Update usage with infinity
#36
by
michaelfeil
- opened
README.md
CHANGED
|
@@ -2786,6 +2786,16 @@ print(output)
|
|
| 2786 |
For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text)
|
| 2787 |
|
| 2788 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2789 |
## Adjusting Dimensionality
|
| 2790 |
|
| 2791 |
`nomic-embed-text-v1.5` is an improvement upon [Nomic Embed](https://huggingface.co/nomic-ai/nomic-embed-text-v1) that utilizes [Matryoshka Representation Learning](https://arxiv.org/abs/2205.13147) which gives developers the flexibility to trade off the embedding size for a negligible reduction in performance.
|
|
|
|
| 2786 |
For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text)
|
| 2787 |
|
| 2788 |
|
| 2789 |
+
## Infinity
|
| 2790 |
+
|
| 2791 |
+
Usage with [Infinity](https://github.com/michaelfeil/infinity).
|
| 2792 |
+
|
| 2793 |
+
```bash
|
| 2794 |
+
docker run --gpus all -v $PWD/data:/app/.cache -e HF_TOKEN=$HF_TOKEN -p "7999":"7997" \
|
| 2795 |
+
michaelf34/infinity:0.0.70 \
|
| 2796 |
+
v2 --model-id nomic-ai/nomic-embed-text-v1.5 --revision "main" --dtype float16 --batch-size 8 --engine torch --port 7997 --no-bettertransformer
|
| 2797 |
+
```
|
| 2798 |
+
|
| 2799 |
## Adjusting Dimensionality
|
| 2800 |
|
| 2801 |
`nomic-embed-text-v1.5` is an improvement upon [Nomic Embed](https://huggingface.co/nomic-ai/nomic-embed-text-v1) that utilizes [Matryoshka Representation Learning](https://arxiv.org/abs/2205.13147) which gives developers the flexibility to trade off the embedding size for a negligible reduction in performance.
|