Johnson Lai | Head of Data & AI @Chromia & Ambassador @Alibaba_Qwen | Previously @ChasmNetwork @CoinGecko
Joined January 2011
- Tweets 5,491
- Following 3,431
- Followers 9,954
- Likes 14,627
1,437 Photos and videos
superoo7 retweeted
Jun 5
Unbound is here, now on iPhone.
The model already runs fully on your phone.
→ Web search for live answers
→ Vision to read your images
→ No cloud, API and runs fully on-device
No subscription.
Free chat stays free.
Join the beta: testflight.apple.com/join/TQ…
2
7
17
1,456
🤣
May 28
wtf this is real?? they really are leaning into the whole slot machine thing huh
3
7
392
superoo7 retweeted
May 28
Added an uncensored text to image model from @PrismML to Unbound
Fully on-device.
No server round-trip, no content moderation pipeline, no logs sitting on someone else's GPU.
Just you, the model, and whatever you want to make.
↓
2
7
17
1,578
Excited to share I've joined the @Alibaba_Qwen Ambassador program 🎉
Looking forward to running events and helping grow the Qwen ecosystem
Always happy to support great open-source projects 🙌
11
1
30
1,986
Big thanks to @HaaaaaaydenH and the @Alibaba_Qwen team for the warm welcome 🙏
1
263
This is happening faster than I expected: @dealignai $DEAL just launched, newest of the "uncensored-model-token wave"
Open weights → real HF downloads → token on @base
$POD $DEAL $SUPERGEMMA $EVAL
More and more open-weight uncensored models on @Huggingface are launching tokens on @Base 👀
@dphnAI $POD — Dolphin series
@0xSUPERGEMMA $SUPERGEMMA — SuperGemma (Gemma fine-tune)
@eval_engine $EVAL — Unbound model
2
3
13
2,016
The rest of the wave worth watching:
$POD @dphnAI (launched on @AskVenice)
$SUPERGEMMA @0xSUPERGEMMA from @jangqai (launched on @bankrbot)
$EVAL from @Eval_Engine & @Chromia (launched on @virtuals_io)
All open-weight, all on @Base 👀
2
2
5
815
Thanks @XiaomiMiMo for supporting @Eval_Engine, we got 200M tokens to spend for improving it 🔥
1
3
11
2,645
superoo7 retweeted
May 24
96hrs since Unbound went live on @Eval_Engine
Total of 6k downloads across various Unbound models running fully offline
No servers, no cloud subscription
Chat with Unbound - unbound.evalengine.ai/
chromaway:native $EVAL
May 20
Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android
Zero servers
Zero cloud
Zero deployment
The whole model lives on your phone
2
7
13
2,436
More and more open-weight uncensored models on @Huggingface are launching tokens on @Base 👀
@dphnAI $POD — Dolphin series
@0xSUPERGEMMA $SUPERGEMMA — SuperGemma (Gemma fine-tune)
@eval_engine $EVAL — Unbound model
3
6
10
3,314
I've been following Qwopus's model for a while, great work!
If you're into fine tuning your own model, can also take a look at their publication, truly a rare 💎
github.com/R6410418/Jackrong…
May 22
BREAKING! Qwopus 3.6 27B is LIVE!
Thank you for your patience on this one, but I believe you'll find the wait was worth it!
We've benchmarked this thing up and down, verified that it holds at least a 75.25% (152/202) in the initial 202 SWE bench solves. Not a full run of 500, but it shows the agentic coding quality from the original 27B is retained while adding all of the additional Qwopus benefits across many domains. As always, Jackrong is absolutely cooking here!
COT quality has improved significantly through the inversion techniques from our Negentropy proof of concept. It also went through thorough curriculum training. You can check out the MMLU pro benchmarks on the model card, but it improved a whopping 10 points over the base model in physics, as well as meaningful jumps in Chemistry, business, and computer science.
However, the best part is that I was able to build an entire survival shooter game using this local model entirely. I genuinely was blown away by the results, which you can play right now on my HF space (link in comments below). "Qwopus Commander" was completed in 9 turns of Qwopus 3.6! To test the new long context training, I made it re-output the entire 3000 line program each turn, and it would make fixes and add features that I requested in large prompts, while perfectly replicating the entire rest of the game from context. What's more is that I did it all at Q8 KV cache quantization, and never had an issue over the entire 303k token run!
IMPORTANT: Run it at --temp 0.75 to 1. Mess with it in that range for your use case. Higher temp actually lets the fine-tune shine and be exploratory and is also more stable. Swe Bench was run at temp 1, the game was built mostly at 0.8!
We're so blessed to have all of you here and using the models! The support means so much! Please let me know what you build with it in the comments! Or if you have any issues getting it up and running, I will try my best to get back to you!
Looking forward to seeing what you legends produce with it this weekend!
huggingface.co/Jackrong/Qwop…
6
661
wllama -> llama.cpp’s WebGPU
expecting some performance boost on our Unbound model demo soon 👀
May 22
WebGPU support enables our Unbound model to run entirely on the browser
Try Unbound here - unbound.evalengine.ai
1
7
961
This is why we leaned into building what claude/chatgpt can't do
@Eval_Engine's Unbound is an uncensored AI model that runs in your browser, nothing leaves your device
most people have never even tried an uncensored model
we made it one click to run on any device
link below 👇
May 20
crypto twitter is a funny place, we complain about coins underperforming & there not being enough apps then dont use them when there's some actually doing well
1
1
6
572
We just released Unbound: 2b and 4b uncensored models, trained on a dgx spark in just a few days!
The model barely drifted from the base (gemma 4), but we got it "uncensored"
learning on top of the giant @dphnAI inspired us to make uncensored models accessible to everyone
excited to share more updates soon 👀
May 20
Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android
Zero servers
Zero cloud
Zero deployment
The whole model lives on your phone
7
31
2,917
superoo7 retweeted
May 20
Introducing Unbound: The first AI model with no guardrails that runs on your device - Browser, iPhone and Android
Zero servers
Zero cloud
Zero deployment
The whole model lives on your phone
5
18
45
16,863