Instructions to use playdev7/theseed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use playdev7/theseed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="playdev7/theseed") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("playdev7/theseed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use playdev7/theseed with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "playdev7/theseed" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "playdev7/theseed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/playdev7/theseed
- SGLang
How to use playdev7/theseed 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 "playdev7/theseed" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "playdev7/theseed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "playdev7/theseed" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "playdev7/theseed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use playdev7/theseed with Docker Model Runner:
docker model run hf.co/playdev7/theseed
| license: mit | |
| language: | |
| - ko | |
| - en | |
| metrics: | |
| - bertscore | |
| - accuracy | |
| - bleu | |
| - code_eval | |
| - charcut_mt | |
| - character | |
| pipeline_tag: text-generation | |
| tags: | |
| - conversational | |
| - mixtral | |
| # TheSeed | |
| ## Model Generation | |
| ``` | |
| from transformers import AutoConfig, AutoModel, AutoTokenizer | |
| config = AutoConfig.from_pretrained("playdev7/theseed", revision=revision) | |
| model = AutoModel.from_pretrained("playdev7/theseed", revision=revision, device_map="auto") | |
| tokenizer = AutoTokenizer.from_pretrained("playdev7/theseed", revision=revision) | |
| ``` | |
| --- | |
| based on Mixtral | |
| Made by Dohyeon Kwon(playdev7@gmail.com) |