burtenshaw/terminus-pi-trl-static-becc55-bucket
104 kB
ben burtenshaw
burtenshaw
AI & ML interests
None yet
Recent Activity
updated a model about 1 hour ago
burtenshaw/terminus-pi-trl-async-grpo-qwen35-4b updated a Space about 1 hour ago
burtenshaw/terminus-pi-trl-static-becc55 published a Space about 1 hour ago
burtenshaw/terminus-pi-trl-static-becc55Organizations
Posts 39
Post
8421
Smol course has a distinctive approach to teaching post-training, so I'm posting about how it’s different to other post-training courses, including the llm course that’s already available.
In short, the smol course is just more direct that any of the other course, and intended for semi-pro post trainers.
- It’s a minimal set of instructions on the core parts.
- It’s intended to bootstrap real projects you're working on.
- The material handsover to existing documentation for details
- Likewise, it handsover to the LLM course for basics.
- Assessment is based on a leaderboard, without reading all the material.
To start the smol course, follow here: smol-course
In short, the smol course is just more direct that any of the other course, and intended for semi-pro post trainers.
- It’s a minimal set of instructions on the core parts.
- It’s intended to bootstrap real projects you're working on.
- The material handsover to existing documentation for details
- Likewise, it handsover to the LLM course for basics.
- Assessment is based on a leaderboard, without reading all the material.
To start the smol course, follow here:
Articles 37
Article
47
DeepSeek-V4: a million-token context that agents can actually use
-
Agentic Environment - Atari Pong
🎮2Play and control Atari 2600 games through a web interface
-
Agentic Environment - Atari PacMan
🎮Control and monitor Atari games through a web interface
-
Agentic Environment - Atari Breakout
🎮1Play Atari games and view results via a web UI
-
Qwen Atari
😻15Play Atari games using a vision-language model
-
Agentic Environment - Atari Pong
🎮2Play and control Atari 2600 games through a web interface
-
Agentic Environment - Atari PacMan
🎮Control and monitor Atari games through a web interface
-
Agentic Environment - Atari Breakout
🎮1Play Atari games and view results via a web UI
-
Qwen Atari
😻15Play Atari games using a vision-language model
spaces 96
Running
Terminus Pi Trl Static Becc55
🎯
View and manage data with the Trackio dashboard
Running
Terminus Pi Trl Static A22f63
🎯
View and explore your tracked data in an interactive dashboard
Running
Terminus Pi Trl Static B697e9
🎯
View and manage your tracking data in an interactive dashboard
Running
Terminus Pi Trl Static D9c625
🎯
Visualize and manage your tracked data in an interactive dashboard
Running
Terminus Pi Trl Static 076221
🎯
Explore your data with an interactive tracking dashboard
Running
Agents
Swe Grpo Dashboard
🚀
Show interactive visualization of your program's I/O activity
models 63
burtenshaw/terminus-pi-trl-async-grpo-qwen35-4b
Text Generation • 4B • Updated
burtenshaw/terminus-pi-trl-async-grpo
Text Generation • 0.6B • Updated
burtenshaw/ptc-optimized-kernel
Updated
burtenshaw/codex
Updated
burtenshaw/dave
Updated
burtenshaw/LFM2.5-1.2B-Instruct-FineTome100k
Updated
burtenshaw/lfm25-finetome-unsloth
Updated
burtenshaw/lfm25-1.2b-finetome
Updated
burtenshaw/qwen3-0.6b-fineproofs-sft
Updated
burtenshaw/prime-lab-wordle
Updated • 4
datasets 65
burtenshaw/transformers-pr-slop-dataset
Viewer • Updated • 1.46M • 6.56k • 2
burtenshaw/1-million-rows
Updated • 48
burtenshaw/european-cities
Viewer • Updated • 40 • 46
burtenshaw/european-countries
Viewer • Updated • 47 • 35
burtenshaw/ptc-optimized-kernel-job-inputs
Updated • 14
burtenshaw/kernel-skill-source
Updated • 115
burtenshaw/qwen3-5-0-8b-rmsnorm-experiment
Viewer • Updated • 33 • 180
burtenshaw/hub-stats-papers-last-week-2026-03-28
Preview • Updated • 50
burtenshaw/test-rlm-sft
Viewer • Updated • 11 • 23
burtenshaw/community-evals-monitoring
Updated • 4