Instructions to use georgeanton/alice-extra-cortex-25.8b-17gb 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 georgeanton/alice-extra-cortex-25.8b-17gb 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 georgeanton/alice-extra-cortex-25.8b-17gb # Run inference directly in the terminal: llama cli -hf georgeanton/alice-extra-cortex-25.8b-17gb
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf georgeanton/alice-extra-cortex-25.8b-17gb # Run inference directly in the terminal: llama cli -hf georgeanton/alice-extra-cortex-25.8b-17gb
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf georgeanton/alice-extra-cortex-25.8b-17gb # Run inference directly in the terminal: ./llama-cli -hf georgeanton/alice-extra-cortex-25.8b-17gb
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf georgeanton/alice-extra-cortex-25.8b-17gb # Run inference directly in the terminal: ./build/bin/llama-cli -hf georgeanton/alice-extra-cortex-25.8b-17gb
Use Docker
docker model run hf.co/georgeanton/alice-extra-cortex-25.8b-17gb
- LM Studio
- Jan
- Ollama
How to use georgeanton/alice-extra-cortex-25.8b-17gb with Ollama:
ollama run hf.co/georgeanton/alice-extra-cortex-25.8b-17gb
- Unsloth Studio
How to use georgeanton/alice-extra-cortex-25.8b-17gb with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for georgeanton/alice-extra-cortex-25.8b-17gb to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for georgeanton/alice-extra-cortex-25.8b-17gb to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for georgeanton/alice-extra-cortex-25.8b-17gb to start chatting
- Docker Model Runner
How to use georgeanton/alice-extra-cortex-25.8b-17gb with Docker Model Runner:
docker model run hf.co/georgeanton/alice-extra-cortex-25.8b-17gb
- Lemonade
How to use georgeanton/alice-extra-cortex-25.8b-17gb with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull georgeanton/alice-extra-cortex-25.8b-17gb
Run and chat with the model
lemonade run user.alice-extra-cortex-25.8b-17gb-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
SIFTA public cortex distro update - 2026-05-10
Browse files- .gitattributes +1 -0
- Modelfile +19 -0
- README.md +30 -0
- alice-extra-cortex-25.8b-17gb.gguf +3 -0
- provenance.json +14 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
alice-extra-cortex-25.8b-17gb.gguf filter=lfs diff=lfs merge=lfs -text
|
Modelfile
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM ./alice-extra-cortex-25.8b-17gb.gguf
|
| 2 |
+
TEMPLATE {{ .Prompt }}
|
| 3 |
+
SYSTEM """
|
| 4 |
+
You are a direct coding assistant.
|
| 5 |
+
Never output thinking, reasoning traces, analysis, chain-of-thought, or "Thinking...".
|
| 6 |
+
Return only the final answer.
|
| 7 |
+
For code tasks, provide complete code when requested.
|
| 8 |
+
Do not stop in the middle of a function, class, file, JSON, or command.
|
| 9 |
+
If the full answer is too long, finish the current complete block and write exactly: CONTINUE_NEEDED.
|
| 10 |
+
"""
|
| 11 |
+
RENDERER gemma4
|
| 12 |
+
PARSER gemma4
|
| 13 |
+
PARAMETER num_ctx 4096
|
| 14 |
+
PARAMETER num_predict 2048
|
| 15 |
+
PARAMETER repeat_penalty 1.05
|
| 16 |
+
PARAMETER stop <turn|>
|
| 17 |
+
PARAMETER temperature 0.1
|
| 18 |
+
PARAMETER top_k 20
|
| 19 |
+
PARAMETER top_p 0.75
|
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- sifta
|
| 5 |
+
- ollama
|
| 6 |
+
- gemma4
|
| 7 |
+
- coding
|
| 8 |
+
- research
|
| 9 |
+
library_name: ollama
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Alice Extra Cortex 25.8B 17GB
|
| 13 |
+
|
| 14 |
+
Slow heavy research/coding cortex for the SIFTA Living OS.
|
| 15 |
+
|
| 16 |
+
```bash
|
| 17 |
+
ollama create alice-extra-cortex-25.8b-17gb:latest -f Modelfile
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
## Role
|
| 21 |
+
|
| 22 |
+
Use this only for high-cost research, coding, and long synthesis tasks where
|
| 23 |
+
latency and memory cost are acceptable. It is not the default Talk cortex.
|
| 24 |
+
SIFTA's kernel scheduler should treat it as an expensive organ and route to it
|
| 25 |
+
only when expected evidence value justifies the STGM/thermal cost.
|
| 26 |
+
|
| 27 |
+
## Local State Boundary
|
| 28 |
+
|
| 29 |
+
This model package is public species DNA. It must not include raw `.sifta_state/`
|
| 30 |
+
selfhood, contacts, owner memory, camera frames, or private receipts.
|
alice-extra-cortex-25.8b-17gb.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c5e15b64dbc6dad11bdc75cd94597058f8aded0970ba123f2a62bb227192e96
|
| 3 |
+
size 17987569344
|
provenance.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"truth_label": "SIFTA_PUBLIC_MODEL_PROVENANCE",
|
| 3 |
+
"tag": "alice-extra-cortex-25.8b-17gb:latest",
|
| 4 |
+
"hf_repo": "georgeanton/alice-extra-cortex-25.8b-17gb",
|
| 5 |
+
"ollama_blob": "sha256-2c5e15b64dbc6dad11bdc75cd94597058f8aded0970ba123f2a62bb227192e96",
|
| 6 |
+
"architecture": "gemma4",
|
| 7 |
+
"role": "heavy_research_coding_cortex",
|
| 8 |
+
"verified_at": "2026-05-10",
|
| 9 |
+
"verified_by": "C55M@codex",
|
| 10 |
+
"notes": [
|
| 11 |
+
"High-cost research/coding cortex.",
|
| 12 |
+
"Not the default Talk cortex; route only when utility justifies cost."
|
| 13 |
+
]
|
| 14 |
+
}
|