Instructions to use FractalGPT/EmbedderDecoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FractalGPT/EmbedderDecoder with Transformers:

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

pipe = pipeline("text-generation", model="FractalGPT/EmbedderDecoder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FractalGPT/EmbedderDecoder")
model = AutoModelForCausalLM.from_pretrained("FractalGPT/EmbedderDecoder")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FractalGPT/EmbedderDecoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FractalGPT/EmbedderDecoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FractalGPT/EmbedderDecoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FractalGPT/EmbedderDecoder

SGLang

How to use FractalGPT/EmbedderDecoder 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 "FractalGPT/EmbedderDecoder" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FractalGPT/EmbedderDecoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "FractalGPT/EmbedderDecoder" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FractalGPT/EmbedderDecoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FractalGPT/EmbedderDecoder with Docker Model Runner:
```
docker model run hf.co/FractalGPT/EmbedderDecoder
```

Ponimash commited on Feb 14, 2024

Commit

b46980a

verified ·

1 Parent(s): 4105808

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -0

README.md CHANGED Viewed

@@ -154,4 +154,23 @@ generator.generate_with_ranker(embd, seq=5)
 ```
 ```bash
 >>> фильм был снят по мотивам произведений
 ```

 ```
 ```bash
 >>> фильм был снят по мотивам произведений
+```
+```python
+embd = sbert.encode('полицейский - главный герой') + sbert.encode('Произошло ужасное событие в фильме')
+embd /= 2
+generator.generate_with_ranker(embd, 'Собеседование на')
+```
+```bash
+>>> Собеседование на роль главного героя фильма — молодого лейтенанта полиции — происходит в доме
+```
+```python
+embd = sbert.encode('машина') - sbert.encode('колеса') + sbert.encode('крылья')
+generator.generate_with_ranker(embd, 'это')
+```
+```bash
+>>> этот самолет
 ```