#   'colbert': [0.7796499729156494, 0.4621465802192688, 0.4523794651031494, 0.7898575067520142], 
+#   'sparse': [0.195556640625, 0.00879669189453125, 0.0, 0.1802978515625], 
+#   'dense': [0.6259765625, 0.347412109375, 0.349853515625, 0.67822265625], 
+#   'sparse+dense': [0.482503205537796, 0.23454029858112335, 0.2332356721162796, 0.5122477412223816], 
+#   'colbert+sparse+dense': [0.6013619303703308, 0.3255828022956848, 0.32089319825172424, 0.6232916116714478]
+# }
+```
+
+
+
+
+## Evaluation  
+
+We provide the evaluation script for [MKQA](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MKQA) and [MLDR](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR)
+
+### Benchmarks from the open-source community
+  ![avatar](./imgs/others.webp)
+ The BGE-M3 model emerged as the top performer on this benchmark (OAI is short for OpenAI). 
+  For more details, please refer to the [article](https://towardsdatascience.com/openai-vs-open-source-multilingual-embedding-models-e5ccb7c90f05) and [Github Repo](https://github.com/Yannael/multilingual-embeddings)
+
+
+### Our results
+- Multilingual (Miracl dataset) 
+
+![avatar](./imgs/miracl.jpg)
+
+- Cross-lingual (MKQA dataset)
+
+![avatar](./imgs/mkqa.jpg)
+
+- Long Document Retrieval
+  - MLDR:   
+  ![avatar](./imgs/long.jpg)
+  Please note that [MLDR](https://huggingface.co/datasets/Shitao/MLDR) is a document retrieval dataset we constructed via LLM, 
+  covering 13 languages, including test set, validation set, and training set. 
+  We utilized the training set from MLDR to enhance the model's long document retrieval capabilities. 
+  Therefore, comparing baselines with `Dense w.o.long`(fine-tuning without long document dataset) is more equitable. 
+  Additionally, this long document retrieval dataset will be open-sourced to address the current lack of open-source multilingual long text retrieval datasets.
+  We believe that this data will be helpful for the open-source community in training document retrieval models.
+
+  - NarritiveQA:  
+  ![avatar](./imgs/nqa.jpg)
+
+- Comparison with BM25  
+
+We utilized Pyserini to implement BM25, and the test results can be reproduced by this [script](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR#bm25-baseline).
+We tested BM25 using two different tokenizers: 
+one using Lucene Analyzer and the other using the same tokenizer as M3 (i.e., the tokenizer of xlm-roberta). 
+The results indicate that BM25 remains a competitive baseline, 
+especially in long document retrieval.
+
+![avatar](./imgs/bm25.jpg)
+
+
+
+## Training
+- Self-knowledge Distillation: combining multiple outputs from different 
+retrieval modes as reward signal to enhance the performance of single mode(especially for sparse retrieval and multi-vec(colbert) retrival)
+- Efficient Batching: Improve the efficiency when fine-tuning on long text. 
+The small-batch strategy is simple but effective, which also can used to fine-tune large embedding model.
+- MCLS: A simple method to improve the performance on long text without fine-tuning. 
+If you have no enough resource to fine-tuning model with long text, the method is useful.
+
+Refer to our [report](https://arxiv.org/pdf/2402.03216.pdf) for more details. 
+
+
+
+
+
+
+## Acknowledgement
+
+Thanks to the authors of open-sourced datasets, including Miracl, MKQA, NarritiveQA, etc. 
+Thanks to the open-sourced libraries like [Tevatron](https://github.com/texttron/tevatron), [Pyserini](https://github.com/castorini/pyserini).
+
+
+
+## Citation
+
+If you find this repository useful, please consider giving a star :star: and citation
+
+```
+@misc{bge-m3,
+      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
+      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
+      year={2024},
+      eprint={2402.03216},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "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,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.33.0",
+    "pytorch": "2.1.2+cu121"
+  }
+}

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993b2248881724788dcab8c644a91dfd63584b6e5604ff2037cb5541e1e38e7e
+size 2271064456

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21106b6d7dab2952c1d496fb21d5dc9db75c28ed361a05f5020bbba27810dd08
+size 17098108

models/hub/models--BAAI--bge-m3/snapshots/5a212480c9a75bb651bcb894978ed409e4c47b82/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

models/hub/version.txt

@@ -0,0 +1 @@
+1

requirements.txt

@@ -0,0 +1,2 @@
+streamlit==1.29.0
+embedchain