prompt2model
prompt2model copied to clipboard
prompt2model - Generate Deployable Models from Natural Language Instructions
# Description This PR deletes the current "ci.yml" continuous integration workflow and instead creates two workflows, "pull_request_ci.yml" (which runs as a gate for all pull requests) and "daily_ci.yml" (which runs...
In the `project.toml`, we do not require a specific version of `openai` and `litellm`. If a user directly runs `pip install .`, then the newest version of `openai` may not...
Currently prompt2model is limited to text input text output tasks. The underlying framework can certainly handle different modalities, and it would be great to see prompt2model be able to handle...
# Description Modified the `generate_dataset_split` method in `prompt2model/dataset_generator/prompt_based.py` to take 3 additional optional arguments, `retrieved_dataset`, `few_shot_method`, and `n_shots` # References https://github.com/neulab/prompt2model/issues/327
Instead of only using examples given by the users in the user prompt, what if we try to use retrieved datasets (if applicable) as high-quality shots for the dataset generator?
phi-1.5 is a new small model with seemingly nice capabilities: https://arxiv.org/abs/2309.05463 It'd be good to make sure that our model retriever has the ability to retrieve this model and fine-tune...
# Description Added explanation column to the dataset generation and modified the prompt templates to include explanations # References Chain-of-thought prompting # Blocked by - NA
Here is the output from my prompt_spec: ``` Instruction: Task description: Identify a broad class given several examples from that class Examples: input= Q: The similarity among DemandBase, InfusionSoft, and...
I encountered a strange bug of `tiktoken`. Basically, we need to change our `count_tokens_from_string` function: ``` def count_tokens_from_string(string: str, encoding_name: str = "cl100k_base") -> int: """Handle count the tokens in...
We currently have interfaces to interact with prompt2model, in the form of prompt2model_demo.py and prompt2model_demo.ipynb. While the individual components of prompt2model are generally well-tested, these two files are completely untested....