PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models
Paper
โข
2501.03124
โข
Published
โข
6
Dokyoon
leeloolee
AI & ML interests
ai
Recent Activity
upvoted
a
paper
about 1 hour ago
PRMBench: A Fine-grained and Challenging Benchmark for Process-Level
Reward Models
reacted
to
singhsidhukuldeep's
post
with ๐
about 22 hours ago
Exciting breakthrough in e-commerce recommendation systems!
Walmart Global Tech researchers have developed a novel Triple Modality Fusion (TMF) framework that revolutionizes how we make product recommendations.
>> Key Innovation
The framework ingeniously combines three distinct data types:
- Visual data to capture product aesthetics and context
- Textual information for detailed product features
- Graph data to understand complex user-item relationships
>> Technical Architecture
The system leverages a Large Language Model (Llama2-7B) as its backbone and introduces several sophisticated components:
Modality Fusion Module
- All-Modality Self-Attention (AMSA) for unified representation
- Cross-Modality Attention (CMA) mechanism for deep feature integration
- Custom FFN adapters to align different modality embeddings
Advanced Training Strategy
- Curriculum learning approach with three complexity levels
- Parameter-Efficient Fine-Tuning using LoRA
- Special token system for behavior and item representation
>> Real-World Impact
The results are remarkable:
- 38.25% improvement in Electronics recommendations
- 43.09% boost in Sports category accuracy
- Significantly higher human evaluation scores compared to traditional methods
Currently deployed in Walmart's production environment, this research demonstrates how combining multiple data modalities with advanced LLM architectures can dramatically improve recommendation accuracy and user satisfaction.
upvoted
a
paper
14 days ago
GUI Agents: A Survey
Organizations
leeloolee's activity
upvoted
a
paper
about 1 hour ago
reacted to
singhsidhukuldeep's
post with ๐
about 22 hours ago
Post
3252
Exciting breakthrough in e-commerce recommendation systems!
Walmart Global Tech researchers have developed a novel Triple Modality Fusion (TMF) framework that revolutionizes how we make product recommendations.
>> Key Innovation
The framework ingeniously combines three distinct data types:
- Visual data to capture product aesthetics and context
- Textual information for detailed product features
- Graph data to understand complex user-item relationships
>> Technical Architecture
The system leverages a Large Language Model (Llama2-7B) as its backbone and introduces several sophisticated components:
Modality Fusion Module
- All-Modality Self-Attention (AMSA) for unified representation
- Cross-Modality Attention (CMA) mechanism for deep feature integration
- Custom FFN adapters to align different modality embeddings
Advanced Training Strategy
- Curriculum learning approach with three complexity levels
- Parameter-Efficient Fine-Tuning using LoRA
- Special token system for behavior and item representation
>> Real-World Impact
The results are remarkable:
- 38.25% improvement in Electronics recommendations
- 43.09% boost in Sports category accuracy
- Significantly higher human evaluation scores compared to traditional methods
Currently deployed in Walmart's production environment, this research demonstrates how combining multiple data modalities with advanced LLM architectures can dramatically improve recommendation accuracy and user satisfaction.
Walmart Global Tech researchers have developed a novel Triple Modality Fusion (TMF) framework that revolutionizes how we make product recommendations.
>> Key Innovation
The framework ingeniously combines three distinct data types:
- Visual data to capture product aesthetics and context
- Textual information for detailed product features
- Graph data to understand complex user-item relationships
>> Technical Architecture
The system leverages a Large Language Model (Llama2-7B) as its backbone and introduces several sophisticated components:
Modality Fusion Module
- All-Modality Self-Attention (AMSA) for unified representation
- Cross-Modality Attention (CMA) mechanism for deep feature integration
- Custom FFN adapters to align different modality embeddings
Advanced Training Strategy
- Curriculum learning approach with three complexity levels
- Parameter-Efficient Fine-Tuning using LoRA
- Special token system for behavior and item representation
>> Real-World Impact
The results are remarkable:
- 38.25% improvement in Electronics recommendations
- 43.09% boost in Sports category accuracy
- Significantly higher human evaluation scores compared to traditional methods
Currently deployed in Walmart's production environment, this research demonstrates how combining multiple data modalities with advanced LLM architectures can dramatically improve recommendation accuracy and user satisfaction.
- 2 replies
upvoted
a
paper
14 days ago
reacted to
m-ric's
post with ๐
20 days ago
Post
2435
๐๐ฎ๐ ๐ ๐ข๐ง๐ ๐
๐๐๐ ๐ซ๐๐ฅ๐๐๐ฌ๐๐ฌ ๐๐ข๐๐จ๐ญ๐ซ๐จ๐ง, ๐ ๐ฆ๐ข๐๐ซ๐จ๐ฌ๐๐จ๐ฉ๐ข๐ ๐ฅ๐ข๐ ๐ญ๐ก๐๐ญ ๐ฌ๐จ๐ฅ๐ฏ๐๐ฌ ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ ๐ฉ๐๐ซ๐๐ฅ๐ฅ๐๐ฅ๐ข๐ณ๐๐ญ๐ข๐จ๐ง ๐ฅณ
๐ฐ๏ธ Llama-3.1-405B took 39 million GPU-hours to train, i.e. about 4.5 thousand years.
๐ด๐ป If they had needed all this time, we would have GPU stories from the time of Pharaoh ๐: "Alas, Lord of Two Lands, the shipment of counting-stones arriving from Cathay was lost to pirates, this shall delay the building of your computing temple by many moons "
๐ ๏ธ But instead, they just parallelized the training on 24k H100s, which made it take just a few months.
This required parallelizing across 4 dimensions: data, tensor, context, pipeline.
And it is infamously hard to do, making for bloated code repos that hold together only by magic.
๐ค ๐๐๐ ๐ป๐ผ๐ ๐๐ฒ ๐ฑ๐ผ๐ป'๐ ๐ป๐ฒ๐ฒ๐ฑ ๐ต๐๐ด๐ฒ ๐ฟ๐ฒ๐ฝ๐ผ๐ ๐ฎ๐ป๐๐บ๐ผ๐ฟ๐ฒ! Instead of building mega-training codes, Hugging Face colleagues cooked in the other direction, towards tiny 4D parallelism libs. A team has built Nanotron, already widely used in industry.
And now a team releases Picotron, a radical approach to code 4D Parallelism in just a few hundred lines of code, a real engineering prowess, making it much easier to understand what's actually happening!
โก ๐๐'๐ ๐๐ถ๐ป๐, ๐๐ฒ๐ ๐ฝ๐ผ๐๐ฒ๐ฟ๐ณ๐๐น:
Counting in MFU (Model FLOPs Utilization, how much the model actually uses all the compute potential), this lib reaches ~50% on SmolLM-1.7B model with 8 H100 GPUs, which is really close to what huge libs would reach. (Caution: the team is leading further benchmarks to verify this)
Go take a look ๐ https://github.com/huggingface/picotron/tree/main/picotron
๐ฐ๏ธ Llama-3.1-405B took 39 million GPU-hours to train, i.e. about 4.5 thousand years.
๐ด๐ป If they had needed all this time, we would have GPU stories from the time of Pharaoh ๐: "Alas, Lord of Two Lands, the shipment of counting-stones arriving from Cathay was lost to pirates, this shall delay the building of your computing temple by many moons "
๐ ๏ธ But instead, they just parallelized the training on 24k H100s, which made it take just a few months.
This required parallelizing across 4 dimensions: data, tensor, context, pipeline.
And it is infamously hard to do, making for bloated code repos that hold together only by magic.
๐ค ๐๐๐ ๐ป๐ผ๐ ๐๐ฒ ๐ฑ๐ผ๐ป'๐ ๐ป๐ฒ๐ฒ๐ฑ ๐ต๐๐ด๐ฒ ๐ฟ๐ฒ๐ฝ๐ผ๐ ๐ฎ๐ป๐๐บ๐ผ๐ฟ๐ฒ! Instead of building mega-training codes, Hugging Face colleagues cooked in the other direction, towards tiny 4D parallelism libs. A team has built Nanotron, already widely used in industry.
And now a team releases Picotron, a radical approach to code 4D Parallelism in just a few hundred lines of code, a real engineering prowess, making it much easier to understand what's actually happening!
โก ๐๐'๐ ๐๐ถ๐ป๐, ๐๐ฒ๐ ๐ฝ๐ผ๐๐ฒ๐ฟ๐ณ๐๐น:
Counting in MFU (Model FLOPs Utilization, how much the model actually uses all the compute potential), this lib reaches ~50% on SmolLM-1.7B model with 8 H100 GPUs, which is really close to what huge libs would reach. (Caution: the team is leading further benchmarks to verify this)
Go take a look ๐ https://github.com/huggingface/picotron/tree/main/picotron
- 1 reply
reacted to
alimotahharynia's
post with ๐ฅ
20 days ago
Post
1565
Here's the space for our new article that leverages LLMs with reinforcement learning to design high-quality small molecules. Check it out at
alimotahharynia/GPT-2-Drug-Generator. You can also access the article here: https://arxiv.org/abs/2411.14157.
I would be happy to receive your feedback.
I would be happy to receive your feedback.
upvoted
a
paper
20 days ago
reacted to
cutechicken's
post with โค๏ธ
20 days ago
Post
2864
๐ RAGOndevice: High-Performance Local AI Document Analysis Assistant
๐ซ Core Value
RAGOndevice is a high-performance AI system running locally without cloud dependency. Using CohereForAI's optimized 7B model, it enables professional-grade document analysis on standard PCs. โจ
๐ Ondevice AI Advantages
1. ๐ Efficient Resource Utilization
๐ฏ Optimized 7B Model: Runs on standard PCs
โก Local Processing: Instant response without cloud
๐ป Low-Spec Compatible: Performs well on regular GPUs
๐ Optimized Memory: Ensures stable operation
2. ๐ก๏ธ Data Security & Cost Efficiency
๐ Complete Privacy: No external data transmission
๐ Offline Operation: No internet required
๐ฐ No Subscription: One-time installation
โ๏ธ Resource Optimization: Uses existing hardware
๐ฎ Key Features
1. ๐ Powerful Document Analysis
๐ Multi-Format Support: TXT, CSV, PDF, Parquet
๐ง Intelligent Analysis: Automatic structure recognition
๐๏ธ OCR Support: Advanced PDF text extraction
๐ฌ Real-time Chat: Natural language interaction
2. ๐ Local RAG System
๐ฏ Efficient Search: TF-IDF based local search
๐งฉ Context Understanding: Accurate information retrieval
๐ Wikipedia Integration: Rich background knowledge
๐ฏ Use Cases
๐ข Enterprise: Secure confidential document processing
๐ฌ Personal Research: Private data analysis
๐ Education: Personal learning material analysis
๐ป Development: Local codebase analysis
โญ Differentiators
๐โโ๏ธ Independent Operation: Zero cloud dependency
โก Instant Response: No network latency
๐ Complete Security: Full data control
๐ Cost Efficiency: No ongoing costs
๐ฎ Future Plans
๐ Enhanced model optimization
๐ Local knowledge base expansion
โก Hardware optimization
๐ Extended file support
๐ RAGOndevice democratizes high-performance AI, providing the optimal local AI solution for security-sensitive environments. ๐
๐ฅ Power of Local AI: Experience enterprise-grade AI capabilities right on your device!
VIDraft/RAGOndevice
๐ซ Core Value
RAGOndevice is a high-performance AI system running locally without cloud dependency. Using CohereForAI's optimized 7B model, it enables professional-grade document analysis on standard PCs. โจ
๐ Ondevice AI Advantages
1. ๐ Efficient Resource Utilization
๐ฏ Optimized 7B Model: Runs on standard PCs
โก Local Processing: Instant response without cloud
๐ป Low-Spec Compatible: Performs well on regular GPUs
๐ Optimized Memory: Ensures stable operation
2. ๐ก๏ธ Data Security & Cost Efficiency
๐ Complete Privacy: No external data transmission
๐ Offline Operation: No internet required
๐ฐ No Subscription: One-time installation
โ๏ธ Resource Optimization: Uses existing hardware
๐ฎ Key Features
1. ๐ Powerful Document Analysis
๐ Multi-Format Support: TXT, CSV, PDF, Parquet
๐ง Intelligent Analysis: Automatic structure recognition
๐๏ธ OCR Support: Advanced PDF text extraction
๐ฌ Real-time Chat: Natural language interaction
2. ๐ Local RAG System
๐ฏ Efficient Search: TF-IDF based local search
๐งฉ Context Understanding: Accurate information retrieval
๐ Wikipedia Integration: Rich background knowledge
๐ฏ Use Cases
๐ข Enterprise: Secure confidential document processing
๐ฌ Personal Research: Private data analysis
๐ Education: Personal learning material analysis
๐ป Development: Local codebase analysis
โญ Differentiators
๐โโ๏ธ Independent Operation: Zero cloud dependency
โก Instant Response: No network latency
๐ Complete Security: Full data control
๐ Cost Efficiency: No ongoing costs
๐ฎ Future Plans
๐ Enhanced model optimization
๐ Local knowledge base expansion
โก Hardware optimization
๐ Extended file support
๐ RAGOndevice democratizes high-performance AI, providing the optimal local AI solution for security-sensitive environments. ๐
๐ฅ Power of Local AI: Experience enterprise-grade AI capabilities right on your device!
VIDraft/RAGOndevice
liked
a
dataset
21 days ago
upvoted
a
paper
22 days ago
upvoted
a
collection
22 days ago
liked
a
model
22 days ago
upvoted
a
collection
23 days ago
liked
a
model
23 days ago
reacted to
julien-c's
post with ๐ฅ
28 days ago
Post
8072
After some heated discussion ๐ฅ, we clarify our intent re. storage limits on the Hub
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community ๐ฅ
cc: @reach-vb @pierric @victor and the HF team
TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
docs: https://huggingface.co/docs/hub/storage-limits
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community ๐ฅ
cc: @reach-vb @pierric @victor and the HF team
- 28 replies
liked
a
model
28 days ago
upvoted
a
paper
28 days ago
liked
a
Space
29 days ago
upvoted
a
paper
30 days ago
liked
a
dataset
about 1 month ago
liked
a
Space
about 1 month ago