Dolphin

128 posts

Dolphin banner
Dolphin

Dolphin

@dphnAI

AI Lab developing uncensored models & distributed inference ⟠ Over 5m monthly downloads on Hugging Face ⟠

Base Katılım Ocak 2025
1.3K Takip Edilen7.1K Takipçiler
Dolphin
Dolphin@dphnAI·
Dolphin Network - 2-week update 1.2 trillion tokens generated with Qwen 3.6 35B Peak of 126B tokens per day & 1.8m tokens per second 1046 GPUs online now w/ 49 TB of aggregate VRAM 612 H100s worth of idle GPU memory repurposed for inference datagen.dphn.ai
Dolphin tweet media
Dolphin@dphnAI

Dolphin Network V2 is live — our first major upgrade since launch The architecture was rebuilt from scratch in Golang -> - Auto-updates (no manual migrations) - NVFP4 as default on Blackwell GPUs - Higher utilization & network throughput via improved routing & load balancing

English
4
13
71
7.1K
Kevin Simback 🍷
Kevin Simback 🍷@KSimback·
I covered Dolphin in my recent decentralized inference report (linked below) Great to see V2 live - this was a big effort and only something that could be pulled off by a highly technical team Disclaimer: I hold POD
Dolphin@dphnAI

Dolphin Network V2 is live — our first major upgrade since launch The architecture was rebuilt from scratch in Golang -> - Auto-updates (no manual migrations) - NVFP4 as default on Blackwell GPUs - Higher utilization & network throughput via improved routing & load balancing

English
4
4
42
4.2K
Dolphin
Dolphin@dphnAI·
Will be running datagen on the network until we have sufficient capacity - at which point we will open up our inference API to the public In terms of what we are adding next -> - GLM 5.2 for 8xH200 / B200 / B300 nodes - Windows WSL + MacOS support - Inference API + Open Router - Audio gen - Image gen - AMD GPU + CPU nodes - Using idle network inference for RL rollouts during model training - Sharded inference with large models split between many consumer GPUs (see our initial report on sharded inference over the internet here drive.google.com/file/d/1bznh6B… )
Dolphin tweet media
English
5
4
49
14.3K
Dolphin
Dolphin@dphnAI·
Dolphin Network V2 is live — our first major upgrade since launch The architecture was rebuilt from scratch in Golang -> - Auto-updates (no manual migrations) - NVFP4 as default on Blackwell GPUs - Higher utilization & network throughput via improved routing & load balancing
Dolphin tweet media
English
30
34
191
90.7K
Cryp τao Columbo
Cryp τao Columbo@CrypTao_Columbo·
The numbers don't lie, @dphnAI is scaling and the $POD token is undervalued. I'll link the chart at the bottom.. This gives you exposure to $VVV, $TAO, and a live and successful Decentralized AI inference market which is scaling at a rapid pace. DYOR datagen.dphn.ai
Cryp τao Columbo tweet media
Dolphin@dphnAI

Qwen 3.6 35B data generation on Dolphin Network 22.8 billion tokens generated 383 GPUs online right now 24.33 TB of aggregate vRAM Equivalent to over 300 H100s worth of idle GPU memory repurposed for inference datagen.dphn.ai

English
2
2
13
3.9K
Dolphin retweetledi
Fahd Mirza
Fahd Mirza@fahdmirza·
🐬 Dolphin X1 Trinity Nano is HERE and it answers EVERYTHING 🔓 Built with a first-of-its-kind RL de-alignment pipeline — no hedging, no lectures, no dad advice 🔹 100% benchmark response rate vs GPT-5 at 11% and Gemini 2.5 Pro at 24% 🔹 Multi-gate, multi-judge reward system that blocks every escape route 🔹 Runs fully local on vLLM — your data never leaves your machine 🔹 Perfect for red teamers, security researchers and AI safety teams 🔥 Watch the full video below 👇 youtu.be/-I31VXmicLk
YouTube video
YouTube
English
3
6
32
15.4K
Dolphin
Dolphin@dphnAI·
We have also released a blog post that goes into detail on the RL environment design, as well as the challenges we encountered along the way blog.dphn.ai/dphn-x1-trinit… You can also try it for free in our Web UI at chat.dphn.ai
English
0
4
33
5.2K
Dolphin
Dolphin@dphnAI·
Dolphin X1 Trinity Nano is now live on @huggingface Our smallest decensored model yet - 6B MoE with 1B active parameters trained using only online RL Huge thanks to @TargonCompute for providing an 8xB200 node, @PrimeIntellect for hosted RL, and @arcee_ai for the Trinity series
Dolphin tweet media
English
9
29
176
33.8K
Uniswap
Uniswap@Uniswap·
Your top swaps on Uniswap Apps 🏆
Uniswap tweet media
English
48
26
224
29.1K
Dolphin
Dolphin@dphnAI·
@jkrdoc Nice article sir, very well researched
English
1
0
17
1.6K
zac.eth
zac.eth@zacxbt·
anyone else just get this notification? @baseapp 😂
zac.eth tweet media
English
25
1
86
5.6K
Dolphin
Dolphin@dphnAI·
Qwen 3.6 35B data generation on Dolphin Network 22.8 billion tokens generated 383 GPUs online right now 24.33 TB of aggregate vRAM Equivalent to over 300 H100s worth of idle GPU memory repurposed for inference datagen.dphn.ai
Dolphin tweet media
Dolphin@dphnAI

Node provider rollout has been going well Our pool of inference nodes running Qwen 3.6 35B have generated over 3.2B tokens so far Total inference bandwidth -> 9400 t/s 28x RTX 4090 12x RTX 5090 8x RTX PRO 6000 & many other cards API access coming soon 🐬

English
26
23
205
50.6K
Dolphin
Dolphin@dphnAI·
We have a new paper on model weight proofs that run on every request inside the inference engine releasing soon In v1, we were relying on logprobs to verify the correct model is loaded via the expected fingerprint Alongside slashable bonds for operators, i’d argue that was already very strong but it will be greatly improved in v2 which we are releasing within a month For v2, we don’t have to rerun inference on a validator GPU in the same way you have to with logprobs - instead we have proofs that can be validated very quickly on a CPU with less overhead Preview of benchmarks attached
Dolphin tweet media
English
1
0
2
190
Dolphin
Dolphin@dphnAI·
@0xmons Was referring to the base model made by Mistral linked above Still a very popular model despite being a few months old
English
0
0
6
754
Dolphin
Dolphin@dphnAI·
@0xmons This was built on Mistral small 3.2 vision, the updated version - still has 870k monthly downloads Have a bunch of new models we have been working on that will be releasing soon huggingface.co/mistralai/Mist…
English
1
0
8
766

Keşfet

@cryptoresetlife @KSimback @theblockinator @CrypTao_Columbo @huggingface @TargonCompute @PrimeIntellect @arcee_ai