Simplify usage; integrate Sentence Transformers (+ LlamaIndex/LangChain, etc.) (#39)

- Add "add_eos_token" to tokenizer config; simplify usage (a5e1612ae784f73eba634b00acf64db7d99ad7e9)
- Integrate with Sentence Transformers + 3rd parties (90cddb89718db232ed6257f69b36e9e601120883)
- Reduce sentence-transformers version to prevent "Upgrade your ST" warning (84b20972705a9d8c825bdf39a81acac66a10d701)

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 4096,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - mteb
+- sentence-transformers
+- transformers
 model-index:
 - name: e5-mistral-7b-instruct
   results:
@@ -6851,6 +6853,36 @@ This model has 32 layers and the embedding size is 4096.
 
 Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
 
+### Sentence Transformers
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("intfloat/e5-mistral-7b-instruct")
+# In case you want to reduce the maximum sequence length:
+model.max_seq_length = 4096
+
+queries = [
+    "how much protein should a female eat",
+    "summit define",
+]
+documents = [
+    "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
+    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
+]
+
+query_embeddings = model.encode(queries, prompt_name="web_search_query")
+document_embeddings = model.encode(documents)
+
+scores = (query_embeddings @ document_embeddings.T) * 100
+print(scores.tolist())
+```
+
+Have a look at [config_sentence_transformers.json](config_sentence_transformers.json) for the prompts that are pre-configured, such as `web_search_query`, `sts_query`, and `summarization_query`. Additionally, check out [unilm/e5/utils.py](https://github.com/microsoft/unilm/blob/9c0f1ff7ca53431fe47d2637dfe253643d94185b/e5/utils.py#L106) for prompts we used for evaluation. You can use these via e.g. `model.encode(queries, prompt="Instruct: Given a claim, find documents that refute the claim\nQuery: ")`.
+
+
+### Transformers
+
 ```python
 import torch
 import torch.nn.functional as F
@@ -6892,10 +6924,7 @@ model = AutoModel.from_pretrained('intfloat/e5-mistral-7b-instruct')
 
 max_length = 4096
 # Tokenize the input texts
-batch_dict = tokenizer(input_texts, max_length=max_length - 1, return_attention_mask=False, padding=False, truncation=True)
-# append eos_token_id to every input_ids
-batch_dict['input_ids'] = [input_ids + [tokenizer.eos_token_id] for input_ids in batch_dict['input_ids']]
-batch_dict = tokenizer.pad(batch_dict, padding=True, return_attention_mask=True, return_tensors='pt')
+batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt')
 
 outputs = model(**batch_dict)
 embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.39.3",
+    "pytorch": "2.1.0+cu121"
+  },
+  "prompts": {
+    "web_search_query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: ",
+    "sts_query": "Instruct: Retrieve semantically similar text.\nQuery: ",
+    "summarization_query": "Instruct: Given a news summary, retrieve other semantically similar summaries\nQuery: ",
+    "bitext_query": "Instruct: Retrieve parallel sentences.\nQuery: "
+  },
+  "default_prompt_name": null
+}

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32768,
+  "do_lower_case": false
+}

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_eos_token": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",