Activity
Mon
Wed
Fri
Sun
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
What is this?
Less
More
Owned by Brandon
Data is just the glyphs on the canvas of the world, it's one part of the BIG Picture. We're here to explore what it all means, building along the way.
Memberships
Organic Money
Private • 96 • Free
Q's Mastermind
Private • 3.4k • $1/m
Data Alchemy
Public • 19.7k • Free
LogikBot
Public • 17 • Free
Data Freelancer
Private • 75 • Paid
Skool Community
Public • 140.3k • Paid
406 contributions to Data Alchemy
19h ago
in
On to level 6 🚀
The irony is that it was this comment that pushed me over the threshold and into level 6: "I can teach you how to turn your $250 into $6,500 in 2hours without sending money to anyone or interrupting your daily activities and it's 100% legitimate and secure TEXT ME IF YOU ARE INTERESTED FOR MORE INFORM WITH THE DETAILS BELOW $$$$." Ah well.. for once it was useful 😂
6
2
New comment 15h ago
3 likes • 17h
#leveledup I guess sp/cammers are useful after all. 😂
Aug 12
in
Got nice little Data Engineering certificate :)
Nothing much, really... only an associate.. but nice :) I feel like sharing :) I'm discovering that I do like the "low level" stuff...
26
30
New comment 7d ago
1 like • Aug 12
Very nice! Congratulations!
Aug 8
in
Robust LLM output
Hi everyone, I am working on a project using LLaMA 3:8B or LLaMA 3.1:B with Ollama. The issue I'm facing is ensuring the output is robust and follows the exact format specified. For example, when I provide a prompt that should force the following output: ```json { "name": "Ali", "age": 20, "major": "CS" } ``` The actual output sometimes looks like this due to variations in the input: ```json { "name": "Ali", "city": "xxx" } ``` as shown it not return certain expected fields (if not exist its not return '' ) and it add field not asked in prompt output format. any ideas thanks
6
4
New comment Aug 10
1 like • Aug 10
Did you figure this out? I've gotten Llama3.1 8b to give me JSON output about 76% of the time for a very complex JSON structure, using Ollama Generate method, opposed to chat. I got it to 100% with a similar json structure like you're doing here. Check out the logs from each here, maybe it'll help! These examples also use a system message. For the following do this: First, select a generation from the right scroll menu. Simpler Structure: You can look at the key "output_format_str:", this is how i'm typically give the LLM the structure of what I want it to output. https://langfuse.bpdata.io/project/cluve1io10001y0rnqesj5bz4/traces/c23f6cd9-5639-4283-b398-265b04bf42d2?observation=2eb2e1f8-c674-4eca-9d9b-439794e71b45 Complex Structure: You can look at the key "output_format_str". The issue with this is that i'm using a library that doesn't make the nested JSON schema look 'nice'. https://langfuse.bpdata.io/project/cluve1io10001y0rnqesj5bz4/traces/80b0f7b8-ae07-4869-9b47-3d86bd68f1f7?observation=8f59c7b1-282d-44b7-9230-bc3042b7359c Let me know if you have any questions.
Aug 7
in
DeepLearning.AI
I strongly recommend the courses from DeepLearning.AI, I find them very useful and easy to follow 😄https://www.deeplearning.ai/courses/
19
18
New comment 3d ago
1 like • Aug 10
Stoked for this Data Engineering by Joe Reis. Hopefully some insights are gained as an extension to The Fundamentals of Data Engineering! https://www.coursera.org/professional-certificates/data-engineering?action=enroll
Aug 5
in
How to learn the most with the least effort?
Recall your best ever learning experience.. when you really learned something and it wasn't hard, maybe even fun. How did that happen? What learning method was it? What was the subject you learn? (let's say the scope of the question is some topic within computer science). Or if you don't remember, you could share your worst learning experience :) within computer science...
12
24
New comment Aug 13
1 like • Aug 10
When I was recently unemployed. Learning as I went in the business creation process, gathering data and improving on cold messaging/calling, creating content, researching and building products to solve the problem of suitable jobs, etc... Not sure why, but I got up everyday with a fire to learn from yesterday's mistakes and iterate. Now that i've gotten this contract, I don't feel that same drive to learn difficult things... 😂
1-10 of 406
@brandon-phillips-8784
Solutions Architect turned Data Synthesizer, interested in how we turn this stuff into useful things to people.
Active 11h ago
Joined Sep 22, 2023
INFP
Utah, United States
powered by