README.md

---
license: apache-2.0
base_model:
- nomic-ai/nomic-embed-text-v1.5
pipeline_tag: sentence-similarity
---
# Nomic Embed Text V1 (ONNX)

**Tags:** `text-embedding` `onnx` `nomic-embed-text` `sentence-transformers`

---

## Model Details

- **Model Name:** Nomic Embed Text V1 (ONNX export)  
- **Original HF Repo:** [nomic-ai/nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1)  
- **ONNX File:** `model.onnx`  
- **Export Date:** 2025-05-27  

This model outputs:
1. **token_embeddings** — per‐token embedding vectors (`[batch_size, seq_len, hidden_size]`)  
2. **sentence_embedding** — pooled sentence‐level embeddings (`[batch_size, hidden_size]`)  

---

## Model Description

Nomic Embed Text V1 is a BERT‐style encoder trained to generate high-quality dense representations of text. It is suitable for:

- Semantic search  
- Text clustering  
- Recommendation systems  
- Downstream classification  

The ONNX export ensures compatibility with inference engines like [ONNX Runtime](https://www.onnxruntime.ai/) and NVIDIA Triton Inference Server.

---

## Usage

### 1. Install Dependencies

```bash
pip install onnxruntime transformers numpy
```

### 2. Install Dependencies

```python
import onnxruntime as ort

session = ort.InferenceSession("model.onnx")
```

### 3. Tokenize Inputs

```python
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("nomic-ai/nomic-embed-text-v1")
inputs = tokenizer(
    ["Hello world", "Another sentence"],
    padding=True,
    truncation=True,
    return_tensors="np"
)
```

### 4. Run Inference

```python
outputs = session.run(
    ["token_embeddings", "sentence_embedding"],
    {
        "input_ids": inputs["input_ids"],
        "attention_mask": inputs["attention_mask"]
    }
)

token_embeddings, sentence_embeddings = outputs
```

## Serving with Triton

Place your model files under:

models/
└── nomic_embeddings/
    └── 1/
        ├── model.onnx
        ├── config.pbtxt
        └── (tokenizer files…)


Create a config.pbtxt file that looks something like this:

```protobuf
name: "nomic_embeddings"
backend: "onnxruntime"
max_batch_size: 8

input [
  {
    name: "input_ids"
    data_type: TYPE_INT32
    dims: [-1]
  },
  {
    name: "attention_mask"
    data_type: TYPE_INT32
    dims: [-1]
  }
]

output [
  {
    name: "token_embeddings"
    data_type: TYPE_FP32
    dims: [-1, 768]
  },
  {
    name: "sentence_embedding"
    data_type: TYPE_FP32
    dims: [-1, 768]
  }
]

instance_group [
  {
    kind: KIND_GPU
    count: 1
  }
]
```

Start Triton:

```bash
tritonserver \
  --model-repository=/path/to/models \
  --model-control-mode=explicit \
  --load-model=nomic_embeddings
```