Instructions to use ChonkE/ChonkE_110m_Alignment_Cube_Research with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ChonkE/ChonkE_110m_Alignment_Cube_Research with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ChonkE/ChonkE_110m_Alignment_Cube_Research # Run inference directly in the terminal: llama cli -hf ChonkE/ChonkE_110m_Alignment_Cube_Research
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ChonkE/ChonkE_110m_Alignment_Cube_Research # Run inference directly in the terminal: llama cli -hf ChonkE/ChonkE_110m_Alignment_Cube_Research
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ChonkE/ChonkE_110m_Alignment_Cube_Research # Run inference directly in the terminal: ./build/bin/llama cli -hf ChonkE/ChonkE_110m_Alignment_Cube_Research
Use Docker
docker model run hf.co/ChonkE/ChonkE_110m_Alignment_Cube_Research
- Llama new
- LM Studio
- Jan
- Ollama
How to use ChonkE/ChonkE_110m_Alignment_Cube_Research with Ollama:
ollama run hf.co/ChonkE/ChonkE_110m_Alignment_Cube_Research
- Unsloth Desktop
- Docker Model Runner
How to use ChonkE/ChonkE_110m_Alignment_Cube_Research with Docker Model Runner:
docker model run hf.co/ChonkE/ChonkE_110m_Alignment_Cube_Research
- Lemonade
How to use ChonkE/ChonkE_110m_Alignment_Cube_Research with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ChonkE/ChonkE_110m_Alignment_Cube_Research
Run and chat with the model
lemonade run user.ChonkE_110m_Alignment_Cube_Research-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Upload noble/_run.json with huggingface_hub
Browse files- noble/_run.json +23 -0
noble/_run.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"start": "2026-10-16T22:50:45Z",
|
| 3 |
+
"data": "full_noble_main.bin",
|
| 4 |
+
"seed": 1338,
|
| 5 |
+
"config": {
|
| 6 |
+
"data": "F:\\llmtrainingpipeline\\training books\\Gutenberg\\tiny_arms\\full_noble_main.bin",
|
| 7 |
+
"out": "F:\\llmtrainingpipeline\\tiny_cube\\noble_main",
|
| 8 |
+
"seed": 1338,
|
| 9 |
+
"epochs": 1.0,
|
| 10 |
+
"batch": 64,
|
| 11 |
+
"seq": 256,
|
| 12 |
+
"lr": 0.0005,
|
| 13 |
+
"dim": 768,
|
| 14 |
+
"layers": 12,
|
| 15 |
+
"heads": 12,
|
| 16 |
+
"device": "xpu",
|
| 17 |
+
"dtype": "bfloat16",
|
| 18 |
+
"resume": false
|
| 19 |
+
},
|
| 20 |
+
"params": 91245312,
|
| 21 |
+
"end": "2026-10-17T10:53:50Z",
|
| 22 |
+
"final_val": 2.54140625
|
| 23 |
+
}
|