OpenPipe @OpenPipeAI Twitter profile

Last Seen Profiles

@GC1508_

@TrevorWatson1

$Aradhana \z/$

@Aradhwin

@ughemoni

@salhthyl13

@JWohlgemut

@bokeplokalmalam

@3baadi2626

@about_asee8800

@87magdi

@QueenMAGAUltra

@hashire_joqr

@9Cy6xx0is2GfM7A

@PackTheater

@ReadBrothersLtd

@Dr_Eng_Alkawash

@katoshoptokyo

@rabumi26718

@zachrobinson

@MandyLJandrell

@TheRedShirtGuy

@bokeplokalmalam

@A_AAA_6

@dykes4jwekae

@Gotcha_rr

@kipmurkomen

@thejiggsupp

@laetitia_model

@Ngalam_wes

@salomeml_

@MalyPlus

@priyankagandhi

@yslthugs

@stwmaniax

@Honiez3

OpenPipe

@OpenPipeAI

5 months

We've added support for fine-tuning GPT-3.5-0125, OpenAI's newest and cheapest model. Sign up and check it out! 🙂 @OpenAIDevs

0

3

7

OpenPipe

@OpenPipeAI

1 year

Curious about Llama 2? Here's a fun feature we shipped last week: automatically convert your GPT-3.5 prompt to the Llama 2 format with best practices! Play with Llama 2, Claude 2, and GPT models at 😉

0

6

OpenPipe

@OpenPipeAI

5 months

Great walkthrough of how to use OpenPipe to create state-of-the-art fine-tuned models!

OctoAI

@OctoAICloud

6 months

Sorry to all the chefs out there, this recipe is only an example 😅 But if you are trying to build an AI-first product on top of LLM models, fine-tuning is definitely the answer!

1

0

8

0

2

4

OpenPipe

@OpenPipeAI

7 months

Super pumped. 💪

Helicone

@helicone_ai

7 months

Automatically link Helicone with OpenPipe to finetune models to improve inference speed, cost, and accuracy. Sign up for our beta here:

0

5

9

0

2

4

OpenPipe

@OpenPipeAI

7 months

If you want to be cool like sign up for OpenPipe. One-click LoRAs on your dataset!

character.ai | Personalized AI for every moment of your day

Meet AIs that feel alive. Chat with anyone, anywhere, anytime. Experience the power of super-intelligent chat bots that hear you, understand you, and remember you.

character.ai

Kyle Corbitt

@corbtt

7 months

I've now heard from two different sources that is fine-tuning hyperpersonalized LoRAs on a per-character and possibly per-user basis. I expect we'll see much more of this! LoRAs aren't much more expensive to serve than base models.

12

13

193

0

2

OpenPipe

@OpenPipeAI

7 months

Available on huggingface ofc, and also on the OpenPipe platform!

Kyle Corbitt

@corbtt

7 months

Just dropped a new Mistral variant "Mistral 7B Fine-Tune Optimized." Built to be a very strong base for downstream fine-tuning. On our evals fine-tunes trained on it are stronger than fine-tunes on any other 7B model, and even beat gpt-4. 🙂

14

29

333

0

2

OpenPipe

@OpenPipeAI

8 months

We've got you covered!

Sergey Karayev

@sergeykarayev

9 months

Solutions from replies: - @OpenPipeAI looks exactly right - @PortkeyAI launching feature soon - @analyticsaurabh building his own I currently use @helicone_ai , any plans from them?

4

7

34

1

0

1

OpenPipe

@OpenPipeAI

11 months

We just officially launched as a YC company, and announced our fine-tuning functionality! With OpenPipe fine-tuning you can automatically convert your expensive LLM prompt into a cheap, fast fine-tuned model. Check out more details in our launch at

Launch YC: OpenPipe: Convert expensive LLM prompts into fast, cheap fine-tuned models | Y Combinator

OpenPipe automatically captures your existing prompts and completions, then uses them to fine-tune a drop-in replacement. The replacement is faster, cheaper and often more accurate than your original...

www.ycombinator.com

1

0

1

OpenPipe

@OpenPipeAI

8 months

Yesterday we released new versions of our Python and JS SDK. Our fine-tuned models now support all the latest OpenAI features, including "tool calls" (the new version of function calls)!

0

1