Instructions to use FLvdW/Zeroth42-4B 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 FLvdW/Zeroth42-4B 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 FLvdW/Zeroth42-4B:Q4_K_M # Run inference directly in the terminal: llama cli -hf FLvdW/Zeroth42-4B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf FLvdW/Zeroth42-4B:Q4_K_M # Run inference directly in the terminal: llama cli -hf FLvdW/Zeroth42-4B:Q4_K_M
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 FLvdW/Zeroth42-4B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf FLvdW/Zeroth42-4B:Q4_K_M
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 FLvdW/Zeroth42-4B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf FLvdW/Zeroth42-4B:Q4_K_M
Use Docker
docker model run hf.co/FLvdW/Zeroth42-4B:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use FLvdW/Zeroth42-4B with Ollama:
ollama run hf.co/FLvdW/Zeroth42-4B:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use FLvdW/Zeroth42-4B with Docker Model Runner:
docker model run hf.co/FLvdW/Zeroth42-4B:Q4_K_M
- Lemonade
How to use FLvdW/Zeroth42-4B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull FLvdW/Zeroth42-4B:Q4_K_M
Run and chat with the model
lemonade run user.Zeroth42-4B-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload MANIFEST.txt with huggingface_hub
Browse files- MANIFEST.txt +11 -9
MANIFEST.txt
CHANGED
|
@@ -1,21 +1,23 @@
|
|
| 1 |
# Zeroth42-4B — release package manifest
|
| 2 |
-
# Generated: 2026-09-
|
| 3 |
# Model sha256: 4022f79f145afdb230388feff651a42d8448aa75bdfe142b5dc475d8a86243e3
|
| 4 |
|
| 5 |
## File hashes
|
| 6 |
-
|
|
|
|
| 7 |
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE
|
| 8 |
-
|
| 9 |
-
|
| 10 |
4022f79f145afdb230388feff651a42d8448aa75bdfe142b5dc475d8a86243e3 Zeroth42-4B-Q4_K_M.gguf
|
| 11 |
-
|
| 12 |
8b6caaab6b4897990beec2040758caf8c31580310e7589a4f797edecd16d403c chat_template.jinja
|
| 13 |
ec5afa5c17674e1ff2aa3fac15e9090cffa9604cb01719f9f9f163df832f69c7 config.json
|
| 14 |
-
|
| 15 |
2b96cd95d02c881fd32f35c8b5e9db975abed9df2885c438285fa019e84bdb02 eval/ootb-honest.json
|
| 16 |
c4345593b98d5c47dcd9c8dfc72c42d03a316080bf982733dc0474469939d71c eval/v4fixed-run1.json
|
| 17 |
c32a4c71876538546c7d5b0c6a2bc0f2aa9f122a88fa0f7a55bd9a7f8b8d9fd6 eval/v4fixed-run2.json
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
|
|
|
| 21 |
b2a5015ebda8ac85dd1e311964cce13d960a6ab90e32d9d8fa653327525d62e7 scripts/rung2_matrix.py
|
|
|
|
| 1 |
# Zeroth42-4B — release package manifest
|
| 2 |
+
# Generated: 2026-09-04 (pre-launch fix pass: codename scrub, self-contained repro scripts, base-model ID corrected)
|
| 3 |
# Model sha256: 4022f79f145afdb230388feff651a42d8448aa75bdfe142b5dc475d8a86243e3
|
| 4 |
|
| 5 |
## File hashes
|
| 6 |
+
|
| 7 |
+
bddaea006e8cf1c755ea4acec884d9c794afec9e47756a129137991a883ccf8e CLAIMS.md
|
| 8 |
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE
|
| 9 |
+
ec84bd05e204407583a4e837d62b19802c81b3d9ef4160536ad3e880d3caee60 MODEL_CARD.md
|
| 10 |
+
d37f79a45a889e10581afde23c1c9d7a955abbe5f3d6283ccc239426bb02cb7f README.md
|
| 11 |
4022f79f145afdb230388feff651a42d8448aa75bdfe142b5dc475d8a86243e3 Zeroth42-4B-Q4_K_M.gguf
|
| 12 |
+
760451078d765b4bf5a0db0e5e8ed991cfea8e43f72f186f4e0e558b4ff6f3be certification.md
|
| 13 |
8b6caaab6b4897990beec2040758caf8c31580310e7589a4f797edecd16d403c chat_template.jinja
|
| 14 |
ec5afa5c17674e1ff2aa3fac15e9090cffa9604cb01719f9f9f163df832f69c7 config.json
|
| 15 |
+
d72144d5237203580e04a08286799bfddff8f9c125cca9c54c1416bc497c6151 eval/golden-table-audit.md
|
| 16 |
2b96cd95d02c881fd32f35c8b5e9db975abed9df2885c438285fa019e84bdb02 eval/ootb-honest.json
|
| 17 |
c4345593b98d5c47dcd9c8dfc72c42d03a316080bf982733dc0474469939d71c eval/v4fixed-run1.json
|
| 18 |
c32a4c71876538546c7d5b0c6a2bc0f2aa9f122a88fa0f7a55bd9a7f8b8d9fd6 eval/v4fixed-run2.json
|
| 19 |
+
7da26b35a6b8c6ab135a9c4053cf1da7a83b23f6e3e8a75fe0ecd6feb3d40e91 hardware-matrix.md
|
| 20 |
+
7448c8ae4f99f291d3a4df556315b2f7fca01c867c9ceaf9591ed0015f9bdd7c scripts/guardrail_rules.py
|
| 21 |
+
0f63e6689078b319569004c7dbacd62d1acfaec30df1ef7468ed078e18a4fbe6 scripts/rules.json
|
| 22 |
+
937c3ded572714aaccc8336c94fc3e5826a3e61f520612fafccbf62d5f676455 scripts/rung1_certify.py
|
| 23 |
b2a5015ebda8ac85dd1e311964cce13d960a6ab90e32d9d8fa653327525d62e7 scripts/rung2_matrix.py
|