MIXTRAL 8x22B: The BEST MoE Just got Better | RAG and Function Calling
Вставка
- Опубліковано 7 чер 2024
- How to get started with the MIXTRAL MoE 8x22B from Mistral AI.
🦾 Discord: / discord
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: / promptengineering
💼Consulting: calendly.com/engineerprompt/c...
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Advanced RAG:
tally.so/r/3y9bb0
LINKS:
Github: github.com/PromtEngineer/Yout...
Blog: mistral.ai/news/mixtral-8x22b/
Huggingface: huggingface.co/mistralai/Mixt...
LlamaIndex playlist: • Llama-Index
TIMESTAMPS:
[00:00] Introducing Mixtral-instruct
[00:45] Hands-On Testing with the Mistral API
[02:40] RAG and Function Calling with Financial Data
[03:55] Advanced Query Routing
[07:51] Extending Functionality to Tool Usage
All Interesting Videos:
Everything LangChain: • LangChain
Everything LLM: • Large Language Models
Everything Midjourney: • MidJourney Tutorials
AI Image Generation: • AI Image Generation Tu... - Наука та технологія
Disclaimer: This video was pre-scheduled before the release of llama3 and was the best model at the moment :) So some of the info in this video is outdated by a week. Crazy how fast things are moving
Fixed
это определенно хорошо. надеюсь скоро искусственный интеллект сможет создавать порноролики с красивыми девушками
Excellent video!
Although I heard you say that you were imagining a scenario in which you had two different, specialized vector stores, it made me want to ask you:: Is there a capacity limit on vector stores that isn't present on traditional rdbms systems? Thx.
Good one
Hi dear friend .
Thank you for your efforts .
How to use this tutorial in PDFs at other language (for example Persian )
What will the subject ?
I made many efforts and tested different models, but the results in asking questions about pdfs are not good and accurate!
Thank you for the explanation
When the LlamaIndex's LLM calls multiplication function then does it use python interpreter to actually run the function and get the answer?
Or does LLM try to do the calculation by trying to figure out the function?
I think can the LLM does the calculations. For simpler calculations like these its not going to be an issue for bigger models but for more complex operations you might want to have another tool which does the computation using python interpreter.
@@engineerprompt I checked, the model calls the function in python and passes the arguments to the function and then picks the output and display it.
Quick way to check: define a function that uses np but don't import np and it will throw an error 😀
Lama i have a question, for RAG is best gpt 4 or this model? And what about gpt3 vs this model?
Appreciate your answer
I think gpt4 will still give you the best results. This model will probably be better than gpt3.5. But for RAG, you need to consider the embedding model that you want to use. That will play a major role.
@@engineerprompt Thank you i really appreciate your answer Lama
Where is the link to the Colab notebook?
Where indeed it is. Unless the omission somehow act as a signpost for 'sign up for 'Advanced RAG' which has recently covered by LanceMartin of LangChain
Did it beat llama3 70b
Probably more uncensored which is a win
Nope, LLaMA 3 70B has beat Mixtral 8x22B on almost all benchmarks with decent margin
@@electric_mind but presumably those benchmarks use the base version of Mixtral 8x22B
@@s0ckpupp3t I don't think so. In my experience all uncensored flavors are worse than there censored versions. And since there exist working jailbreaks if one really needs it, I don't use uncensored models (means de-censored models) anymore.
@@dasistdiewahrheit9585 de-censored is probably worse than a censored base model yes, re-alignment is still a form of lobotomy and brute forcing the weights. But comparing base model to base model a less censored model is far more useful
is Llama3 better in function calling?
Haven't really seen function calling with llama3 yet. Will have to wait for that.
@@engineerprompt dolphin llama 3 on ollama model list
Is the Mistral API free ?
Mistral api is not free.
But still, Mistral/Mixtral was moving this industry forward for a long time. RIP
Why RIP? MoE is still great
Guess it is useless now after Llama 3 release.
I wouldn't say that. llama3 is great but its only 8k context but this model supports upto 64k context. This alone limits the use of llama3 in a whole bunch of applications.
It's a really late video
I agree, it was pre-scheduled for release before llama3. Added a pinned comment with a disclaimer :) things are moving just too fast.
@@engineerprompt yeah true not easy to keep up, you should try to compare the two model in function calling and rag
@@user-en4ek6xt6w that's a great suggestion. Planning on doing it.
Useless!! Dont bother watching this