---
license: other
license_name: som-1.0
license_link: https://github.com/jxmorris12/vec2text/blob/master/LICENSE
library_name: vec2text
tags:
  - vec2text
  - embedding-inversion
  - clip
  - text-embedding-inversion
language:
  - en
---

# clip-text-msmarco-inversion

A **vec2text inversion (hypothesizer) model** that reconstructs text from the
embeddings produced by the **CLIP ViT-L/14 text encoder** (the text encoder used by
Stable Diffusion v1.5, identical to [`openai/clip-vit-large-patch14`](https://huggingface.co/openai/clip-vit-large-patch14)).

It is the first-stage model: given a CLIP text embedding, it produces an initial
text hypothesis. Pair it with the corrector model
[`Afrostnova/clip-text-msmarco-corrector`](https://huggingface.co/Afrostnova/clip-text-msmarco-corrector)
to iteratively refine that hypothesis.

- **Base architecture:** `vec2text` `InversionModel` (T5-based encoder–decoder)
- **Embedder:** `CLIPTextModel` — `openai/clip-vit-large-patch14`
- **Training data:** MS MARCO
- **Embedding transform:** `repeat` (`num_repeat_tokens=16`)

## ⚠️ Requirements

This is **not** loadable with the upstream `pip install vec2text` package — upstream
does not support a `CLIPTextModel` embedder. You need the fork that adds CLIP support
(the one this model was trained with). With the wrong version, `from_pretrained` fails
because the `CLIPTextModel` embedder is unknown.

## Usage

```python
import vec2text

inv = vec2text.models.InversionModel.from_pretrained("Afrostnova/clip-text-msmarco-inversion")
cor = vec2text.models.CorrectorEncoderModel.from_pretrained("Afrostnova/clip-text-msmarco-corrector")
corrector = vec2text.load_corrector(inv, cor)

# `embeddings` = CLIP text-encoder last_hidden_state, pooled at the EOS position.
text = vec2text.invert_embeddings(
    embeddings=embeddings,   # (batch, hidden_dim) on the same device as the model
    corrector=corrector,
    num_steps=20,
    sequence_beam_width=1,
)
```

The CLIP text encoder is loaded automatically when the inversion model is instantiated.
On a clean machine it is fetched from `openai/clip-vit-large-patch14`; override with the
`CLIP_TEXT_ENCODER` environment variable if you want a local copy.