Prompt-templates docs: moritzlaurer.github.io/prompt_templ...
Templates on the hub: huggingface.co/datasets/Mor...
Prompt-templates collection: huggingface.co/collections/...
Paper: arxiv.org/pdf/2501.04519
—without GPT-4-based data distillation.
💾 While we wait for the release of code and datasets, you can already download the prompts they used from the HF Hub!
Details here 👇
🤖 A Process Preference Model (PPM) enables fine-grained evaluation of intermediate steps, improving training data quality.
🧪 The system underwent four rounds of self-evolution, progressively refining both the policy and reward models to tackle Olympiad-level math problems
📏 The paper introduces rStar-Math, which claims to rival OpenAI o1's math reasoning capabilities by integrating Monte Carlo Tree Search (MCTS) with step-by-step verified reasoning trajectories.
.@microsoft.com's rStar-Math paper claims that 🤏 ~7B models can match the math skills of o1 using clever train- and test-time techniques. You can now download their prompt templates from @hf.co !
🧵
- prompt-templates docs: moritzlaurer.github.io/prompt_templ...
- all templates on the HF Hub: huggingface.co/datasets/Mor...
- FACTS paper: storage.googleapis.com/deepmind-med...
💾 You can now download and reuse these prompt templates via the prompt-templates library!
🔄 The library simplifies sharing prompt templates on the HF hub or locally via standardized YAML files. Let’s make LLM work more transparent and reproducible by sharing more templates like this!
Links 👇
🧪 The authors tested different prompt templates on held-out data to ensure their generalization.
📚 It's highly educational to read these templates to learn how frontier labs design prompts and understand their limitations.
📏 The paper introduces the FACTS Grounding benchmark for evaluating the factuality of LLM outputs.
🤖 Fact-checking is automated by an ensemble of LLM judges that verify if a response is fully grounded in a factual reference document.
FACTS is a great paper from @GoogleDeepMind on measuring the factuality of LLM outputs. You can now download their prompt templates from @huggingface to improve LLM-based fact-checking yourself!
🧵
Release: github.com/huggingface/...
Mergekit: github.com/arcee-ai/mer...
Mixture of judges paper: huggingface.co/papers/2409....
⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.
Read the release notes and other resources here 👇
🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.
Perfect for tasks like stepwise reasoning.
🔀 Model merging: A new callback leverages mergekit to merge models during training, improving performance by blending reference and policy models - optionally pushing merged models to the Hugging Face Hub.
The TRL v0.13 release is 🔥! My highlight are the new process reward trainer to train models similar to o1 and tool call support:
🧠 Process reward trainer: Enables training of Process-supervised Reward Models (PRMs), which reward the quality of intermediate steps, promoting structured reasoning.
on revenue of $3.7 billion last year, with ChatGPT alone once costing an estimated $700,000 per day to operate. 💸🔥
- They build strong models and do great research. Whether this business model will work in the long run is one of the biggest questions in the AI economy.
Source with the numbers 👇
OpenAI is losing money on the $200/month subscription 🤯. It's crazy how expensive it is to run these largest LLMs:
- ChatGPT Pro costs $200/month ($2,400/year) and is still unprofitable for OpenAI due to higher-than-expected usage.
- OpenAI reportedly expected losses of about $5 billion
Base model: huggingface.co/MoritzLaurer...
Large model: huggingface.co/MoritzLaurer...
Updated zeroshot collection: huggingface.co/collections/...
ModernBERT collection with paper: huggingface.co/collections/...
Great work by @answerdotai !
If you’re looking for a high-speed zeroshot classifier, give it a try!
📄 Resources below: 👇
- 💡 What’s next? I’m preparing a newer version trained on better + longer synthetic data to fully leverage the 8k context window and improve upon the training mix of my older zeroshot-v2.0 models. I also hope that there will be a multilingual variant in the future.
- 📉 Performance tradeoff: It performs slightly worse than DeBERTav3 on average across my zeroshot classification task collection
- 🧠 Use cases: I recommend using it for scenarios requiring speed and a larger context window (8k).
🚀 Releasing a new zeroshot-classifier based on ModernBERT! Some key takeaways:
- ⚡ Speed & efficiency: It's multiple times faster and uses significantly less memory than DeBERTav3. You can use larger batch sizes and enabling bf16 (instead of fp16) gave me a ~2x speed boost
- 📉 Performance tradeoff:
Congrats @answerdotai, @LightOnIO and collaborators like @tomaarsen.com !
Paper and models here 👇https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb
Quite excited by the ModernBERT release! 0.15/0.4B small, 2T modern pre-training data and tokenizer with code, 8k context window, great efficient model for embeddings & classification!
This will probably be the basis for many future SOTA encoders! I can finally stop using DeBERTav3 2021 :D
"Open-source AI: year in review 2024": amazing Space with lots of data-driven insights into AI in 2024! Check it out 👇
The library is in early stages, feedback is welcome!
More details in the docs: github.com/MoritzLaurer...
```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")
```
- 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:
