Instructions to use dkalpakchi/SweCTRL-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dkalpakchi/SweCTRL-Mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dkalpakchi/SweCTRL-Mini")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dkalpakchi/SweCTRL-Mini") model = AutoModelForCausalLM.from_pretrained("dkalpakchi/SweCTRL-Mini", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dkalpakchi/SweCTRL-Mini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dkalpakchi/SweCTRL-Mini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dkalpakchi/SweCTRL-Mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dkalpakchi/SweCTRL-Mini
- SGLang
How to use dkalpakchi/SweCTRL-Mini 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 "dkalpakchi/SweCTRL-Mini" \ --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": "dkalpakchi/SweCTRL-Mini", "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 "dkalpakchi/SweCTRL-Mini" \ --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": "dkalpakchi/SweCTRL-Mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dkalpakchi/SweCTRL-Mini with Docker Model Runner:
docker model run hf.co/dkalpakchi/SweCTRL-Mini
Commit ·
3a9c601
1
Parent(s): c9a0e19
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,12 @@ SweCTRL-Mini is a large Swedish language model that can be used for inference an
|
|
| 35 |
- **NOT** trained for conversations, like ChatGPT
|
| 36 |
- **NOT** trained on any multi-modal data during training. Only one modality -- text, more than 99% of it in Swedish.
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
## Model Details
|
| 39 |
|
| 40 |
### Model Description
|
|
|
|
| 35 |
- **NOT** trained for conversations, like ChatGPT
|
| 36 |
- **NOT** trained on any multi-modal data during training. Only one modality -- text, more than 99% of it in Swedish.
|
| 37 |
|
| 38 |
+
**Note on using Inference API (text box to the right):** There are a number of presets that start the text with appropriate control codes to control the genre, e.g., `:wiki:` for
|
| 39 |
+
texts form Wikipedia. You can add your own prompt on top of these control codes. For instance, if you want a Wikipedia article about Stockholm, you could write
|
| 40 |
+
`:wiki: Stockholm`. The generation in the example is limited to 75 new tokens max. Also, normally the generation should stop after reaching the ending control code,
|
| 41 |
+
which has `$` symbol at the end, e.g., `:wiki:$` for Wikipedia texts, however I couldn't configure that here, so please ignore all text after such tokens if they were to be
|
| 42 |
+
generated.
|
| 43 |
+
|
| 44 |
## Model Details
|
| 45 |
|
| 46 |
### Model Description
|