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
+model.neuron filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,32 @@
 ---
 license: apache-2.0
 ---
+
+This model is compiled for neuronx devices (eg. on inf2 instance).
+
+This original checkpoint is [`BAAI/bge-base-en-v1.5`](https://huggingface.co/BAAI/bge-base-en-v1.5).
+
+## Export
+
+Here below is the command used for exporting this model:
+
+```bash
+optimum-cli export neuron -m BAAI/bge-base-en-v1.5 --sequence_length 384 --batch_size 1 --task feature-extraction bge_emb/
+```
+
+## Usage
+
+To use the compiled artifacts for inference, here is an example:
+
+```python
+from transformers import AutoTokenizer
+from optimum.neuron import NeuronModelForSenetenceTransformers
+
+emb_model = NeuronModelForSenetenceTransformers.from_pretrained("optimum/bge-base-en-v1.5-neuronx")
+inputs = tokenizer("Hamilton is considered to be the best musical of human history.", return_tensors="pt")
+emb = emb_model(**inputs)
+
+print(emb.keys())
+
+# ["token_embeddings", "sentence_embedding"]
+```

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/torch/sentence_transformers/BAAI_bge-base-en-v1.5/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "neuron": {
+    "auto_cast": null,
+    "auto_cast_type": null,
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.54.0+f631c2365",
+    "dynamic_batch_size": false,
+    "input_names": [
+      "input_ids",
+      "attention_mask"
+    ],
+    "model_type": "sentence-transformers-transformer",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "token_embeddings",
+      "sentence_embedding"
+    ],
+    "static_batch_size": 1,
+    "static_num_beams": 1,
+    "static_sequence_length": 384
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task": "feature-extraction",
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20055c325eb2c4e990664218588f0674937ac7cf7ada42652460f00f32d8c013
+size 272398850

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}