juiceb0xc0de/juicebucket
0 Bytes
Rick Holmberg PRO
juiceb0xc0de
AI & ML interests
Currently accepting pre-train models as candidates to run my neural network analysis pipeline on during intervals of the process. Early work is showing promising results in early stage intervention of drift and more organized results.
Recent Activity
updated a dataset 42 minutes ago
juiceb0xc0de/MiniCPM5-1B-atlas published a dataset 44 minutes ago
juiceb0xc0de/MiniCPM5-1B-atlas updated a Space about 2 hours ago
juiceb0xc0de/atlasingOrganizations
Posts 13
Post
174
HF community! Thank you so much the overwhelming flood of downloads I've received on my model atlases over the last couple of weeks. It makes me so happy to know other people out there are enjoying my work. With that being said, I am looking for an opportunity from the builders and trainers out there.
I've recently had the chance to do a mid pre training snapshot durin process and am looking for the opportunity to get some more of these images . This is a symbiotic trade. I am more than happy to do full reports on the status of your model and translate what your model may stand to gain from as you head towards the finish line. The atlas building process uses 8965 different prompt over a wide variety of behavioural features. I combines many different methods of interpreting what is going on inside the model between prompt and response that we are unable to see.
For anyone else interested in neural network imaging and mechanistic interpretation check out my library of atlases and my new work translating the numbers into a 3d visual format to accompany the sqlite database. If you've gpt a model that you wish to have atlased leave a commen and I'kk be sure to ge arounf to it as soon as possible.
https://huggingface.co/collections/juiceb0xc0de/cloud-atlases
I've recently had the chance to do a mid pre training snapshot durin process and am looking for the opportunity to get some more of these images . This is a symbiotic trade. I am more than happy to do full reports on the status of your model and translate what your model may stand to gain from as you head towards the finish line. The atlas building process uses 8965 different prompt over a wide variety of behavioural features. I combines many different methods of interpreting what is going on inside the model between prompt and response that we are unable to see.
For anyone else interested in neural network imaging and mechanistic interpretation check out my library of atlases and my new work translating the numbers into a 3d visual format to accompany the sqlite database. If you've gpt a model that you wish to have atlased leave a commen and I'kk be sure to ge arounf to it as soon as possible.
https://huggingface.co/collections/juiceb0xc0de/cloud-atlases
Articles 5
Article
What happens when you scale a hybrid SSM-Mamba-transformer: tmax-2B β 4B β 9B β 27B
This is a collection of models that I've trained on data collected through conversations with frontier models GPT, Claude, Perplexity and myself.
-
juiceb0xc0de/locus-gemma-4-e2b
Text Generation β’ 8B β’ Updated β’ 4 β’ 3 -
juiceb0xc0de/bella-bartender-gemma-e2b
Text Generation β’ 5B β’ Updated β’ 6 β’ 4 -
juiceb0xc0de/bella-bartender-8b-llama3.1
Text Generation β’ 8B β’ Updated β’ 1.55k β’ β’ 4 -
juiceb0xc0de/bella-bartender-heretic-1b
Text Generation β’ 1B β’ Updated β’ 2.49k β’ 2
This is a collection of models that I've trained on data collected through conversations with frontier models GPT, Claude, Perplexity and myself.
-
juiceb0xc0de/locus-gemma-4-e2b
Text Generation β’ 8B β’ Updated β’ 4 β’ 3 -
juiceb0xc0de/bella-bartender-gemma-e2b
Text Generation β’ 5B β’ Updated β’ 6 β’ 4 -
juiceb0xc0de/bella-bartender-8b-llama3.1
Text Generation β’ 8B β’ Updated β’ 1.55k β’ β’ 4 -
juiceb0xc0de/bella-bartender-heretic-1b
Text Generation β’ 1B β’ Updated β’ 2.49k β’ 2
A collection of model atlases for mechanistic interpretation I've created.
spaces 7
pinned
Running
Agents
2
LR Scheduler Benchmark
π
Standardized benchmark comparing learning rate schedulers
Sleeping
Agents
Tmax 4b Atlas 3d
π
Explore interactive 3D visualizations of a model interpretability atlas
Running
Agents
Atlasing
πΊ
Show pipeline status and run instructions
Sleeping
Agents
Llama.cpp-cu12.8-sm 80
π
Generate a personalized greeting for any name
Paused
Agents
8
Gemma 4 E2b Brain Atlas
π
Serve a Gradio web UI with embedded HF token
Sleeping
2
Forge
π₯
Build compatible ML training recipes with evidence
models 31
juiceb0xc0de/minicpm5-1b-SAE
Updated
juiceb0xc0de/bella-bartender-gemma-e4b
Text Generation β’ 8B β’ Updated β’ 631 β’ 1
juiceb0xc0de/qwen3-0.6b-SAE
Updated
juiceb0xc0de/dread-llama-8b-existential
Text Generation β’ 8B β’ Updated β’ 1.34k β’ 3
juiceb0xc0de/dread-llama-8b-existential-GGUF
Text Generation β’ 8B β’ Updated β’ 135
juiceb0xc0de/bella-bartender-v2
Text Generation β’ 9B β’ Updated β’ 820
juiceb0xc0de/bella-bartender-v2-GGUF
9B β’ Updated β’ 859
juiceb0xc0de/bella-tao-merged-qwen2_5-coder-7b
Text Generation β’ 8B β’ Updated β’ 927
juiceb0xc0de/bella-tao-merged-qwen2_5-coder-7b-GGUF
Text Generation β’ 8B β’ Updated β’ 871
juiceb0xc0de/bella-bartender-v2-moody-8b
Text Generation β’ Updated β’ 1.16k β’ 2
datasets 51
juiceb0xc0de/MiniCPM5-1B-atlas
Updated
juiceb0xc0de/llama-cpp-binaries
Updated β’ 76
juiceb0xc0de/a1july26
Preview β’ Updated β’ 41
juiceb0xc0de/llama-cpp-cuda-builds
Updated β’ 36
juiceb0xc0de/b-sides-index
Updated β’ 42
juiceb0xc0de/llama3.2-3b-instruct-atlas
Updated β’ 39
juiceb0xc0de/llama3.2-1b-instruct-atlas
Updated β’ 159
juiceb0xc0de/nova-1-large-atlas-v1.3
Updated β’ 41
juiceb0xc0de/AI21-Jamba2-3B
Updated β’ 451
juiceb0xc0de/loopcoder-v2-atlas
Updated β’ 675