Alphatu🐇
@Alphatu4
Followers
3K
Following
5K
Media
862
Statuses
5K
YaqiZHANG @Alphatu4 in MENA｜Engineer ➡️Author&Founder&Writer | |NerdDiplomat🤗 | Author of 2 Books |Speaker of @pku1898 @penn @ApacheCon
Universe
Joined February 2022
Love technology Forever❤️ Be the change we wish to see in the world. In globalization We Trust🤝
2
1
42
We are also now working closely with cline to make Hermes even stronger in Cline with direct work on training and optimizing built around their coding harness!
Check out Hermes 4 70b & 405b models from Nous Research. Now available for you through both the Nous Research and Cline providers. (Nous Research brand booklet linked below)
2
5
53
First Milestone📌 Thai language🇹🇭 RAG integration with @llama_index, @weaviate_io, and #SeaLLM on https://t.co/gnTGXT6o0F. This blog (or notebook) demonstrate how to manage a non-English language RAG system without OpenAI🔥 HuggingFace and OpenAI-like https://t.co/S6qU1tk8hB
blog.float16.cloud
Thai language doesn't complete sentences with a "full stop". Integrate Huggingface Embedding and an OpenAI API-like with LlamaIndex.
3
7
25
"Follow the gradient" That's great. We are learning so much from open source, shipping, screwing up and figuring it out. Plans are good, reality is better
I have never seen it expressed exactly like that, but I wholeheartedly endorse it: Feedback beats planning. My plea at Meta was “No grand plans, follow the gradient of user value”.
14
63
828
❤️
A big milestone for Hermes. We did a lot of work to make a frontier level openmodel that does not dictate what expression you can elicit from the model. Super strong at math, coding, STEM, and creativity. Model Weights: https://t.co/ft01mebGW4 Check it out 👇
0
0
3
Anecdotally, I’ve found the people most vocal and showy about grinding hard (9-9-6) tend to have less throughput than a garden variety workaholic. I suspect this is because they’ve internalized endurance pace all the time. And loose the ability to sprint when needed.
68
60
2K
❤️🙏
1
0
4
Does anthropic trust claude code on their clusters i wonder lol
13
2
104
Crazy week! @moritzthuening ported his project from Wormhole to Blackhole with 1-line of code change. @OnDemandai has a killer agentic workflow available in the cloud and on-prem for @tenstorrent users @gokoyeb continues to expand TT offerings 🥹 it’s a beautiful thing
3
4
22
🏆Always the No.1 @Teknium1
Congrats to our post training team who worked on the Hermes 3's dataset - @Teknium1, @nullvaluetensor, and outside contributor @intrstllrninja - on creating the now #1 Trending dataset on HuggingFace!
1
1
2
Another image -> 3D -> v2v (wan 2.1) render. The quality you can get is awesome. And because it's 3D mid workflow you can do arbitrary camera position / movement etc. Still 10 hour rendering time 🤡
33
8
174
We are honored to have you here sharing your expertise with us. Everyone has been delighted.🙏 @jimkxa
@DavidBennett__
#riscv
1
1
3
🏆Always the No.1 @Teknium1
Congrats to our post training team who worked on the Hermes 3's dataset - @Teknium1, @nullvaluetensor, and outside contributor @intrstllrninja - on creating the now #1 Trending dataset on HuggingFace!
1
1
2
The Psyche office hours is beginning in 20 minutes in our Discord - https://t.co/t6H2MT8Qc7 See you there!
discord.com
We're a like-minded community interested in open-source AI. Join us and connect with fellow enthusiasts & experts alike! | 75525 members
Join the team behind the decentralized training projects Psyche and DisTrO for an office hours session in Nous Research's discord - Thursday evening, 6PM PST Discord Link: https://t.co/sUBzzedRFK
5
8
91
The IMO winner agent systems seems to have just been nous forge with reasoning models all along 😂 maybe we are going to have to bring that back in a much more rl enabled form some day soon? 😇 Read about that here https://t.co/va35smrdO2
forge.nousresearch.com
Forge Reasoning API by Nous Research
0
3
29
A bit more protection with local models - I dont blame chatgpt for this though, seems to just be a confusing fact about our legal system lol
Listen carefully to what Sam Altman says here before you use ChatGPT… “If you go talk to ChatGPT about your most sensitive stuff and then there's a lawsuit, we could be required to produce that … It makes sense to … really want the privacy clarity before you use it a lot.”
4
1
16
❤️
0
0
0
We are honored to have you here sharing your expertise with us. Everyone has been delighted.🙏 @jimkxa
@DavidBennett__
#riscv
1
1
3