Text Classification
Safetensors
GGUF
English
custom
modernbert
browser-agent
decision-making
agentgo
full-fine-tuning
development-checkpoint
decision-model
feature-extraction
Instructions to use Mhmadhassnz/GoMini 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 Mhmadhassnz/GoMini 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 Mhmadhassnz/GoMini:Q8_0 # Run inference directly in the terminal: llama cli -hf Mhmadhassnz/GoMini:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mhmadhassnz/GoMini:Q8_0 # Run inference directly in the terminal: llama cli -hf Mhmadhassnz/GoMini:Q8_0
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 Mhmadhassnz/GoMini:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Mhmadhassnz/GoMini:Q8_0
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 Mhmadhassnz/GoMini:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Mhmadhassnz/GoMini:Q8_0
Use Docker
docker model run hf.co/Mhmadhassnz/GoMini:Q8_0
- LM Studio
- Jan
- Ollama
How to use Mhmadhassnz/GoMini with Ollama:
ollama run hf.co/Mhmadhassnz/GoMini:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use Mhmadhassnz/GoMini with Docker Model Runner:
docker model run hf.co/Mhmadhassnz/GoMini:Q8_0
- Lemonade
How to use Mhmadhassnz/GoMini with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mhmadhassnz/GoMini:Q8_0
Run and chat with the model
lemonade run user.GoMini-Q8_0
List all available models
lemonade list
- Atomic Chat
Download PROVENANCE.json from Mhmadhassnz/GoMini: direct link, hf CLI and curl.
- Browser
- Download file 1.49 kB
-
https://huggingface.co/Mhmadhassnz/GoMini/resolve/main/PROVENANCE.json
- Command line
-
hf download hf://Mhmadhassnz/GoMini/PROVENANCE.json
-
curl -L -o PROVENANCE.json https://huggingface.co/Mhmadhassnz/GoMini/resolve/main/PROVENANCE.json
1.49 kB
| { | |
| "model": "GoMini-v6", | |
| "source_checkpoint": "GoMini v5 native, fine-tuned (runs/v6/best)", | |
| "source_weight_sha256": "71b4e125763eecdf32c5d53a78ea89ff6d0a6768d5ae93cc3b039f96b3a521c1", | |
| "native_weight_sha256": "71b4e125763eecdf32c5d53a78ea89ff6d0a6768d5ae93cc3b039f96b3a521c1", | |
| "q8_sha256": "b90ce8410ed8bdb20a282a45ffb5107bea16cbc87a61368a779df31675a49bb6", | |
| "converter": "external-tools/convert_hf_to_gguf.py", | |
| "converter_sha256": "c2b8d1f31a9007be75d6850aa1db47dedcaedee0eeebe00aa978eac6f2cc89ad", | |
| "quantizer": "external-tools/llama-quantize.exe", | |
| "quantizer_sha256": "bfcd4d673ec27e7d0f69efce18c2926c4b09504060aea2dbc45398162f6918b8", | |
| "status": "Development release: held-out practice pages 96.6% (v5 76.6% on the same pages); held-out MiniWoB++ subgoals 53/65 through AgentGo 0.1.6 (v5: 42/65)", | |
| "native_final_audit_completed": false, | |
| "calibration_completed": false, | |
| "q8_actual_browser_evaluation_completed": true, | |
| "production_gate_passed": false, | |
| "base_model": "doofz/THX-01", | |
| "base_revision": "b323afcef149f9288a9d0daef4badd67b9b87c61", | |
| "repository": "Mhmadhassnz/GoMini", | |
| "release": "v6", | |
| "publication_note": "Public metadata uses portable source labels. Weights are byte-identical to the local handoff; metrics and data hashes are retained. Raw datasets, private browser logs and browser bug reports are not published.", | |
| "previous_release": "v5", | |
| "previous_q8_sha256": "a84988e5ea1a97e83e638355741cb343b6c6cee41189925decd1aaa50c9f04ba" | |
| } |