AdamF92 commited on
Commit
c855565
·
verified ·
1 Parent(s): aafebfc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -5
README.md CHANGED
@@ -1,29 +1,58 @@
1
  ---
2
  title: README
3
- emoji: 🦀
4
  colorFrom: blue
5
  colorTo: red
6
  sdk: static
7
  pinned: false
 
8
  ---
9
 
10
  # Reactive AI
11
- We are working on our own idea of Reactive Neural Networks (RxNN) - special kind of memory-augmented neural networks, that keeps state/memory
12
- between interactions/sequences instead of between tokens/elements in sequence and provides reactive communication patterns.
13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  Our primary architecture - **Reactor** - is planned as the first _**awareness AGI model**_, that's modelling awareness as an _Infinite Chain-of-Thoughts_,
15
  connected to _Short-Term and Long-Term Memory_ (_Attention-based Memory System_) and _Receptors/Effectors_ systems for real-time reactive processing.
16
  It will be able to constantly and autonomously learn from interactions in _Continouos Live Learning_ process.
17
 
 
18
  While the **Reactor** is the main goal, it's extremely hard to achieve, as it's definitely the most advanced neural network ensemble ever.
19
 
20
  That's why we designed simplified architectures, for incremental transformation from language/reasoning models to awareness model:
21
  - **Reactive Transformer** is introducing _Attention-based Memory System_ and adding _Short-Term Memory_ to Transformer language models
22
  - **Preactor** is adding _Long-Term Memory_ and ability to learn from interactions
23
 
24
- We are currently working on **Reactive Transformer Proof-of-Concept - RxT-Alpha**, that will be published soon
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
 
26
- More info soon
27
 
28
  ## RxNN Platform
29
  We are working on complete Reactive Neural Networks development framework - [RxNN github](https://github.com/RxAI-dev/RxNN)
 
1
  ---
2
  title: README
3
+ emoji: 👁
4
  colorFrom: blue
5
  colorTo: red
6
  sdk: static
7
  pinned: false
8
+ short_description: Reactive AI - Reactive Neural Networks and Event-Driven AI
9
  ---
10
 
11
  # Reactive AI
12
+ We are working on our own ideas of Reactive Neural Networks (RxNN) and Event-Driven AI, advancing from language models to AGI awareness models.
 
13
 
14
+ ## Reactive Neural Networks and Event-Driven AI
15
+ Reactive Neural Networks (RxNN) are memory-augmented neural networks with higher levels of recurrence (inter-sequence vs. intra-sequence in RNNs),
16
+ focused on processing single interactions with access to previous interactions via memory layers. We call this _**event-driven real-time processing**_
17
+ to distinguish it from classical _data-driven processing_ of the full conversation history in each interaction. This difference is crucial in case
18
+ of AGI and awareness - the key feature of humans awareness, is that we remember what we were doing 10 mins ago, without recalling the whole-day history - we
19
+ are working in real-time - just like event-driven _Reactive Neural Networks_.
20
+
21
+ In Event-Driven AI models are processing the data in reaction to environment or internal events, and are emitting other response events as a result.
22
+ Processing of input and output events by the model is called the interaction. Event or an interaction could occur in any point in continous time. Models
23
+ have to be stateful and remember the data between the interactions.
24
+
25
+ _**Strong Reactive Neural Networks**_ like **Reactor** could emit and listen to its internal events, while the _**Weak Reactive Neural Networks**_ are
26
+ working only on environment events.
27
+
28
+ ## Reactor AGI
29
  Our primary architecture - **Reactor** - is planned as the first _**awareness AGI model**_, that's modelling awareness as an _Infinite Chain-of-Thoughts_,
30
  connected to _Short-Term and Long-Term Memory_ (_Attention-based Memory System_) and _Receptors/Effectors_ systems for real-time reactive processing.
31
  It will be able to constantly and autonomously learn from interactions in _Continouos Live Learning_ process.
32
 
33
+ ## Reactive Language Models (RxLM)
34
  While the **Reactor** is the main goal, it's extremely hard to achieve, as it's definitely the most advanced neural network ensemble ever.
35
 
36
  That's why we designed simplified architectures, for incremental transformation from language/reasoning models to awareness model:
37
  - **Reactive Transformer** is introducing _Attention-based Memory System_ and adding _Short-Term Memory_ to Transformer language models
38
  - **Preactor** is adding _Long-Term Memory_ and ability to learn from interactions
39
 
40
+ ### RxT-Alpha Open Research
41
+ We are currently working on **Reactive Transformer Proof-of-Concept - RxT-Alpha**, especially on the new reinforcement learning stage - **Memory Reinforcement Learning**,
42
+ that's required for our reactive models, between the _Supervised Fine-Tuning_ and _Reinforcement Learning from Human Feedback for reactive models (RxRLHF)_. The research
43
+ is open, we are publishing the results of all separate steps, just after finishing them.
44
+
45
+ The Proof-of-Concept includes 3 small scale models based on **Reactive Transformer** architecture:
46
+ - RxT-Alpha-Micro (~11M params) - pre-training and fine-tuning finished, MRL in progress - training based on small synthetic datasets
47
+ - RxT-Alpha-Mini (~70M params) - pre-training in progress - training on real data
48
+ - RxT-Alpha (~530M/0.5B params) - pre-training in progress - training on real data
49
+
50
+ All the models have theoretically infinite context, limited only for single interaction (message + response), but in practice it's limited by short-term memory
51
+ capacity (it will be improved in Preactor). Limits are:
52
+ - RxT-Alpha-Micro - 256 tokens for single interaction, 6 * 256 for STM size (768kb), expected length of a smooth conversation min. ~4k tokens
53
+ - RxT-Alpha-Mini - 1024 tokens for single interaction, 8 * 1024 for STM size (8mb), expected length of a smooth conversation min. ~16k tokens
54
+ - RxT-Alpha - 2048 tokens for single interaction, 12 * 2048 for STM size (50mb), expected length of a smooth conversation min. ~32k tokens
55
 
 
56
 
57
  ## RxNN Platform
58
  We are working on complete Reactive Neural Networks development framework - [RxNN github](https://github.com/RxAI-dev/RxNN)