Instructions to use swype/deepshard-13B-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use swype/deepshard-13B-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="swype/deepshard-13B-ft")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("swype/deepshard-13B-ft") model = AutoModelForCausalLM.from_pretrained("swype/deepshard-13B-ft") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use swype/deepshard-13B-ft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "swype/deepshard-13B-ft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "swype/deepshard-13B-ft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/swype/deepshard-13B-ft
- SGLang
How to use swype/deepshard-13B-ft 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 "swype/deepshard-13B-ft" \ --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": "swype/deepshard-13B-ft", "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 "swype/deepshard-13B-ft" \ --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": "swype/deepshard-13B-ft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use swype/deepshard-13B-ft with Docker Model Runner:
docker model run hf.co/swype/deepshard-13B-ft
Can you share the training script and data?
#1
by NotOpenAI - opened
This comment has been hidden
Will do soon - training isn't yet completed.
@srikanthsrnvs - any news on that? I'd also be interested in the training script / finetuning script!? Any chance to get that?