7
Financial LLM Performance Leaderboard
📈
Expect the Unexpected: FailSafe Long Context QA for Finance
Sam Julien PRO
samjulien
AI & ML interests
None yet
Recent Activity
liked
a Space
22 days ago
Writer/Financial_LLM_Performance_Leaderboard
liked
a Space
29 days ago
galileo-ai/agent-leaderboard
upvoted
a
paper
29 days ago
Expect the Unexpected: FailSafe Long Context QA for Finance
Organizations
samjulien's activity
liked
a
Space
22 days ago
liked
a
Space
29 days ago
upvoted
a
paper
29 days ago
liked
a
Space
3 months ago
updated
a
Space
3 months ago
posted
an
update
3 months ago
Post
1522
🔥 RAG in just a few lines of code?!
Try out our Hacker News Listener with new built-in RAG capabilities and Palmyra X 004 from the team at Writer!
This Writer Framework app:
- Scrapes up to 500 HN stories and comments
- Uploads them to a Knowledge Graph
- Enables interactive chat with the content using graph-based RAG
- Provides source attribution with every response
The best part? Setting up RAG is now incredibly simple - just a few lines of code to connect your Knowledge Graph as a tool with Palmyra X 004.
🤗 Space: samjulien/hacker-news-listener
💻 Code: https://github.com/writer/framework-tutorials/tree/main/hacker-news-social-listener
Try out our Hacker News Listener with new built-in RAG capabilities and Palmyra X 004 from the team at Writer!
This Writer Framework app:
- Scrapes up to 500 HN stories and comments
- Uploads them to a Knowledge Graph
- Enables interactive chat with the content using graph-based RAG
- Provides source attribution with every response
The best part? Setting up RAG is now incredibly simple - just a few lines of code to connect your Knowledge Graph as a tool with Palmyra X 004.
🤗 Space: samjulien/hacker-news-listener
💻 Code: https://github.com/writer/framework-tutorials/tree/main/hacker-news-social-listener
updated
a
Space
3 months ago
commented
a
paper
7 months ago
Congratulations, team! Amazing work! 👏
reacted to
melisa's
post with 🔥
7 months ago
Post
3090
🔥 Introducing "Writing in the Margins (WiM)" - better inference pattern for long context LLMs that solves the Lost-in-the-Middle problem 🔥
Paper page: Writing in the Margins: Better Inference Pattern for Long Context Retrieval (2408.14906)
TL;DR
Make your model write "margin notes" as you chunk prefill the KV cache. Then ask it reread all notes before it speaks up.
Works with humans, works with AI 🤖
WiM leverages the chunked prefill of the key-value cache, which concurrently generates query-based extractive summaries at each step of the prefill that are subsequently reintegrated at the end of the computation. We term these intermediate outputs “margins”, drawing inspiration from the practice of making margin notes for improved comprehension of long contexts in human reading. We show that this technique, which adds only minimal additional computation, significantly improves LLMs long context reasoning capabilities.
Think: Every chunk has a chance to be attended to/ be at the end of the context at least once. 🎉
📊 Results:
- An average accuracy boost of 7.5% in multi-hop reasoning tasks like HotpotQA and MultiHop-RAG.
- Even a 30% increase in F1-score for summarisation-like tasks (CWE).
Plus, WiM fits seamlessly into interactive applications (think: progress bar!). It can provide real-time progress updates during data retrieval and integration, making it user-friendly and transparent - a stark contrast to feeding 1mln tokens to an LLMs and waiting 6 min for the first token. 🤯
👩💻🧑💻 Check it out and contribute to our open-source project here: https://github.com/writer/writing-in-the-margins
🧠 More about chunked prefill: https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill
Paper page: Writing in the Margins: Better Inference Pattern for Long Context Retrieval (2408.14906)
TL;DR
Make your model write "margin notes" as you chunk prefill the KV cache. Then ask it reread all notes before it speaks up.
Works with humans, works with AI 🤖
WiM leverages the chunked prefill of the key-value cache, which concurrently generates query-based extractive summaries at each step of the prefill that are subsequently reintegrated at the end of the computation. We term these intermediate outputs “margins”, drawing inspiration from the practice of making margin notes for improved comprehension of long contexts in human reading. We show that this technique, which adds only minimal additional computation, significantly improves LLMs long context reasoning capabilities.
Think: Every chunk has a chance to be attended to/ be at the end of the context at least once. 🎉
📊 Results:
- An average accuracy boost of 7.5% in multi-hop reasoning tasks like HotpotQA and MultiHop-RAG.
- Even a 30% increase in F1-score for summarisation-like tasks (CWE).
Plus, WiM fits seamlessly into interactive applications (think: progress bar!). It can provide real-time progress updates during data retrieval and integration, making it user-friendly and transparent - a stark contrast to feeding 1mln tokens to an LLMs and waiting 6 min for the first token. 🤯
👩💻🧑💻 Check it out and contribute to our open-source project here: https://github.com/writer/writing-in-the-margins
🧠 More about chunked prefill: https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill
-
- 2 replies
upvoted
a
paper
7 months ago
published
an
article
7 months ago
Article
Using Writer Framework with HF中国镜像站 Spaces
By
•
•
30
updated
2
Spaces
7 months ago
replied to
their
post
7 months ago
Thank you for all of your support!
liked
2
models
7 months ago
posted
an
update
7 months ago
Post
1964
🔥 Today, Writer dropped Palmyra-Med-70b and Palmyra-Fin-70b, two new domain-specific models that are setting a new standard for medical and financial model performance.
TL;DR
Palmyra-Med-70b
🔢 8k and 32k versions available
🚀 MMLU performance of ~86%, outperforming other top models
👨⚕️ Great for diagnosing, planning treatments, medical research, insurance coding and billing
📃 Open-model license for non-commercial use cases
🤗 Available on HF中国镜像站: Writer/Palmyra-Med-70B
💾 Live on NVIDIA NIM: https://build.nvidia.com/writer/palmyra-med-70b
Palmyra-Fin-70b
🚀 Passed the CFA Level III exam with a 73% score — the first model to do so
💸 Skilled at complex tasks like investment research, financial analysis, and sentiment analysis
📈 Outperformed other top models on a long-fin-eval test of real-world use cases
📃 Open-model license for non-commercial use cases
🤗 Available on HF中国镜像站: https://huggingface.co/Writer/Palmyra-Fin-70B-32K
💾 Live on NVIDIA NIM: https://build.nvidia.com/writer/palmyra-fin-70b-32k
Try them out and let us know what you think!
TL;DR
Palmyra-Med-70b
🔢 8k and 32k versions available
🚀 MMLU performance of ~86%, outperforming other top models
👨⚕️ Great for diagnosing, planning treatments, medical research, insurance coding and billing
📃 Open-model license for non-commercial use cases
🤗 Available on HF中国镜像站: Writer/Palmyra-Med-70B
💾 Live on NVIDIA NIM: https://build.nvidia.com/writer/palmyra-med-70b
Palmyra-Fin-70b
🚀 Passed the CFA Level III exam with a 73% score — the first model to do so
💸 Skilled at complex tasks like investment research, financial analysis, and sentiment analysis
📈 Outperformed other top models on a long-fin-eval test of real-world use cases
📃 Open-model license for non-commercial use cases
🤗 Available on HF中国镜像站: https://huggingface.co/Writer/Palmyra-Fin-70B-32K
💾 Live on NVIDIA NIM: https://build.nvidia.com/writer/palmyra-fin-70b-32k
Try them out and let us know what you think!
-
- 2 replies
liked
a
model
9 months ago
