Text Generation
Transformers
Safetensors
Czech
gpt2
czech
chat
steganography
small-language-model
encrypt.click
text-generation-inference
Instructions to use danielsebesta/kecal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use danielsebesta/kecal with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="danielsebesta/kecal")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("danielsebesta/kecal") model = AutoModelForCausalLM.from_pretrained("danielsebesta/kecal", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use danielsebesta/kecal with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "danielsebesta/kecal" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "danielsebesta/kecal", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/danielsebesta/kecal
- SGLang
How to use danielsebesta/kecal 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 "danielsebesta/kecal" \ --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": "danielsebesta/kecal", "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 "danielsebesta/kecal" \ --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": "danielsebesta/kecal", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use danielsebesta/kecal with Docker Model Runner:
docker model run hf.co/danielsebesta/kecal
README: clearer sample without mid-thought drift
Browse files
README.md
CHANGED
|
@@ -24,15 +24,15 @@ A small language model that writes casual Czech chat messages: one person sendin
|
|
| 24 |
Kecal was made for the **Chat cipher** on [encrypt.click](https://encrypt.click), where it turns encrypted data into ordinary looking chat messages and back. It is a tool for that job, not a chatbot or an assistant.
|
| 25 |
|
| 26 |
```
|
| 27 |
-
to je
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
```
|
| 37 |
|
| 38 |
## Model
|
|
|
|
| 24 |
Kecal was made for the **Chat cipher** on [encrypt.click](https://encrypt.click), where it turns encrypted data into ordinary looking chat messages and back. It is a tool for that job, not a chatbot or an assistant.
|
| 25 |
|
| 26 |
```
|
| 27 |
+
to je pravda
|
| 28 |
+
tak jsem ti psal
|
| 29 |
+
abys věděla že to vím
|
| 30 |
+
jinak bych ti mohl pomoct něco zjistit
|
| 31 |
+
třeba ti můžu poslat odkaz na nějaký obchod
|
| 32 |
+
ale to ještě nevím
|
| 33 |
+
tak ti napíšu až budu vědět
|
| 34 |
+
jinak jak se máš
|
| 35 |
+
už dlouho jsme si neviděli
|
| 36 |
```
|
| 37 |
|
| 38 |
## Model
|