Instructions to use kblomdahl/hugging_go with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kblomdahl/hugging_go with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, MistralForCausalLMAndSequenceClassification tokenizer = AutoTokenizer.from_pretrained("kblomdahl/hugging_go") model = MistralForCausalLMAndSequenceClassification.from_pretrained("kblomdahl/hugging_go", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model associated with https://github.com/kblomdahl/hugging_go.
It is a combined CasualLM and SequenceClassification model (based on Mistral) which given a sequence of game moves in a modified A1 algebraic notation [1] (with the player prefixed to each token), predict the winner and the next token.
Example input:
Bq16 Wd17 Bq5 Wq3 Bc5 Wd15 Br3 Wr2 Br4 Wp2
- Downloads last month
- 17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support