ben burtenshaw
AI & ML interests
None yet
Recent Activity
published a bucket about 3 hours ago
burtenshaw/youtube-livestream-1-gemma4-pi-mono-trackio-bucket-3 published a bucket about 3 hours ago
burtenshaw/youtube-livestream-1-gemma4-pi-mono-trackio-bucket-2 updated a Space about 3 hours ago
burtenshaw/youtube-livestream-1-gemma4-pi-mono-trackioOrganizations
buckets 63
2.36 MB
burtenshaw/youtube-livestream-1-gemma4-pi-mono-trackio-bucket-3
0 Bytes
burtenshaw/youtube-livestream-1-gemma4-pi-mono-trackio-bucket-2
0 Bytes
burtenshaw/youtube-livestream-1-gemma4-pi-mono-trackio-bucket
0 Bytes
burtenshaw/youtube-livestream-1-trackio-bucket-16
0 Bytes
burtenshaw/youtube-livestream-1-trackio-bucket-15
0 Bytes
Posts 39
Post
8706
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:
VLMs playing atari
- RunningRL2
Agentic Environment - Atari Pong
🎮2Play and control Atari 2600 games through a web interface
- Sleeping
Agentic Environment - Atari PacMan
🎮Control and monitor Atari games through a web interface
- SleepingRL1
Agentic Environment - Atari Breakout
🎮1Play Atari games and view results via a web UI
- Runtime errorAgentsFeatured15
Qwen Atari
😻15Play Atari games using a vision-language model
RL Environments
VLMs playing atari
- RunningRL2
Agentic Environment - Atari Pong
🎮2Play and control Atari 2600 games through a web interface
- Sleeping
Agentic Environment - Atari PacMan
🎮Control and monitor Atari games through a web interface
- SleepingRL1
Agentic Environment - Atari Breakout
🎮1Play Atari games and view results via a web UI
- Runtime errorAgentsFeatured15
Qwen Atari
😻15Play Atari games using a vision-language model
spaces 137
Running
Agents
Youtube Livestream 1 Gemma4 Pi Mono Trackio
🎯
Display an interactive tracking dashboard
Running
Agents
Youtube Livestream 1 Trackio
🎯
Show interactive visualizations of your tracked data
Running
Agents
Openenv Examples Trackio
🚀
Show an interactive dashboard of your tracking data
Running
Agents
Openenv Wordle Qwen06b R3 20260622
🚀
Display real‑time I/O activity dashboard
Running
Agents
Openenv Wordle Qwen17b R3 20260622
🚀
Running
Agents
Openenv Wordle Qwen17b R2 20260622
🚀
models 106
burtenshaw/gemma4-pi-mono-youtube-livestream-1-scripts
Updated
burtenshaw/openenv-echo-world-model-liquidai-lfm2.5-350m-seed1
Text Generation • 0.4B • Updated
burtenshaw/openenv-echo-world-model-liquidai-lfm2.5-350m-seed2
Text Generation • 0.4B • Updated
burtenshaw/openenv-echo-world-model-liquidai-lfm2.5-350m-seed0
Text Generation • 0.4B • Updated
burtenshaw/openenv-echo-world-model-distilgpt2-seed0
Text Generation • 81.9M • Updated
burtenshaw/openenv-echo-world-model-distilgpt2-seed2
Text Generation • 81.9M • Updated
burtenshaw/openenv-echo-world-model-distilgpt2-seed1
Text Generation • 81.9M • Updated
burtenshaw/lfm25-350m-commonsenseqa-sft-lr1e4-r16-2k
Text Generation • Updated • 26
burtenshaw/qwen3-0.6b-mbpp-sft-lr1e4-r16-best-len2k
Text Generation • Updated • 27
burtenshaw/gemma-4-12b-sdpo-pi-mono-brevity-topk-v5
Updated • 32 • 1
datasets 67
burtenshaw/terminus-pi-trl-hard-tasks
Viewer • Updated • 16 • 45
burtenshaw/terminus-pi-trl-tasks
Viewer • Updated • 8 • 83
burtenshaw/transformers-pr-slop-dataset
Viewer • Updated • 1.46M • 990 • 2
burtenshaw/1-million-rows
Updated • 17
burtenshaw/european-cities
Viewer • Updated • 40 • 6
burtenshaw/european-countries
Viewer • Updated • 47 • 8
burtenshaw/ptc-optimized-kernel-job-inputs
Updated • 22
burtenshaw/kernel-skill-source
Updated • 87
burtenshaw/qwen3-5-0-8b-rmsnorm-experiment
Viewer • Updated • 33 • 46
burtenshaw/hub-stats-papers-last-week-2026-03-28
Preview • Updated • 14