1 11

anish PRO

gpu-poor

http://gpupoor.me

gpu-poor

AI & ML interests

Multinode training, Multi-modal training, SLM

Recent Activity

liked a model about 1 month ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

liked a model about 2 months ago

gpt-omni/mini-omni

reacted to MoritzLaurer's post with 👍 2 months ago

I've been building a small library for working with prompt templates on the HF hub: `pip install prompt-templates`. Motivation: The community currently shares prompt templates in a wide variety of formats: in datasets, in model cards, as strings in .py files, as .txt/.yaml/.json/.jinja2 files etc. This makes sharing and working with prompt templates unnecessarily complicated. Prompt templates are currently the main hyperparameter that people tune when building complex LLM systems or agents. If we don't have a common standard for sharing them, we cannot systematically test and improve our systems. After comparing different community approaches, I think that working with modular .yaml or .json files is the best approach. The `prompt-templates` library : - proposes a standard for sharing prompts (entirely locally or on the HF hub) - provides some utilities that are interoperable with the broader ecosystem Try it: ```py # !pip install prompt-templates from prompt_templates import PromptTemplateLoader prompt_template = PromptTemplateLoader.from_hub(repo_id="MoritzLaurer/closed_system_prompts", filename="claude-3-5-artifacts-leak-210624.yaml") ``` The library is in early stages, feedback is welcome! More details in the docs: https://github.com/MoritzLaurer/prompt_templates/

View all activity

Organizations

None yet

gpu-poor's activity

liked a model about 1 month ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated 3 days ago • 1.19M • • 944

liked a model about 2 months ago

gpt-omni/mini-omni

Text-to-Speech • Updated Sep 4, 2024 • 418

reacted to MoritzLaurer's post with 👍 2 months ago

Post

1296

I've been building a small library for working with prompt templates on the HF hub: pip install prompt-templates. Motivation:

The community currently shares prompt templates in a wide variety of formats: in datasets, in model cards, as strings in .py files, as .txt/.yaml/.json/.jinja2 files etc. This makes sharing and working with prompt templates unnecessarily complicated.

Prompt templates are currently the main hyperparameter that people tune when building complex LLM systems or agents. If we don't have a common standard for sharing them, we cannot systematically test and improve our systems. After comparing different community approaches, I think that working with modular .yaml or .json files is the best approach.

The prompt-templates library :
- proposes a standard for sharing prompts (entirely locally or on the HF hub)
- provides some utilities that are interoperable with the broader ecosystem

Try it:

# !pip install prompt-templates
from prompt_templates import PromptTemplateLoader 
prompt_template = PromptTemplateLoader.from_hub(repo_id="MoritzLaurer/closed_system_prompts", filename="claude-3-5-artifacts-leak-210624.yaml")

The library is in early stages, feedback is welcome!

More details in the docs: https://github.com/MoritzLaurer/prompt_templates/