Instructions to use dicta-il/dictalm2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dicta-il/dictalm2.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dicta-il/dictalm2.0")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dicta-il/dictalm2.0") model = AutoModelForCausalLM.from_pretrained("dicta-il/dictalm2.0") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dicta-il/dictalm2.0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dicta-il/dictalm2.0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dicta-il/dictalm2.0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dicta-il/dictalm2.0
- SGLang
How to use dicta-il/dictalm2.0 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 "dicta-il/dictalm2.0" \ --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": "dicta-il/dictalm2.0", "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 "dicta-il/dictalm2.0" \ --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": "dicta-il/dictalm2.0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dicta-il/dictalm2.0 with Docker Model Runner:
docker model run hf.co/dicta-il/dictalm2.0
Please add GGUF support for Hebrew Leaderboard
Hi, I didn't know how else to contact you,
Kindly please add GGUF support for the leaderboard. GPTQ is a depreciate format, EXL2 or GGUF would provide better compatibility with quantized models.
Thank you.
Hi,
Feel free to also open a discussion on the leaderboard page.
Regarding support for GGUF - the leaderboard uses the lighteval library with the HF endpoints deployed with a TGI container. In order to support GGUF we would have to create a container which serves a GGUF model on a TGI-compatible server.
We'll add it to the list, but it can take some time until we add support for it.