Instructions to use SciPhi/Triplex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SciPhi/Triplex with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SciPhi/Triplex", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SciPhi/Triplex", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SciPhi/Triplex", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use SciPhi/Triplex with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SciPhi/Triplex",
	filename="quantized_model-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SciPhi/Triplex with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SciPhi/Triplex:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SciPhi/Triplex:Q4_K_M

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 SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SciPhi/Triplex:Q4_K_M

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 SciPhi/Triplex:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SciPhi/Triplex:Q4_K_M

Use Docker

docker model run hf.co/SciPhi/Triplex:Q4_K_M

LM Studio
Jan

vLLM

How to use SciPhi/Triplex with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SciPhi/Triplex"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SciPhi/Triplex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SciPhi/Triplex:Q4_K_M

SGLang

How to use SciPhi/Triplex 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 "SciPhi/Triplex" \
    --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": "SciPhi/Triplex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "SciPhi/Triplex" \
        --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": "SciPhi/Triplex",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SciPhi/Triplex with Ollama:
```
ollama run hf.co/SciPhi/Triplex:Q4_K_M
```

Unsloth Studio new

How to use SciPhi/Triplex with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SciPhi/Triplex to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SciPhi/Triplex to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SciPhi/Triplex to start chatting

Docker Model Runner
How to use SciPhi/Triplex with Docker Model Runner:
```
docker model run hf.co/SciPhi/Triplex:Q4_K_M
```

Lemonade

How to use SciPhi/Triplex with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SciPhi/Triplex:Q4_K_M

Run and chat with the model

lemonade run user.Triplex-Q4_K_M

List all available models

lemonade list

add AIBOM

by RiccardoDav - opened Sep 23, 2025

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

+60

-0

Files changed (1) hide show

SciPhi_Triplex.json +60 -0

SciPhi_Triplex.json ADDED Viewed

	@@ -0,0 +1,60 @@

+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:4e32b58a-e73a-4dfb-95d5-48a058070727",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-07-14T10:38:07.802424+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "SciPhi/Triplex-fc753e69-381d-5d82-9b45-a116ddfa0201",
+            "name": "SciPhi/Triplex",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/SciPhi/Triplex",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "text-generation",
+                    "architectureFamily": "phi3",
+                    "modelArchitecture": "Phi3ForCausalLM"
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "SciPhi"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "CC-BY-NC-SA-4.0",
+                        "url": "https://spdx.org/licenses/CC-BY-NC-SA-4.0.html"
+                    }
+                }
+            ],
+            "tags": [
+                "transformers",
+                "safetensors",
+                "gguf",
+                "phi3",
+                "text-generation",
+                "conversational",
+                "custom_code",
+                "license:cc-by-nc-sa-4.0",
+                "autotrain_compatible",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    }
+}