Instructions to use mrfakename/ReverseBERT-EmbeddingGemma-300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrfakename/ReverseBERT-EmbeddingGemma-300M with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B-Base")
model = PeftModel.from_pretrained(base_model, "mrfakename/ReverseBERT-EmbeddingGemma-300M")

Transformers

How to use mrfakename/ReverseBERT-EmbeddingGemma-300M with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mrfakename/ReverseBERT-EmbeddingGemma-300M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mrfakename/ReverseBERT-EmbeddingGemma-300M", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mrfakename/ReverseBERT-EmbeddingGemma-300M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrfakename/ReverseBERT-EmbeddingGemma-300M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrfakename/ReverseBERT-EmbeddingGemma-300M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mrfakename/ReverseBERT-EmbeddingGemma-300M

SGLang

How to use mrfakename/ReverseBERT-EmbeddingGemma-300M with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mrfakename/ReverseBERT-EmbeddingGemma-300M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrfakename/ReverseBERT-EmbeddingGemma-300M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mrfakename/ReverseBERT-EmbeddingGemma-300M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrfakename/ReverseBERT-EmbeddingGemma-300M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mrfakename/ReverseBERT-EmbeddingGemma-300M with Docker Model Runner:
```
docker model run hf.co/mrfakename/ReverseBERT-EmbeddingGemma-300M
```

An experiment, see details: https://github.com/fakerybakery/ReverseBERT. Inspired by https://github.com/vec2text/vec2text

Overview	Details
Embedding Model	https://huggingface.co/google/embeddinggemma-300m
LLM Backbone	https://huggingface.co/Qwen/Qwen3-0.6B-Base

Overview

Can you go from embeddings back to text?

The setup is pretty simple: take a sentence encoder and freeze it. Then train a small projection layer that maps those embeddings into "soft prompt" tokens for a language model. The LLM learns to reconstruct the original text from just those projected embeddings.

It's far from perfect. You probably can't reconstruct the exact meaning of the text, but you can get the general idea/vibe of the original input.

Usage

See: https://github.com/fakerybakery/ReverseBERT/blob/main/infer.py

Reconstruction samples

Coming soon

Credits

As always, huge thanks to Hugging Face 🤗 for supporting the compute used to train this model!

Downloads last month: 3

Model tree for mrfakename/ReverseBERT-EmbeddingGemma-300M

Base model

Qwen/Qwen3-0.6B-Base

Adapter

(57)

this model

mrfakename
/

ReverseBERT-EmbeddingGemma-300M

Overview

Usage

Reconstruction samples

Credits

Model tree for mrfakename/ReverseBERT-EmbeddingGemma-300M

Dataset used to train mrfakename/ReverseBERT-EmbeddingGemma-300M