SakanaAI/TinySwallow-1.5B-Instruct
Text Generation
•
Updated
•
3.38k
•
21
Nicky
NickyNicky
AI & ML interests
None yet
Recent Activity
liked
a model
about 2 hours ago
SakanaAI/TinySwallow-1.5B-Instruct
liked
a model
about 2 hours ago
Vision-CAIR/LongVU_Llama3_2_1B
reacted
to
singhsidhukuldeep's
post
with 🔥
about 7 hours ago
Exciting Research Alert: Revolutionizing Complex Information Retrieval!
A groundbreaking paper from researchers at MIT, AWS AI, and UPenn introduces ARM (Alignment-Oriented LLM-based Retrieval Method), a novel approach to tackle complex information retrieval challenges.
>> Key Innovations
Information Alignment
The method first decomposes queries into keywords and aligns them with available data using both BM25 and embedding similarity, ensuring comprehensive coverage of information needs.
Structure Alignment
ARM employs a sophisticated mixed-integer programming solver to identify connections between data objects, exploring relationships beyond simple semantic matching.
Self-Verification
The system includes a unique self-verification mechanism where the LLM evaluates and aggregates results from multiple retrieval paths, ensuring accuracy and completeness.
>> Performance Highlights
The results are impressive:
- Outperforms standard RAG by up to 5.2 points in execution accuracy on Bird dataset
- Achieves 19.3 points higher F1 scores compared to existing approaches on OTT-QA
- Reduces the number of required LLM calls while maintaining superior retrieval quality
>> Technical Implementation
The system uses a three-step process:
1. N-gram indexing and embedding computation for all data objects
2. Constrained beam decoding for information alignment
3. Mixed-integer programming optimization for structure exploration
This research represents a significant step forward in making complex information retrieval more efficient and accurate. The team's work demonstrates how combining traditional optimization techniques with modern LLM capabilities can solve challenging retrieval problems.
Organizations
NickyNicky's activity
liked
2
models
about 2 hours ago
reacted to
singhsidhukuldeep's
post with 🔥
about 7 hours ago
Post
649
Exciting Research Alert: Revolutionizing Complex Information Retrieval!
A groundbreaking paper from researchers at MIT, AWS AI, and UPenn introduces ARM (Alignment-Oriented LLM-based Retrieval Method), a novel approach to tackle complex information retrieval challenges.
>> Key Innovations
Information Alignment
The method first decomposes queries into keywords and aligns them with available data using both BM25 and embedding similarity, ensuring comprehensive coverage of information needs.
Structure Alignment
ARM employs a sophisticated mixed-integer programming solver to identify connections between data objects, exploring relationships beyond simple semantic matching.
Self-Verification
The system includes a unique self-verification mechanism where the LLM evaluates and aggregates results from multiple retrieval paths, ensuring accuracy and completeness.
>> Performance Highlights
The results are impressive:
- Outperforms standard RAG by up to 5.2 points in execution accuracy on Bird dataset
- Achieves 19.3 points higher F1 scores compared to existing approaches on OTT-QA
- Reduces the number of required LLM calls while maintaining superior retrieval quality
>> Technical Implementation
The system uses a three-step process:
1. N-gram indexing and embedding computation for all data objects
2. Constrained beam decoding for information alignment
3. Mixed-integer programming optimization for structure exploration
This research represents a significant step forward in making complex information retrieval more efficient and accurate. The team's work demonstrates how combining traditional optimization techniques with modern LLM capabilities can solve challenging retrieval problems.
A groundbreaking paper from researchers at MIT, AWS AI, and UPenn introduces ARM (Alignment-Oriented LLM-based Retrieval Method), a novel approach to tackle complex information retrieval challenges.
>> Key Innovations
Information Alignment
The method first decomposes queries into keywords and aligns them with available data using both BM25 and embedding similarity, ensuring comprehensive coverage of information needs.
Structure Alignment
ARM employs a sophisticated mixed-integer programming solver to identify connections between data objects, exploring relationships beyond simple semantic matching.
Self-Verification
The system includes a unique self-verification mechanism where the LLM evaluates and aggregates results from multiple retrieval paths, ensuring accuracy and completeness.
>> Performance Highlights
The results are impressive:
- Outperforms standard RAG by up to 5.2 points in execution accuracy on Bird dataset
- Achieves 19.3 points higher F1 scores compared to existing approaches on OTT-QA
- Reduces the number of required LLM calls while maintaining superior retrieval quality
>> Technical Implementation
The system uses a three-step process:
1. N-gram indexing and embedding computation for all data objects
2. Constrained beam decoding for information alignment
3. Mixed-integer programming optimization for structure exploration
This research represents a significant step forward in making complex information retrieval more efficient and accurate. The team's work demonstrates how combining traditional optimization techniques with modern LLM capabilities can solve challenging retrieval problems.
liked
a
model
about 10 hours ago
reacted to
nicolay-r's
post with 🔥
about 10 hours ago
Post
1393
📢 The LLaMA-3.1-8B distilled 8B version of the R1 DeepSeek AI is available besides the one based on Qwen
📙 Notebook for using it in reasoning over series of data 🧠 :
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_deep_seek_7b_distill_llama3.ipynb
Loading using the pipeline API of the transformers library:
https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_llama.py
🟡 GPU Usage: 12.3 GB (FP16/FP32 mode) which is suitable for T4. (a 1.5 GB less than Qwen-distilled version)
🐌 Perfomance: T4 instance: ~0.19 tokens/sec (FP32 mode) and (FP16 mode) ~0.22-0.30 tokens/sec. Is it should be that slow? 🤔
Model name: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
⭐ Framework: https://github.com/nicolay-r/bulk-chain
🌌 Notebooks and models hub: https://github.com/nicolay-r/nlp-thirdgate
📙 Notebook for using it in reasoning over series of data 🧠 :
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_deep_seek_7b_distill_llama3.ipynb
Loading using the pipeline API of the transformers library:
https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_llama.py
🟡 GPU Usage: 12.3 GB (FP16/FP32 mode) which is suitable for T4. (a 1.5 GB less than Qwen-distilled version)
🐌 Perfomance: T4 instance: ~0.19 tokens/sec (FP32 mode) and (FP16 mode) ~0.22-0.30 tokens/sec. Is it should be that slow? 🤔
Model name: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
⭐ Framework: https://github.com/nicolay-r/bulk-chain
🌌 Notebooks and models hub: https://github.com/nicolay-r/nlp-thirdgate
liked
a
dataset
about 13 hours ago
liked
a
model
1 day ago
upvoted
an
article
1 day ago
Article
The AI tools for Art Newsletter - Issue 1
•
37
reacted to
Jaward's
post with 🔥
2 days ago
Post
1379
The beauty in GRPO is the fact that it doesn’t care if the rewards are rule-based or learned, the hack: let the data self-normalize— trajectories in a batch compete against their mean, no value model, no extra params, just clean, efficient RL that cuts memory usage by 50%, while maintaining SOTA performance. btw it was introduced 9months prior to R1: arxiv.org/pdf/2402.03300
- 1 reply
liked
a
dataset
2 days ago
liked
2
models
2 days ago
liked
2
datasets
2 days ago
liked
3
models
2 days ago
liked
a
dataset
2 days ago
updated
a
model
3 days ago
liked
a
model
3 days ago