Upload CodeEmbed model weights and configuration

1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 768,
+    "pooling_mode": "cls",
+    "include_prompt": true
+}

2_Dense/config.json

@@ -0,0 +1,8 @@
+{
+    "in_features": 768,
+    "out_features": 1536,
+    "bias": true,
+    "activation_function": "torch.nn.modules.activation.GELU",
+    "module_input_name": "sentence_embedding",
+    "module_output_name": "sentence_embedding"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4d6d258634c33ffb49baca0ff9bd1b2a7239072ab083c6f4d94b24a10c5e3a
+size 4724896

3_Dense/config.json

@@ -0,0 +1,8 @@
+{
+    "in_features": 1536,
+    "out_features": 1536,
+    "bias": true,
+    "activation_function": "torch.nn.modules.linear.Identity",
+    "module_input_name": "sentence_embedding",
+    "module_output_name": "sentence_embedding"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e1cb8d74d64879696ce7a8154c615b7e6a953e36f020c5d57bfd7a153b79b4
+size 9443488

4_Normalize/config.json

@@ -0,0 +1,4 @@
+{
+    "module_input_name": "sentence_embedding",
+    "module_output_name": "sentence_embedding"
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.20.1",
+  "type_vocab_size": 10,
+  "use_cache": true,
+  "vocab_size": 51416
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.14.1",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.20.1"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d013b306ee92fa36c45c0ced65e3b41742c9c14855ee2c1d9cae08bf0c3029e5
+size 525761392

modules.json

@@ -0,0 +1,32 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.base.modules.dense.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.base.modules.dense.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.base.modules.normalize.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 8192,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": {
     "strategy": "BatchLongest",
     "direction": "Right",

tokenizer_config.json

@@ -5,13 +5,20 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
-  "is_local": false,
+  "is_local": true,
   "local_files_only": false,
   "mask_token": "<mask>",
+  "max_length": 8192,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }