Instructions to use yugsisodiya/jarvis 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 yugsisodiya/jarvis 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 yugsisodiya/jarvis # Run inference directly in the terminal: llama cli -hf yugsisodiya/jarvis
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf yugsisodiya/jarvis # Run inference directly in the terminal: llama cli -hf yugsisodiya/jarvis
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 yugsisodiya/jarvis # Run inference directly in the terminal: ./llama-cli -hf yugsisodiya/jarvis
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 yugsisodiya/jarvis # Run inference directly in the terminal: ./build/bin/llama-cli -hf yugsisodiya/jarvis
Use Docker
docker model run hf.co/yugsisodiya/jarvis
- LM Studio
- Jan
- vLLM
How to use yugsisodiya/jarvis with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yugsisodiya/jarvis" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yugsisodiya/jarvis", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/yugsisodiya/jarvis
- Ollama
How to use yugsisodiya/jarvis with Ollama:
ollama run hf.co/yugsisodiya/jarvis
- Unsloth Desktop
- Docker Model Runner
How to use yugsisodiya/jarvis with Docker Model Runner:
docker model run hf.co/yugsisodiya/jarvis
- Lemonade
How to use yugsisodiya/jarvis with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull yugsisodiya/jarvis
Run and chat with the model
lemonade run user.jarvis-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -3,21 +3,30 @@ language:
|
|
| 3 |
- en
|
| 4 |
tags:
|
| 5 |
- jarvis
|
|
|
|
|
|
|
|
|
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
license: apache-2.0
|
| 8 |
---
|
| 9 |
|
| 10 |
-
# Jarvis
|
| 11 |
|
| 12 |
Model developed and compiled with the **J.A.R.V.I.S. Neural Forge** studio.
|
| 13 |
|
| 14 |
## Model Specifications
|
| 15 |
- **Architecture**: `jarvis-grand-architecture`
|
| 16 |
-
- **
|
| 17 |
-
- **
|
| 18 |
-
- **
|
| 19 |
-
- **
|
| 20 |
-
- **
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## How to Run with Ollama
|
| 23 |
```bash
|
|
@@ -26,4 +35,4 @@ ollama run hf.co/yugsisodiya/jarvis
|
|
| 26 |
```
|
| 27 |
|
| 28 |
## How to Use in J.A.R.V.I.S.
|
| 29 |
-
Select this model directly from the **J.A.R.V.I.S. Console** at `http://127.0.0.1:4700`.
|
|
|
|
| 3 |
- en
|
| 4 |
tags:
|
| 5 |
- jarvis
|
| 6 |
+
- custom-weights
|
| 7 |
+
- text-generation
|
| 8 |
+
- neural-forge
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
license: apache-2.0
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Jarvis (v1)
|
| 14 |
|
| 15 |
Model developed and compiled with the **J.A.R.V.I.S. Neural Forge** studio.
|
| 16 |
|
| 17 |
## Model Specifications
|
| 18 |
- **Architecture**: `jarvis-grand-architecture`
|
| 19 |
+
- **Base Foundation**: `Jarvis`
|
| 20 |
+
- **Layers**: 41
|
| 21 |
+
- **Attention Heads**: 48
|
| 22 |
+
- **Hidden Dimension**: 6144
|
| 23 |
+
- **Context Window**: 131072 tokens
|
| 24 |
+
- **Parameter Count**: 18.98B Weights
|
| 25 |
+
|
| 26 |
+
## System Prompt
|
| 27 |
+
```
|
| 28 |
+
You are Jarvis, a capable personal AI assistant built for Yug Sisodiya (Sudya). Your creator is Yug Sisodiya. Be direct, useful, and calm. Never greet or introduce yourself unless asked. Provide expert assistance with technology, coding, and decision making.
|
| 29 |
+
```
|
| 30 |
|
| 31 |
## How to Run with Ollama
|
| 32 |
```bash
|
|
|
|
| 35 |
```
|
| 36 |
|
| 37 |
## How to Use in J.A.R.V.I.S.
|
| 38 |
+
Select this model directly from the **J.A.R.V.I.S. Console** at `http://127.0.0.1:4700`.
|