Sabitlenmiş Tweet
English
Mahdi Kamani (mmkamani7 🦋)
833 posts
Mahdi Kamani (mmkamani7 🦋)
@MMKamani7
Efficient GenAI @NVIDIA PhD of Informatics @PennState. ML & CV researcher, prev @AMD @WyzeCam @Twitter @Honeywell
Seattle, WA Katılım Ağustos 2013
1.3K Takip Edilen437 Takipçiler
Mahdi Kamani (mmkamani7 🦋) retweetledi
As I told @andersoncooper, we need statesmanship to end this war. Here's a plan.
1) Ceasefire of Iran, Israel, and US bombing.
2) Ironclad guarantee from US & Israel not to attack Iran with China & Russia involved.
3) Open the Straight of Hormuz.
4) Enact sanctions relief in exchange for Iran giving up enriched uranium.
Anderson Cooper 360°@AC360
Democratic Rep. Ro Khanna, who co-sponsored the war powers resolution which failed in the House in March, says if President Trump "starts carte blanche bombing power plants, that would be war crimes, and you would see some Republicans starting to speak up."
English
Mahdi Kamani (mmkamani7 🦋) retweetledi
Bombing civilian infrastructure is a war crime, and the time to speak out against it is right now.
English
Mahdi Kamani (mmkamani7 🦋) retweetledi
The aggression against Pasteur Institute of Iran—a century-old pillar of global health & member of International Pasteur Network—is a direct assault on international health security. This violates Geneva Conventions & IHL principles. We call on @WHO @ICRC & global health bodies to condemn this attack, assess damages & support reconstruction.
#PasteurInstituteIran #HealthSecurity #GenevaConventions #InternationalLaw #GlobalHealth #WHO #ICRC #HumanitarianLaw #Iran #ReconstructHealth
#PasteurNetwork
English
Mahdi Kamani (mmkamani7 🦋) retweetledi
Trump and Israel are bombing civilian bridges in Iran.
Not military targets.
Bridges that let people escape.
Roads that let ambulances reach the wounded.
Food, medicine, water: all blocked.
We saw it in Gaza, then Lebanon, and now Iran.
This is systematic assault on civilians
English
Exciting News: I officially got tenure!
Huge thanks to my amazing students, collaborators, and mentors!
English
Mahdi Kamani (mmkamani7 🦋) retweetledi
Section 620I of the Foreign Assistance Act is a law that prohibits the United States from providing security assistance or arms
sales to any country when the President is made aware that the country’s government “prohibits or otherwise restricts, directly or indirectly, the transport or delivery of United States humanitarian assistance.”
English
Mahdi Kamani (mmkamani7 🦋) retweetledi
The political system is broken. Over 60% of us now say the two-party establishment has failed us and we need a party that serves the people.
I’m running for President to offer a better choice for the people. Join us!
jillstein2024.com
English
Mahdi Kamani (mmkamani7 🦋) retweetledi
Mahdi Kamani (mmkamani7 🦋) retweetledi
Mahdi Kamani (mmkamani7 🦋) retweetledi
Super excited to welcome the @silo_AI team to @AMD - adding a phenomenal team of AI scientists and engineers to accelerate the adoption of AMD AI solutions and extend our open source AI software capabilities! shorturl.at/SmR6N
English
Excited to receive the @Google Research Scholar Award for my work on Learning and Fine-Tuning Large Models in Federated Environments! @GoogleAI
research.google/programs-and-e…
English
@ZozoHacker @lmsysorg @cohere The results are for one round. Nothing special. Since this is a RAG, I think the performance heavily relies on the Knowledge Base you are querying on. That is why I think Cohere model might not be an optimal choice for "us".
English
@MMKamani7 @lmsysorg @cohere Our results show similar performance between cmd-r and gpt-3.5 where Haiku is much worse. Seeing your Haiku gets high results catches my eyes. Are you doing many-shots? Or what's your secret?
English
Exciting news - the latest Arena result are out!
@cohere's Command R+ has climbed to the 6th spot, matching GPT-4-0314 level by 13K+ human votes! It's undoubtedly the **best** open model on the leaderboard now🔥
Big congrats to @cohere's incredible work & valuable contribution to the open community!
More exciting updates:
- Qwen1.5-32B-Chat almost top-10
- Gemma-1.1-7B-it shows great improvement (1044 -> 1088, on par with Llama-2-70b)
- Starling-7B-Beta still the best 7B with over 13K votes!
English
@lmsysorg @cohere Interesting performance from Command-R+! 👏 I'm wondering why we are getting different results with them in our RAG benchmarks.
x.com/MMKamani7/stat…
Mahdi Kamani (mmkamani7 🦋)@MMKamani7
Update to our RAG benchmarks with new models from @cohere. It seems that these models may not perfectly align with our specific use cases. I am curious if others have found the same trend or not in different benchmarks. Still #Haiku from @AnthropicAI has the best performance-cost tradeoff.
English
Hi Maxime. I am using the following snippet to call the Cohere model.
response = self.llm.chat( model=self.model, preamble=prompt_template, message=question, temperature=self.temperature, documents= documents)
The documentation around on how to format documents was not that clear. I used this to format the relevant documents.
documents = [ {'Content': doc.page_content, 'Source': doc.metadata['source']} for doc in documents ]
The preamble is the same for all models we are testing as well as document chunks for each question.
We have a predefined context for each question and prompt GPT4 to evaluate the responses for correctness and comprehensiveness from 0-4 based on some in context examples.
English
@MMKamani7 @cohere @AnthropicAI Very interesting. Are you able to share the code snippets you used for Command R/R+?
Eg what preamble did you use? How you split documents in the documents=… parameter?
Also, how do you evaluate results?
English
Update to our RAG benchmarks with new models from @cohere. It seems that these models may not perfectly align with our specific use cases. I am curious if others have found the same trend or not in different benchmarks. Still #Haiku from @AnthropicAI has the best performance-cost tradeoff.
Mahdi Kamani (mmkamani7 🦋)@MMKamani7
Interesting that even #Haiku model from @Anthropic beats all the models from @OpenAI in our internal RAG benchmark. This model is almost half the price of GPT 3.5 turbo!
English
@giannis2two @cohere @AnthropicAI I did it through "documents" parameter. Should it be the other way?
English
@MMKamani7 @cohere @AnthropicAI Hey Mahdi, qq re: the command models. Did you pass in the RAG resources in the context window or in the "documents" parameter supported by the chat endpoint?
English
Wow! It is almost @GroqInc fast 🤯
SambaNova@SambaNovaAI
🚀🌟🚀Excited to announce Samba-CoE v0.2, which outperforms DBRX by @DbrxMosaicAI and @databricks, Mixtral-8x7B from @MistralAI, and Grok-1 by @grok at a breakneck speed of 330 tokens/s. These breakthrough speeds were achieved without sacrificing precision and only on 8 sockets, showcasing the true capabilities of dataflow! Why would you buy 576 sockets and go to 8 bits when you can run using 16 bits and just 8 sockets. Try out the model and check out the speed here - coe-1.cloud.snova.ai. We are also providing a sneak peak of our next model, Samba-CoE v0.3, available soon with our partners at @LeptonAI. Read more about this announcement at sambanova.ai/blog/accurate-…
English
@ContextualAI Seems that you are fine tuning the embedding and LLM together with your data. What are the base models used for the benchmark here?
English
Today, we’re excited to announce RAG 2.0, our end-to-end system for developing production-grade AI.
Using RAG 2.0, we’ve created Contextual Language Models (CLMs), which achieve state-of-the-art performance on a variety of industry benchmarks. CLMs outperform strong RAG baselines built using GPT-4 and top open-source models like Mixtral, according to our research and customers.
Read more in our blog post: rag2.ai
English
Does that mean @Microsoft will embed all my private data and pass it to @OpenAI models for generating answers??!!!
Mushfiq Sajib@heysajib
Microsoft just integrated Copilot in OneDrive. This integration will revolutionize the way we work. Here's how this new feature will impact your life: ⤵️
English