I'll try this
yaw
megoyaw3
AI & ML interests
You can contact here "Celebrity600@gmail.com"
Recent Activity
commented on
an
article
1 day ago
20+ Free and Paid AI Digital Marketing Tools to Automate Repetitive Tasks
upvoted
an
article
7 months ago
Yay! Organizations can now publish blog Articles
liked
a Space
about 1 year ago
derek-thomas/hugging-face-blog-assistant
Organizations
commented on
20+ Free and Paid AI Digital Marketing Tools to Automate Repetitive Tasks
1 day ago
upvoted
an
article
7 months ago
Article
Yay! Organizations can now publish blog Articles
β’
53
upvoted
an
article
over 1 year ago
Article
Optimizing Solar Panel Efficiency and Placement Using AI-Driven Project Management Tools
β’
4
reacted to
derek-thomas's
post with β€οΈ
over 1 year ago
Post
2768
Here is an AI Puzzle!
When you solve it just use a π emoji.
NO SPOILERS
A similar puzzle might have each picture that has a hidden meaning of summer, winter, fall, spring, and the answer would be seasons.
Its a little dated now (almost a year), so bottom right might be tough.
Thanks to @johko for the encouragement to post!
When you solve it just use a π emoji.
NO SPOILERS
A similar puzzle might have each picture that has a hidden meaning of summer, winter, fall, spring, and the answer would be seasons.
Its a little dated now (almost a year), so bottom right might be tough.
Thanks to @johko for the encouragement to post!
reacted to
inflatebot's
post with π
over 1 year ago
Post
3077
!!SEE UPDATE BELOW!!
I don't know who still needs to hear this, but if you're using Mistral Nemo-based models, you might have been using the wrong completions format. This is a signal boost from MarinaraSpaghetti's model card for NemoMix-Unleashed: MarinaraSpaghetti/NemoMix-Unleashed-12B
A lot of people have been working with a version of Nemo that's been reconfigured for ChatML, and while that works great, simply using the right format might be just as effective at correcting weirdness people in the AIRP scene sometimes have with Nemo.
Huge ups to Marinara for pointing this out, and to the MistralAI team member who let her know.
Update: A PR has been merged to SillyTavern Staging with new corrected templates! If you don't want to switch or wait, I put them up on GitHub: https://github.com/inflatebot/SillyTavern-Mistral-Templates
PRs for KoboldCPP's chat adapters and KoboldAI Lite *have been merged* and are coming in their respective releases (probably the next time KoboldCPP updates -- it didn't make it for 1.75.1, but you could just grab 'em from the repo!)
I don't know who still needs to hear this, but if you're using Mistral Nemo-based models, you might have been using the wrong completions format. This is a signal boost from MarinaraSpaghetti's model card for NemoMix-Unleashed: MarinaraSpaghetti/NemoMix-Unleashed-12B
A lot of people have been working with a version of Nemo that's been reconfigured for ChatML, and while that works great, simply using the right format might be just as effective at correcting weirdness people in the AIRP scene sometimes have with Nemo.
Huge ups to Marinara for pointing this out, and to the MistralAI team member who let her know.
Update: A PR has been merged to SillyTavern Staging with new corrected templates! If you don't want to switch or wait, I put them up on GitHub: https://github.com/inflatebot/SillyTavern-Mistral-Templates
PRs for KoboldCPP's chat adapters and KoboldAI Lite *have been merged* and are coming in their respective releases (probably the next time KoboldCPP updates -- it didn't make it for 1.75.1, but you could just grab 'em from the repo!)
reacted to
zolicsaki's
post with π₯
over 1 year ago
Post
1331
Weβve open-sourced an app, powered by SambaNova Cloud and Llama 405B, that intelligently detects when a web search is neededβthen answers directly or with RAG.
sambanovasystems/auto-web-search
π₯ A hidden Easter egg is that Auto Search detection is already trained into Llama 3.1 checkpoints. Simply use the tool usage system prompt below, and the model will either respond with a web search query if it deems necessary or respond to the query directly.π₯
Environment: IPython
Tools: Brave Search
Knowledge Cutoff Date: December 2023
Today's Date: September 2024
You are a helpful assistant. Reminder:
Search function calls MUST follow the specified format: "brave_search.call(query)"
You can see the documentation here
https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1#built-in-tooling
and read about how the tool usage was trained into Llama3.1 models in section 4.3.5 here https://arxiv.org/pdf/2407.21783
sambanovasystems/auto-web-search
π₯ A hidden Easter egg is that Auto Search detection is already trained into Llama 3.1 checkpoints. Simply use the tool usage system prompt below, and the model will either respond with a web search query if it deems necessary or respond to the query directly.π₯
Environment: IPython
Tools: Brave Search
Knowledge Cutoff Date: December 2023
Today's Date: September 2024
You are a helpful assistant. Reminder:
Search function calls MUST follow the specified format: "brave_search.call(query)"
You can see the documentation here
https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1#built-in-tooling
and read about how the tool usage was trained into Llama3.1 models in section 4.3.5 here https://arxiv.org/pdf/2407.21783
upvoted
an
article
over 1 year ago
Article
Introducing Community Tools on HuggingChat
β’
37
upvoted
an
article
over 1 year ago
Article
How No-Code Platforms Are Making Tech More Accessible to Everyone
β’
1
upvoted
a
paper
over 1 year ago
published
an
article
over 1 year ago
Article
How No-Code Platforms Are Making Tech More Accessible to Everyone
β’
1