Update README; modeling_gemma2.py; overwrite

README.md

@@ -1,5 +1,11 @@
 ---
 license: cc-by-nc-4.0
+pipeline_tag: feature-extraction
+tags:
+- transformers
+- sentence-transformers
+- code
+- retrieval
 ---
 <h1 align="center">Salesforce/SFR-Embedding-Code-2B_R</h1>
 
@@ -12,7 +18,7 @@ Check out our [paper](https://arxiv.org/abs/2411.12644) for more details!
 We also offer 400M-size model [Salesforce/SFR-Embedding-Code-400_R](https://huggingface.co/Salesforce/SFR-Embedding-Code-400M_R)
 
 ### Ethical Considerations
-This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our [AUP](https://www.salesforce.com/content/dam/web/en_us/www/documents/legal/Agreements/policies/ExternalFacing_Services_Policy.pdf) and [AI AUP](https://www.salesforce.com/content/dam/web/en_us/www/documents/legal/Agreements/policies/ai-acceptable-use-policy.pdf).
+This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact peopleÔÇÖs lives, rights, or safety. For further guidance on use cases, refer to our [AUP](https://www.salesforce.com/content/dam/web/en_us/www/documents/legal/Agreements/policies/ExternalFacing_Services_Policy.pdf) and [AI AUP](https://www.salesforce.com/content/dam/web/en_us/www/documents/legal/Agreements/policies/ai-acceptable-use-policy.pdf).
 
 ### License Statement:
 Users need to make their own assessment regarding any obligations or responsibilities under the corresponding licenses or terms and conditions pertaining to the original datasets and data. This release is for research purposes only in support of an academic paper.
@@ -32,14 +38,14 @@ This released model is a fine-tuned version of Gemma and Gemma is provided under
 | CodeSage-Small        | 130M       | 54.4               |
 
 
-SFR-Embedding Team († indicates co-leaders)
+SFR-Embedding Team (ÔÇá indicates co-leaders)
 * Ye Liu
 * Rui Meng
 * Shafiq Rayhan Joty
 * Silvio Savarese
-* Caiming Xiong †
-* Yingbo Zhou †
-* Semih Yavuz †
+* Caiming Xiong ÔÇá
+* Yingbo Zhou ÔÇá
+* Semih Yavuz ÔÇá
 
 ## How to run
 
@@ -52,7 +58,7 @@ from transformers import AutoTokenizer, AutoModel
 query_instruction_example = "Given Code or Text, retrieval relevant content"
 queries = [
     "how to implement quick sort in Python?"
-    ]
+]
 
 # No instruction needed for retrieval passages
 passages = [
@@ -74,6 +80,35 @@ passage_embeddings = F.normalize(passage_embeddings, p=2, dim=1)
 
 scores = (query_embeddings @ passage_embeddings.T) * 100
 print(scores.tolist())
+# [[52.76957702636719, 26.118698120117188]]
+```
+
+#### Sentence Transformers
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Each query needs to be accompanied by an corresponding instruction describing the task.
+query_instruction_example = "Instruct: Given Code or Text, retrieval relevant content\nQuery: "
+queries = ["how to implement quick sort in Python?"]
+
+# No instruction needed for retrieval passages
+passages = [
+    "def quick_sort(arr):\n    if len(arr) <= 1:\n        return arr\n    pivot = arr[len(arr) // 2]\n    left = [x for x in arr if x < pivot]\n    middle = [x for x in arr if x == pivot]\n    right = [x for x in arr if x > pivot]\n    return quick_sort(left) + middle + quick_sort(right)",
+    "def bubble_sort(arr):\n    n = len(arr)\n    for i in range(n):\n        for j in range(0, n-i-1):\n            if arr[j] > arr[j+1]:\n                arr[j], arr[j+1] = arr[j+1], arr[j]\n    return arr"
+]
+
+# Load the Sentence Transformer model, including pooling
+model = SentenceTransformer('Salesforce/SFR-Embedding-Code-2B_R', trust_remote_code=True)
+
+# Compute the embeddings for both queries and passages. Use 'prompt' for queries only
+query_embeddings = model.encode(queries, prompt=query_instruction_example)
+passage_embeddings = model.encode(passages)
+
+# Compute the similarities between the queries and passages
+similarities = model.similarity(query_embeddings, passage_embeddings)
+print(similarities)
+# tensor([[0.5277, 0.2612]])
 ```
 
 ### Citation

modeling_gemma2.py

@@ -1350,6 +1350,9 @@ class CodeXEmbedModel2B(PreTrainedModel):
             self.tokenizer.pad_token = self.tokenizer.eos_token
         self.tokenizer.padding_side = 'right'
 
+    def forward(self, **kwargs):
+        return self.model(**kwargs)
+
     def last_token_pool(self, model_output, attention_mask):
         last_hidden_states = model_output.last_hidden_state
         sequence_lengths = attention_mask.sum(dim=1) - 1