Discrepancy in embeddings similarity between Infinity and SentenceTransformer / HF TEI

I’ve observed significant discrepancies in the embeddings produced by **Infinity** compared to **SentenceTransformer** for the same model:
`sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`.

#### Example

When computing the cosine similarity between the embeddings of the two inputs `mountains` and `joyeux noel`:

```python
def cosine_similarity(vector1, vector2):
"""
Calculate cosine similarity between two vectors
"""
dot_product = np.dot(vector1, vector2)
magnitude1 = np.linalg.norm(vector1)
magnitude2 = np.linalg.norm(vector2)

if magnitude1 == 0 or magnitude2 == 0:
return 0

return dot_product / (magnitude1 * magnitude2)
```

* **Infinity result:** `0.497474`
* **SentenceTransformer result:** `0.354079`

The similarity score from SentenceTransformer matches what is reported in both:

* Hugging Face UI
* Hugging Face Text Embeddings Inference (TEI)

This suggests Infinity is producing different embeddings than the expected reference implementations.

### Reproduction

**Infinity (CPU):**

```bash
docker run --rm -it \
-p 8080:8080 \
michaelf34/infinity:latest-cpu \
v2 \
--engine optimum \
--port 8080 \
--model-id sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
```

**Hugging Face TEI (CPU):**

```bash
docker run -p 8081:80 -v $volume:/data --pull always \
ghcr.io/huggingface/text-embeddings-inference-cpu:1.8 \
--model-id sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
```

**SentenceTransformer code**

```python
model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
embeddings = model.encode([text1, text2])
```

Start by running the provided Infinity and Hugging Face TEI Docker commands with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2, then compare their embeddings for “mountains” and “joyeux noel” with the SentenceTransformer example. Done means Infinity produces embeddings whose cosine similarity matches the SentenceTransformer, Hugging Face UI, and TEI results.

Written by the indexing model from the issue text.