Instructions to use rustformers/dolly-v2-ggml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rustformers/dolly-v2-ggml with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rustformers/dolly-v2-ggml")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rustformers/dolly-v2-ggml", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rustformers/dolly-v2-ggml with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rustformers/dolly-v2-ggml" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rustformers/dolly-v2-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rustformers/dolly-v2-ggml
- SGLang
How to use rustformers/dolly-v2-ggml 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 "rustformers/dolly-v2-ggml" \ --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": "rustformers/dolly-v2-ggml", "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 "rustformers/dolly-v2-ggml" \ --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": "rustformers/dolly-v2-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rustformers/dolly-v2-ggml with Docker Model Runner:
docker model run hf.co/rustformers/dolly-v2-ggml
Unrecognized model
I'm trying to load it as the example in the README shows, but I'm getting the following error:
Unrecognized model in rustformers/dolly-v2-ggml. Should have a `model_type` key in its config.json
What am I missing?
It probably means that you have to explicitly define the model type, or add it to the config.json file.
sure, but shouldn't it be part of the repo itself? Also, what's the model_type of the models provided in this repo?
Moste of these Repos were autoconverted by this Repo: https://github.com/LLukas22/Auto-GGML-Conversions It could be possible that some of them are missing some identifiers in their config.json files. These models are based on the gptneox architecture, you can also look this up if you simply navigate to the model pages of the base models.