Periodic checkpoint at step 250 (loss=0.00004)

backbone/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": 1026,
+  "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
+}

backbone/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebd5cd7e91212156f229c391f3af18779720266fa9592a5366e9b24a49aea13
+size 503741296

backbone/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

code_embed_config.json

@@ -0,0 +1,9 @@
+{
+  "base_model_name_or_path": "microsoft/unixcoder-base",
+  "backbone_hidden_size": 768,
+  "embedding_dim": 1536,
+  "projection_hidden_dim": 1536,
+  "pooling": "mean",
+  "max_seq_length": 1024,
+  "dropout": 0.1
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fa8042d2e60c4db760026c1da0e01df46faf5b99a463c05ce14a59f400c3dd
+size 1031217338

projection_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863d5a7185dd4c86f0e5ee6f440a2e4f12400cc0001cec8b079004ceb0135bdb
+size 14170320

pycode_embed_config.json

@@ -0,0 +1,9 @@
+{
+  "base_model_name_or_path": "microsoft/unixcoder-base",
+  "backbone_hidden_size": 768,
+  "embedding_dim": 1536,
+  "projection_hidden_dim": 1536,
+  "pooling": "mean",
+  "max_seq_length": 1024,
+  "dropout": 0.1
+}

rng_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b4928cd7ee30852ac66cf551b18d9e59d60c45fc21cf2ddf3c36d50e2e1f5f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a42ac0ebdafd07ca4427102b72c87fd07dfa02a1a4517c07497b9f3e334935
+size 1064

sentence_transformers/1_Pooling/config.json

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

sentence_transformers/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"
+}

sentence_transformers/2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5a673cc4a68ee6d87cc8bd0d78abba471d3d1095848596824db7f01a83ef94
+size 4724896

sentence_transformers/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"
+}

sentence_transformers/3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9fa7beca52eaa2963fd237551acd314232b1b30383e481d960d05750734c8d3
+size 9443488

sentence_transformers/4_Normalize/config.json

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

sentence_transformers/README.md

@@ -0,0 +1,154 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+base_model: microsoft/unixcoder-base
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on microsoft/unixcoder-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/unixcoder-base](https://huggingface.co/microsoft/unixcoder-base). It maps inputs to a 1536-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [microsoft/unixcoder-base](https://huggingface.co/microsoft/unixcoder-base) <!-- at revision 5604afdc964f6c53782a6813140ade5216b99006 -->
+- **Maximum Sequence Length:** 1024 tokens
+- **Output Dimensionality:** 1536 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Supported Modality:** Text
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'RobertaModel'})
+  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
+  (2): Dense({'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'})
+  (3): Dense({'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'})
+  (4): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1536]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.4488, 0.3237],
+#         [0.4488, 1.0000, 0.3997],
+#         [0.3237, 0.3997, 1.0000]])
+```
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.11.10
+- Sentence Transformers: 6.1.0
+- Transformers: 5.20.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.15.0
+- Datasets: 5.1.0
+- Tokenizers: 0.23.3
+
+## Additional Resources
+
+- [Training and Finetuning Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sentence-transformers): the end-to-end guide for training or finetuning Sentence Transformer models.
+- [Introduction to Matryoshka Embedding Models](https://huggingface.co/blog/matryoshka): variable-size embeddings that can be truncated with minimal quality loss.
+- [Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval](https://huggingface.co/blog/embedding-quantization): post-training compression of embedding vectors.
+- [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video models through the same API.
+- [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): train multimodal embedding models, with a Visual Document Retrieval walkthrough.
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

sentence_transformers/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": 1026,
+  "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
+}

sentence_transformers/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.6.0+cu124",
+    "sentence_transformers": "6.1.0",
+    "transformers": "5.20.1"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "cosine"
+}

sentence_transformers/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebd5cd7e91212156f229c391f3af18779720266fa9592a5366e9b24a49aea13
+size 503741296

sentence_transformers/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_transformers/sentence_bert_config.json

@@ -0,0 +1,11 @@
+{
+  "transformer_task": "feature-extraction",
+  "modality_config": {
+    "text": {
+      "method": "forward",
+      "method_output_name": "last_hidden_state"
+    }
+  },
+  "module_output_name": "token_embeddings",
+  "max_seq_length": 1024
+}

sentence_transformers/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,9 @@
+{
+  "global_step": 250,
+  "current_epoch": 0,
+  "total_training_steps": 6314,
+  "learning_rate": 1.1885895404120445e-05,
+  "scheduler_name": "cosine",
+  "fp16": false,
+  "bf16": true
+}