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pre-scheduled before the release of llama3 and was the best model at the moment :) So some of the info in this video is outdated by a week.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
@rusdad13044 ай бұрын
Fixed
@sankyuubigan4 ай бұрын
это определенно хорошо. надеюсь скоро искусственный интеллект сможет создавать порноролики с красивыми девушками
@geniusxbyofejiroagbaduta86654 ай бұрын
Did it beat llama3 70b
@s0ckpupp3t4 ай бұрын
Probably more uncensored which is a win
@electric_mind4 ай бұрын
Nope, LLaMA 3 70B has beat Mixtral 8x22B on almost all benchmarks with decent margin
@elawchess4 ай бұрын
@@electric_mind but presumably those benchmarks use the base version of Mixtral 8x22B
@dasistdiewahrheit95854 ай бұрын
@@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.
@s0ckpupp3t4 ай бұрын
@@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
@scitechtalktv97424 ай бұрын
Where is the link to the Colab notebook?
@AubzMan4 ай бұрын
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
@bertobertoberto34 ай бұрын
Excellent video!
@malikrumi12063 ай бұрын
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.
@kishoretvk4 ай бұрын
Good one
@mohsenghafari76524 ай бұрын
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
@pawan31334 ай бұрын
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?
@engineerprompt4 ай бұрын
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.
@pawan31334 ай бұрын
@@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 😀
@barackobama45524 ай бұрын
Lama i have a question, for RAG is best gpt 4 or this model? And what about gpt3 vs this model? Appreciate your answer
@engineerprompt4 ай бұрын
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.
@barackobama45524 ай бұрын
@@engineerprompt Thank you i really appreciate your answer Lama
@Techonsapevole4 ай бұрын
is Llama3 better in function calling?
@engineerprompt4 ай бұрын
Haven't really seen function calling with llama3 yet. Will have to wait for that.
@adriangpuiu4 ай бұрын
@@engineerprompt dolphin llama 3 on ollama model list
@mohamedkeddache42024 ай бұрын
Is the Mistral API free ?
@engineerprompt4 ай бұрын
Mistral api is not free.
@8eck4 ай бұрын
But still, Mistral/Mixtral was moving this industry forward for a long time. RIP
@pawan31334 ай бұрын
Why RIP? MoE is still great
@8eck4 ай бұрын
Guess it is useless now after Llama 3 release.
@engineerprompt4 ай бұрын
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.
@user-en4ek6xt6w4 ай бұрын
It's a really late video
@engineerprompt4 ай бұрын
I agree, it was pre-scheduled for release before llama3. Added a pinned comment with a disclaimer :) things are moving just too fast.
@user-en4ek6xt6w4 ай бұрын
@@engineerprompt yeah true not easy to keep up, you should try to compare the two model in function calling and rag
@engineerprompt4 ай бұрын
@@user-en4ek6xt6w that's a great suggestion. Planning on doing it.