NousResearch Profile Banner
Nous Research Profile
Nous Research

@NousResearch

Followers
79K
Following
3K
Media
125
Statuses
616

The AI Accelerator Company https://t.co/vrD0aDIGDQ

New York
Joined October 2020
Don't wanna be here? Send us removal request.
@NousResearch
Nous Research
2 months
Announcing the launch of Psyche. Nous Research is democratizing the development of Artificial Intelligence. Today, we’re embarking on our greatest effort to date to make that mission a reality: The Psyche Network. Psyche is a decentralized training
Tweet media one
172
418
2K
@NousResearch
Nous Research
6 hours
Atropos v0.3 is now out!. Our RL Environments framework has seen a lot of upgrades since v0.2 - some highlights:. - Atropos can now be used as a benchmarking and evaluations framework by @rogershijin, with our first external benchmark, Reward-Bench 2! . - Added the Reasoning Gym,.
@Teknium1
Teknium (e/λ)
6 hours
Just merged a PR for an environment to improve LLM as a Judge as well as evaluate models on their capability of doing judgements!. Did you know that all verifiable RL environments are nearly equivalent to benchmarks (and vice-versa!)? So we added an evaluate command to Atropos'
Tweet media one
7
18
168
@NousResearch
Nous Research
2 days
RT @StudioMilitary: Hermes 3 dataset, alternate art.
Tweet media one
Tweet media two
Tweet media three
Tweet media four
0
5
0
@NousResearch
Nous Research
2 days
RT @Teknium1: In case the post was too vague, yes - this is the Hermes 3 dataset. - 1 Million Samples.- Created SOTA without the censorship….
0
54
0
@NousResearch
Nous Research
2 days
Tweet media one
38
72
693
@NousResearch
Nous Research
10 days
Good technology spawns exploration and wonder.
Tweet media one
32
53
706
@NousResearch
Nous Research
21 days
Open-source tools for human challenges.
Tweet media one
Tweet media two
42
47
642
@NousResearch
Nous Research
1 month
RT @spencershum: It was fun working with the @huggingface team to make this feature a reality! Thanks for all your work and creativity @pcu….
0
23
0
@NousResearch
Nous Research
1 month
RT @Teknium1: 101 new and challenging reasoning RL environments are now supported in Atropos! . The entirety of the Reasoning Gym from by @….
0
16
0
@NousResearch
Nous Research
1 month
RT @_AndrewZhao: SOTA Gear, thanks based @Teknium1
Tweet media one
0
6
0
@NousResearch
Nous Research
1 month
RT @StudioMilitary: Guardian of Hermes. Protected by his sigil baldric.
Tweet media one
Tweet media two
Tweet media three
0
17
0
@NousResearch
Nous Research
1 month
Front Toward Enemy
Tweet media one
36
36
609
@NousResearch
Nous Research
1 month
This work is continued from and made possible thanks to the work of @gabe_grand and the MIT PPL team. Original paper:
1
3
51
@NousResearch
Nous Research
1 month
We are sharing the code for a parallelized inference server, which enables those using SMC to quickly benchmark on their constraint design, alongside example experiments with entropy based triggering and control vectors. LInk to repo:
Tweet media one
1
13
104
@NousResearch
Nous Research
1 month
Sequential Monte Carlo (SMC) is a powerful approximation method where multiple branches, or “particles”, are sampled, weighted, and resampled against a scoring function to produce likelier completions that fit the constraints.
Tweet media one
2
7
69
@NousResearch
Nous Research
1 month
Controlling text generation and structure remains a difficult problem to solve. Our newest blog post and release from Researcher in Residence @yaboilyrical explores how this problem becomes solvable using Sequential Monte Carlo approximation.
14
47
369
@NousResearch
Nous Research
2 months
RT @theemozilla: world's first 40B CC0-licensed model with DeepSeek MLA trained across dozens of data centers over the internet and the los….
0
45
0
@NousResearch
Nous Research
2 months
Nous Research will pay the first to properly and fully implement Atropos support into the VeRL project $2500!. For information on Atropos, our standalone RL environments framework, see: For the official VeRL issue on the bounty:
Tweet media one
@Teknium1
Teknium (e/λ)
2 months
First to integrate Atropos into VeRL gets $2500 - show me the PR and it working. If you want to find a team to work on it with and split the money come ask here too.
18
22
231
@NousResearch
Nous Research
2 months
We've made some updates to our API and NousChat over the past few weeks: . Access to our Inference API is no longer behind a waitlist: new users get immediate access . Hermes-3-Llama-3.1-405B is now available via the API (in addition to Hermes-3-Llama-3.1-70B,
Tweet media one
24
41
349
@NousResearch
Nous Research
2 months
Highlights from our first ever hackathon on RL Environments with Atropos!.
@cerebral_valley
Cerebral Valley
2 months
Six teams just won $50,000 at Nous' first ever RL hackathon 🤩. Check out the winning demos👇. @NousResearch @xai @nvidia @nebiusai @akashnet_ @LambdaAPI @tensorstax @runpod_io
10
18
211
@NousResearch
Nous Research
2 months
RT @Teknium1: Finally completed and merged the SWE_RL environment that was described by Meta's SWE RL paper into Atropos - A really difficu….
0
16
0