MouseWurX commited on
Commit
0dd429a
·
verified ·
1 Parent(s): 8586ab1

Card: add Part of Bob section

Browse files
Files changed (1) hide show
  1. README.md +31 -0
README.md CHANGED
@@ -37,6 +37,37 @@ Each GGUF has a `.bob.json` card beside it that Bob's catalogue reads when you a
37
 
38
  The project's own tests on one machine, for comparing Bobs with each other and with the model they came from, not for leaderboards.
39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  ## Licence and credit
41
 
42
  Apache 2.0, as the base model (Alibaba's Qwen team). The lessons it learned are Bob's own lesson sets (CC BY-SA 4.0) plus
 
37
 
38
  The project's own tests on one machine, for comparing Bobs with each other and with the model they came from, not for leaderboards.
39
 
40
+ ## Part of Bob
41
+
42
+ This is part of **[Bob](https://github.com/MouseWurX/Bob)**, a free, open-source AI agent that runs on your own computer (Windows, Mac, Linux, Raspberry Pi, Android). Nothing goes online unless you turn it on.
43
+
44
+ **What Bob does**
45
+ - **A real agent:** researches with sources, writes, runs and fixes code, reads and edits documents and files, works other apps, and makes pictures, clips, music and a voice.
46
+ - **His own brains:** models cut and retrained to run Bob on everyday graphics cards, with every score, lesson set and dollar published.
47
+ - **Bob-Net:** your Bobs share graphics cards and memory and check each other's work, on your home network.
48
+ - **Gaming friendly:** the brain unloads when idle, and a Gaming session gives the graphics card back to your game.
49
+ - **Private:** no account, no telemetry. Everything optional starts switched off.
50
+
51
+ **The Computer Science Lab** ([guide](https://github.com/MouseWurX/Bob/blob/main/app/docs/USER-GUIDE.md#make-your-own-brain-the-lab), [code](https://github.com/MouseWurX/Bob/tree/main/app/model-lab)), where this was made and measured. It's a workbench inside Bob, with no command line:
52
+ - **Make a brain:** shrink it, cut experts, or take out sight, hearing or the refusal habit. A brain is usable only after it has been tested.
53
+ - **Forge:** every way to make a new brain, side by side. It writes the plan for jobs that need a rented card.
54
+ - **Test:** scored challenges, one brain in six sizes, long-context and speed tests, and blind taste tests.
55
+ - **Teach:** teach a brain a lesson set, or have a bigger brain teach a smaller one.
56
+ - **Look inside:** see which experts your work uses. **fNRI** scans a brain while it answers and plays it back in 3D.
57
+
58
+ **Training protocols** ([Forge guide](https://github.com/MouseWurX/Bob/blob/main/app/model-lab/forge/README.md), [Forge journal](https://github.com/MouseWurX/Bob/blob/main/app/docs/FORGE-JOURNAL.md), [Making smaller models](https://github.com/MouseWurX/Bob/blob/main/app/docs/MAKING-SMALLER-MODELS.md)). Every model goes through the same steps, in order: baseline → clean first → analyse → train → cut in steps → heal → check every target → learn from its own answers → blend → live dials → publish. Each step is benchmarked. Why we chose this order:
59
+ - **Baseline first,** so every change is measured against the untouched model, not against a guess.
60
+ - **Clean before teaching, cut after training,** so a cut keeps what training taught and no fault gets baked in.
61
+ - **Measure before cutting (REAP),** so the experts that do the least work are the ones removed, per job, from real traces.
62
+ - **Cut in steps and heal from the full model's odds** (distillation), because small steps show where quality breaks, and copying the teacher's odds recovers more than plain answers can.
63
+ - **No target may drop,** so a gain in tools can't quietly cost coding, facts or safety.
64
+ - **Learn from its own answers** (on-policy, reward for tool calls that really work), because a model fixes the mistakes it actually makes, not the ones a teacher imagines.
65
+ - **Honest data:** test items are never taught, surgery and evil-check data never train, and everything is scrubbed of private data first.
66
+
67
+ **The plan:** what comes next, and why, in the [roadmap](https://github.com/MouseWurX/Bob/pull/230).
68
+
69
+ **Costs:** every rental, its card, its hours and what it bought, on the [costs page](https://github.com/MouseWurX/Bob/blob/main/app/docs/COSTS.md).
70
+
71
  ## Licence and credit
72
 
73
  Apache 2.0, as the base model (Alibaba's Qwen team). The lessons it learned are Bob's own lesson sets (CC BY-SA 4.0) plus