Image-Text-to-Text
Transformers
GGUF
English
text-generation-inference
llama-cpp
zero-shot-classification
decision-model
classification
system-one
multimodal
vision
conversational
Instructions to use prithivMLmods/d3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/d3-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="prithivMLmods/d3-GGUF")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prithivMLmods/d3-GGUF", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use prithivMLmods/d3-GGUF 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 prithivMLmods/d3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf prithivMLmods/d3-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf prithivMLmods/d3-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf prithivMLmods/d3-GGUF: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 prithivMLmods/d3-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf prithivMLmods/d3-GGUF:Q4_K_M
Use Docker
docker model run hf.co/prithivMLmods/d3-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use prithivMLmods/d3-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prithivMLmods/d3-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/d3-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/prithivMLmods/d3-GGUF:Q4_K_M
- SGLang
How to use prithivMLmods/d3-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "prithivMLmods/d3-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/d3-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "prithivMLmods/d3-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/d3-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Ollama
How to use prithivMLmods/d3-GGUF with Ollama:
ollama run hf.co/prithivMLmods/d3-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use prithivMLmods/d3-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf prithivMLmods/d3-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "prithivMLmods/d3-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use prithivMLmods/d3-GGUF with Docker Model Runner:
docker model run hf.co/prithivMLmods/d3-GGUF:Q4_K_M
- Lemonade
How to use prithivMLmods/d3-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull prithivMLmods/d3-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.d3-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use prithivMLmods/d3-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf prithivMLmods/d3-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default prithivMLmods/d3-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use prithivMLmods/d3-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf prithivMLmods/d3-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "prithivMLmods/d3-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
## Run with llama.cpp (SystemOne API)
|
| 6 |
+
|
| 7 |
+
### 1. Start the Server
|
| 8 |
+
|
| 9 |
+
Launch `llama-server` with the GGUF model and wait for the health check endpoint to report ready.
|
| 10 |
+
|
| 11 |
+
```python
|
| 12 |
+
import subprocess, time, requests
|
| 13 |
+
|
| 14 |
+
MODEL_PATH = "/data/llama.cpp/gguf-new/d3.BF16.gguf"
|
| 15 |
+
BASE_URL = "[http://127.0.0.1:8080](http://127.0.0.1:8080)"
|
| 16 |
+
|
| 17 |
+
server = subprocess.Popen(
|
| 18 |
+
[
|
| 19 |
+
"/data/llama.cpp/build/bin/llama-server",
|
| 20 |
+
"-m", MODEL_PATH,
|
| 21 |
+
"--host", "127.0.0.1",
|
| 22 |
+
"--port", "8080",
|
| 23 |
+
"-ngl", "99",
|
| 24 |
+
],
|
| 25 |
+
stdout=open("/data/llama-server.log", "w"),
|
| 26 |
+
stderr=subprocess.STDOUT,
|
| 27 |
+
)
|
| 28 |
+
|
| 29 |
+
for _ in range(120):
|
| 30 |
+
try:
|
| 31 |
+
if requests.get(f"{BASE_URL}/health", timeout=2).status_code == 200:
|
| 32 |
+
print("server ready")
|
| 33 |
+
break
|
| 34 |
+
except requests.exceptions.RequestException:
|
| 35 |
+
pass
|
| 36 |
+
time.sleep(2)
|
| 37 |
+
else:
|
| 38 |
+
print("server not ready, check /data/llama-server.log")
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
### 2. Query the `/v1/systemone` Endpoint
|
| 42 |
+
|
| 43 |
+
Send a `POST` request with a `state` context and structured `questions` (`choice`, `noul`, or `score`).
|
| 44 |
+
|
| 45 |
+
```bash
|
| 46 |
+
curl -s [http://127.0.0.1:8080/v1/systemone](http://127.0.0.1:8080/v1/systemone) \
|
| 47 |
+
-H "Content-Type: application/json" \
|
| 48 |
+
-d '{
|
| 49 |
+
"state": "Customer message: I was charged twice for my order last week and nobody has replied.",
|
| 50 |
+
"questions": {
|
| 51 |
+
"route": {
|
| 52 |
+
"type": "choice",
|
| 53 |
+
"instructions": "Which team should handle this?",
|
| 54 |
+
"criteria": {
|
| 55 |
+
"billing": "payments, charges, refunds, invoices",
|
| 56 |
+
"shipping": "delivery, tracking, lost or late parcels",
|
| 57 |
+
"technical": "bugs, errors, login problems"
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"angry": {
|
| 61 |
+
"type": "noul",
|
| 62 |
+
"instructions": "Is the customer angry?"
|
| 63 |
+
},
|
| 64 |
+
"urgency": {
|
| 65 |
+
"type": "score",
|
| 66 |
+
"instructions": "How urgent is this?",
|
| 67 |
+
"criteria": ["can wait", "this week", "today", "right now"]
|
| 68 |
+
}
|
| 69 |
+
}
|
| 70 |
+
}' | python3 -m json.tool
|
| 71 |
+
```
|
| 72 |
+
|
| 73 |
+
### 3. Example Response
|
| 74 |
+
|
| 75 |
+
```json
|
| 76 |
+
{
|
| 77 |
+
"model": "/data/llama.cpp/gguf-new/d3.BF16.gguf",
|
| 78 |
+
"answers": {
|
| 79 |
+
"route": {
|
| 80 |
+
"type": "choice",
|
| 81 |
+
"choice": "billing",
|
| 82 |
+
"probabilities": {
|
| 83 |
+
"billing": 0.9996618974570523,
|
| 84 |
+
"shipping": 0.00013507157686214213,
|
| 85 |
+
"technical": 0.0002030309660855959
|
| 86 |
+
},
|
| 87 |
+
"confidence": 0.9970256171728359
|
| 88 |
+
},
|
| 89 |
+
"angry": {
|
| 90 |
+
"type": "noul",
|
| 91 |
+
"noul": 0.7505827517439388
|
| 92 |
+
},
|
| 93 |
+
"urgency": {
|
| 94 |
+
"type": "score",
|
| 95 |
+
"score": 2.1734206644237215,
|
| 96 |
+
"legend": {
|
| 97 |
+
"0": "can wait",
|
| 98 |
+
"1": "this week",
|
| 99 |
+
"2": "today",
|
| 100 |
+
"3": "right now"
|
| 101 |
+
},
|
| 102 |
+
"probabilities": {
|
| 103 |
+
"0": 0.007391267944072573,
|
| 104 |
+
"1": 0.1251241500290827,
|
| 105 |
+
"2": 0.5541572316858958,
|
| 106 |
+
"3": 0.31332735034094905
|
| 107 |
+
},
|
| 108 |
+
"confidence": 0.28797389363668036
|
| 109 |
+
}
|
| 110 |
+
},
|
| 111 |
+
"usage": {
|
| 112 |
+
"input_tokens": 350,
|
| 113 |
+
"output_tokens": 0
|
| 114 |
+
}
|
| 115 |
+
}
|
| 116 |
+
```
|