Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap
•
11
Moritz Laurer
MoritzLaurer
AI & ML interests
None yet
Recent Activity
posted
an
update
about 4 hours ago
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!
📏 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.
🧪 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.
💾 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 👇
- prompt-templates docs: https://moritzlaurer.github.io/prompt_templates/
- all templates on the HF Hub: https://huggingface.co/datasets/MoritzLaurer/facts-grounding-prompts
- FACTS paper: https://storage.googleapis.com/deepmind-media/FACTS/FACTS_grounding_paper.pdf
posted
an
update
2 days ago
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. 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.
🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.
⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.
Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: https://huggingface.co/papers/2409.20370
Articles
Organizations
MoritzLaurer's activity
posted
an
update
about 4 hours ago
Post
115
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!
📏 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.
🧪 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.
💾 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 👇
- prompt-templates docs: https://moritzlaurer.github.io/prompt_templates/
- all templates on the HF Hub: MoritzLaurer/facts-grounding-prompts
- FACTS paper: https://storage.googleapis.com/deepmind-media/FACTS/FACTS_grounding_paper.pdf
📏 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.
🧪 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.
💾 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 👇
- prompt-templates docs: https://moritzlaurer.github.io/prompt_templates/
- all templates on the HF Hub: MoritzLaurer/facts-grounding-prompts
- FACTS paper: https://storage.googleapis.com/deepmind-media/FACTS/FACTS_grounding_paper.pdf
reacted to
merve's
post with ❤️
about 23 hours ago
Post
1280
What a beginning to this year in open ML 🤠
Let's unwrap! merve/jan-10-releases-677fe34177759de0edfc9714
Multimodal 🖼️
> ByteDance released SA2VA: a family of vision LMs that can take image, video, text and visual prompts
> moondream2 is out with new capabilities like outputting structured data and gaze detection!
> Dataset: Alibaba DAMO lab released multimodal textbook — 22k hours worth of samples from instruction videos 🤯
> Dataset: SciCap captioning on scientific documents benchmark dataset is released along with the challenge!
LLMs 💬
> Microsoft released Phi-4, sota open-source 14B language model 🔥
> Dolphin is back with Dolphin 3.0 Llama 3.1 8B 🐬🐬
> Prime-RL released Eurus-2-7B-PRIME a new language model trained using PRIME alignment
> SmallThinker-3B is a new small reasoning LM based on Owen2.5-3B-Instruct 💭
> Dataset: QWQ-LONGCOT-500K is the dataset used to train SmallThinker, generated using QwQ-32B-preview 📕
> Dataset: @cfahlgren1 released React Code Instructions: a dataset of code instruction-code pairs 📕
> Dataset: Qwen team is on the roll, they just released CodeElo, a dataset of code preferences 👩🏻💻
Embeddings 🔖
> @MoritzLaurer released zero-shot version of ModernBERT large 👏
> KaLM is a new family of performant multilingual embedding models with MIT license built using Qwen2-0.5B
Image/Video Generation ⏯️
> NVIDIA released Cosmos, a new family of diffusion/autoregressive World Foundation Models generating worlds from images, videos and texts 🔥
> Adobe released TransPixar: a new text-to-video model that can generate assets with transparent backgrounds (a first!)
> Dataset: fal released cosmos-openvid-1m Cosmos-tokenized OpenVid-1M with samples from OpenVid-1M
Others
> Prior Labs released TabPFNv2, the best tabular transformer is out for classification and regression
> Metagene-1 is a new RNA language model that can be used for pathogen detection, zero-shot embedding and genome understanding
Let's unwrap! merve/jan-10-releases-677fe34177759de0edfc9714
Multimodal 🖼️
> ByteDance released SA2VA: a family of vision LMs that can take image, video, text and visual prompts
> moondream2 is out with new capabilities like outputting structured data and gaze detection!
> Dataset: Alibaba DAMO lab released multimodal textbook — 22k hours worth of samples from instruction videos 🤯
> Dataset: SciCap captioning on scientific documents benchmark dataset is released along with the challenge!
LLMs 💬
> Microsoft released Phi-4, sota open-source 14B language model 🔥
> Dolphin is back with Dolphin 3.0 Llama 3.1 8B 🐬🐬
> Prime-RL released Eurus-2-7B-PRIME a new language model trained using PRIME alignment
> SmallThinker-3B is a new small reasoning LM based on Owen2.5-3B-Instruct 💭
> Dataset: QWQ-LONGCOT-500K is the dataset used to train SmallThinker, generated using QwQ-32B-preview 📕
> Dataset: @cfahlgren1 released React Code Instructions: a dataset of code instruction-code pairs 📕
> Dataset: Qwen team is on the roll, they just released CodeElo, a dataset of code preferences 👩🏻💻
Embeddings 🔖
> @MoritzLaurer released zero-shot version of ModernBERT large 👏
> KaLM is a new family of performant multilingual embedding models with MIT license built using Qwen2-0.5B
Image/Video Generation ⏯️
> NVIDIA released Cosmos, a new family of diffusion/autoregressive World Foundation Models generating worlds from images, videos and texts 🔥
> Adobe released TransPixar: a new text-to-video model that can generate assets with transparent backgrounds (a first!)
> Dataset: fal released cosmos-openvid-1m Cosmos-tokenized OpenVid-1M with samples from OpenVid-1M
Others
> Prior Labs released TabPFNv2, the best tabular transformer is out for classification and regression
> Metagene-1 is a new RNA language model that can be used for pathogen detection, zero-shot embedding and genome understanding
posted
an
update
2 days ago
Post
1462
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. 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.
🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.
⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.
Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: The Perfect Blend: Redefining RLHF with Mixture of Judges (2409.20370)
🧠 Process reward trainer: Enables training of Process-supervised Reward Models (PRMs), which reward the quality of intermediate steps, promoting structured reasoning. 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.
🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.
⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.
Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: The Perfect Blend: Redefining RLHF with Mixture of Judges (2409.20370)
updated
a
collection
2 days ago
reacted to
andrewrreed's
post with 🤝🔥
3 days ago
Post
2525
🚀 Supercharge your LLM apps with Langfuse on Hugging Face Spaces!
Langfuse brings end-to-end observability and tooling to accelerate your dev workflow from experiments through production
Now available as a Docker Space directly on the HF Hub! 🤗
🔍 Trace everything: monitor LLM calls, retrieval, and agent actions with popular frameworks
1⃣ One-click deployment: on Spaces with persistent storage and integrated OAuth
🛠 Simple Prompt Management: Version, edit, and update without redeployment
✅ Intuitive Evals: Collect user feedback, run model/prompt evaluations, and improve quality
📊 Dataset Creation: Build datasets directly from production data to enhance future performance
Kudos to the Langfuse team for this collab and the awesome, open-first product they’re building! 👏 @marcklingen @Clemo @MJannik
🔗 Space: langfuse/langfuse-template-space
🔗 Docs: https://huggingface.co/docs/hub/spaces-sdks-docker-langfuse
Langfuse brings end-to-end observability and tooling to accelerate your dev workflow from experiments through production
Now available as a Docker Space directly on the HF Hub! 🤗
🔍 Trace everything: monitor LLM calls, retrieval, and agent actions with popular frameworks
1⃣ One-click deployment: on Spaces with persistent storage and integrated OAuth
🛠 Simple Prompt Management: Version, edit, and update without redeployment
✅ Intuitive Evals: Collect user feedback, run model/prompt evaluations, and improve quality
📊 Dataset Creation: Build datasets directly from production data to enhance future performance
Kudos to the Langfuse team for this collab and the awesome, open-first product they’re building! 👏 @marcklingen @Clemo @MJannik
🔗 Space: langfuse/langfuse-template-space
🔗 Docs: https://huggingface.co/docs/hub/spaces-sdks-docker-langfuse
- 1 reply
updated
a
dataset
4 days ago
posted
an
update
4 days ago
Post
2001
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 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 today.
Source with the numbers 👇
https://techcrunch.com/2025/01/05/openai-is-losing-money-on-its-pricey-chatgpt-pro-plan-ceo-sam-altman-says/
- 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 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 today.
Source with the numbers 👇
https://techcrunch.com/2025/01/05/openai-is-losing-money-on-its-pricey-chatgpt-pro-plan-ceo-sam-altman-says/
- 3 replies
upvoted
a
collection
4 days ago
upvoted
an
article
4 days ago
Article
Announcing NVIDIA Cosmos World Foundation Models
By
•
•
21
upvoted
a
paper
4 days ago
posted
an
update
5 days ago
Post
2156
🚀 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 as well
- 📉 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).
- 💡 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.
Great work by https://huggingface.co/answerdotai !
If you’re looking for a high-speed zeroshot classifier, give it a try!
📄 Resources below: 👇
Base model: MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Large model: MoritzLaurer/ModernBERT-large-zeroshot-v2.0
Updated zeroshot collection: MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f
ModernBERT collection with paper: answerdotai/modernbert-67627ad707a4acbf33c41deb
- ⚡ 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 as well
- 📉 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).
- 💡 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.
Great work by https://huggingface.co/answerdotai !
If you’re looking for a high-speed zeroshot classifier, give it a try!
📄 Resources below: 👇
Base model: MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Large model: MoritzLaurer/ModernBERT-large-zeroshot-v2.0
Updated zeroshot collection: MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f
ModernBERT collection with paper: answerdotai/modernbert-67627ad707a4acbf33c41deb
liked
a
Space
5 days ago
updated
a
collection
5 days ago
updated
2
models
5 days ago
replied to
their
post
5 days ago
I'm experiencing the same, will release a 0-shot model based on ModernBERT soon
updated
a
collection
9 days ago