Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1536,
+  "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

@@ -3,15 +3,15 @@ language:
 - zh
 - en
 tags:
-- feature-extraction
-- sentence-similarity
 - sentence-transformers
+- sentence-similarity
+- feature-extraction
 - transformers
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
 license: apache-2.0
 ---
 
-# CodeR
-
 Here is the CodeR model trained on both text-only data and the full code data.
 
 ## Usage
@@ -35,7 +35,7 @@ documents = [
     "DELETE FROM Livestock WHERE age > 5;"
 ]
 model = FlagLLMModel('nebula2025/CodeR-full', 
-                     query_instruction_format="<instruct>{}\n<query>{}"
+                     query_instruction_format="<instruct>{}\n<query>{}",
                      query_instruction_for_retrieval="Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
                      trust_remote_code=True,
                      use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation

config.json

@@ -22,7 +22,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.49.0",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151667

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

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": 256,
+  "do_lower_case": false
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56524092f5d0676e63537511b535e73e7580a7efe440247ef3fa43d019a0af0
+size 11422261

tokenizer_config.json

@@ -202,7 +202,7 @@
   ],
   "auto_map": {
     "AutoTokenizer": [
-      "tokenization_qwen.Qwen2Tokenizer",
+      "/share_2/chaofan/models/CodeR-full--tokenization_qwen.Qwen2Tokenizer",
       null
     ]
   },
@@ -212,7 +212,7 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
+  "model_max_length": 256,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",