GGUF
Spanish
English
deepseek_v2
moderno-tech
nova
nova-coder
quantized
code-generation
local-ai
custom_code
conversational
Instructions to use ModernoTech/Nova-Coder 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 ModernoTech/Nova-Coder 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 ModernoTech/Nova-Coder:Q4_K_M # Run inference directly in the terminal: llama cli -hf ModernoTech/Nova-Coder:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ModernoTech/Nova-Coder:Q4_K_M # Run inference directly in the terminal: llama cli -hf ModernoTech/Nova-Coder: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 ModernoTech/Nova-Coder:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ModernoTech/Nova-Coder:Q4_K_M
Use Docker
docker model run hf.co/ModernoTech/Nova-Coder:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use ModernoTech/Nova-Coder with Ollama:
ollama run hf.co/ModernoTech/Nova-Coder:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use ModernoTech/Nova-Coder with Docker Model Runner:
docker model run hf.co/ModernoTech/Nova-Coder:Q4_K_M
- Lemonade
How to use ModernoTech/Nova-Coder with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ModernoTech/Nova-Coder:Q4_K_M
Run and chat with the model
lemonade run user.Nova-Coder-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Remove visible manufacturer reference from public Model Card; hidden compatibility identifiers remain external
Browse files
README.md
CHANGED
|
@@ -62,7 +62,7 @@ Todos los nombres son identificadores Nova y se almacenan directamente en este r
|
|
| 62 |
|
| 63 |
## Arquitectura
|
| 64 |
|
| 65 |
-
|
| 66 |
- Tipo: Mixture-of-Experts (MoE)
|
| 67 |
- Parámetros totales: aproximadamente 16B
|
| 68 |
- Parámetros activos por token: aproximadamente 2.4B
|
|
|
|
| 62 |
|
| 63 |
## Arquitectura
|
| 64 |
|
| 65 |
+
| Arquitectura | Clase heredada de compatibilidad para MoE orientada a código especializado |
|
| 66 |
- Tipo: Mixture-of-Experts (MoE)
|
| 67 |
- Parámetros totales: aproximadamente 16B
|
| 68 |
- Parámetros activos por token: aproximadamente 2.4B
|