Text Generation
GGUF
French
quantitative-finance
french
llama.cpp
tool-use
deterministic-engine
conversational
Instructions to use gptradeinvest/sigmaquant-copilot 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 gptradeinvest/sigmaquant-copilot 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 gptradeinvest/sigmaquant-copilot:Q4_K_M # Run inference directly in the terminal: llama cli -hf gptradeinvest/sigmaquant-copilot:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf gptradeinvest/sigmaquant-copilot:Q4_K_M # Run inference directly in the terminal: llama cli -hf gptradeinvest/sigmaquant-copilot:Q4_K_M
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 gptradeinvest/sigmaquant-copilot:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf gptradeinvest/sigmaquant-copilot:Q4_K_M
Use Docker
docker model run hf.co/gptradeinvest/sigmaquant-copilot:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use gptradeinvest/sigmaquant-copilot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gptradeinvest/sigmaquant-copilot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gptradeinvest/sigmaquant-copilot", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/gptradeinvest/sigmaquant-copilot:Q4_K_M
- Ollama
How to use gptradeinvest/sigmaquant-copilot with Ollama:
ollama run hf.co/gptradeinvest/sigmaquant-copilot:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use gptradeinvest/sigmaquant-copilot with Docker Model Runner:
docker model run hf.co/gptradeinvest/sigmaquant-copilot:Q4_K_M
- Lemonade
How to use gptradeinvest/sigmaquant-copilot with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull gptradeinvest/sigmaquant-copilot:Q4_K_M
Run and chat with the model
lemonade run user.sigmaquant-copilot-Q4_K_M
List all available models
lemonade list
- Atomic Chat
|
Download README.md from gptradeinvest/sigmaquant-copilot: direct link, hf CLI and curl.
- Browser
- Download file 1.94 kB
-
https://huggingface.co/gptradeinvest/sigmaquant-copilot/resolve/main/README.md
- Command line
-
hf download hf://gptradeinvest/sigmaquant-copilot/README.md
-
curl -L -o README.md https://huggingface.co/gptradeinvest/sigmaquant-copilot/resolve/main/README.md
1.94 kB
| license: apache-2.0 | |
| language: | |
| - fr | |
| library_name: gguf | |
| pipeline_tag: text-generation | |
| tags: | |
| - quantitative-finance | |
| - french | |
| - gguf | |
| - llama.cpp | |
| - tool-use | |
| - deterministic-engine | |
| # SigmaQuant Copilot — SQSL 2.0 (GGUF) | |
| Modèle de **copilote quantitatif en français** (~4 milliards de paramètres), quantifié | |
| **Q4_K_M** pour `llama.cpp`. Il route chaque question vers la bonne méthode financière et | |
| **délègue tout calcul exact à un moteur déterministe** via un bloc ` ```engine ` — il ne fait | |
| jamais d'arithmétique lui-même, donc les nombres renvoyés par l'application sont exacts et | |
| auditables. | |
| - **Fichier** : `sqsl-2.0-Q4_K_M.gguf` | |
| - **Format** : GGUF (quantification Q4_K_M) | |
| - **Runtime** : `llama-server` (llama.cpp), template de chat ChatML | |
| - **App de référence** : https://github.com/Gaetan-PRUVOT-SQS/sigmaquant-copilot (app macOS native SwiftUI, 100 % locale) | |
| ## Utilisation (llama.cpp) | |
| ```bash | |
| hf download gptradeinvest/sigmaquant-copilot sqsl-2.0-Q4_K_M.gguf --local-dir models | |
| llama-server -m models/sqsl-2.0-Q4_K_M.gguf --chat-template chatml -c 4096 -ngl 999 | |
| ``` | |
| Envoyez toujours le prompt système fourni avec l'application. Le modèle émet un bloc | |
| ` ```engine {module, function, params} ` que le moteur déterministe exécute pour produire le | |
| nombre final. | |
| ## Modules couverts | |
| - **01 — Fondations** : Black-Scholes, parité put-call, forwards, binomial risque-neutre, rente perpétuelle | |
| - **02 — Crédit & structure par terme** : spread CDS au pair, treillis ZC, crédit amortissable, hasard/survie | |
| - **03 — Portefeuille & exécution** : MEDAF, Sharpe, exécution optimale Almgren-Chriss | |
| - **04 — Pricing avancé** : grecques (delta), densité de Breeden-Litzenberger, perte de tranche CDO | |
| - **05 — Calcul** : pricing FFT Carr-Madan, calibration de modèles, ajustement Vasicek | |
| ## Licence | |
| Apache 2.0. Ne constitue pas un conseil en investissement. © 2026 SigmaQuantSystems. | |