context-is-key-forecasting icon indicating copy to clipboard operation
context-is-key-forecasting copied to clipboard

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Results 7 context-is-key-forecasting issues
Sort by recently updated
recently updated
newest added

Great work! we are very interested in your dataset. I was wondering if you plan to organize it into a JSON file for release, or if it’s already available somewhere,...

enhancement

# Add LiteLLM - support for Vertex AI, Gemini, Anthropic, Bedrock (100+LLMs) # What's changing This PR adds support for the above mentioned LLMs using LiteLLM https://github.com/BerriAI/litellm/ LiteLLM is a...

Hello @AndrewRobertWilliams 🤗 Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers...

Adds support for using Direct Prompt for models that are do not support instructions in HF. * Checks if the tokenizer has a chat template. * If not, the context...

# What's new - Instructions on setting up a basic environment to get started - More robust handling if the per-token cost for a model doesn't exist (assume zero) -...

Add step-by-step installation instructions to run the benchmark (including subsets thereof).

In particular, the `run_baselines.py` function doesn't run at all if ``NIXTLA_API_KEY` is not set, regardless of whether one of the Nixtla models is requested to be run. Key issue is...