Instructions to use DuoNeural/CrystalCall-v5-DCG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DuoNeural/CrystalCall-v5-DCG with Transformers:

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

pipe = pipeline("text-generation", model="DuoNeural/CrystalCall-v5-DCG")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import DCGCrystalCallV5
model = DCGCrystalCallV5.from_pretrained("DuoNeural/CrystalCall-v5-DCG", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use DuoNeural/CrystalCall-v5-DCG 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 DuoNeural/CrystalCall-v5-DCG:Q8_0
# Run inference directly in the terminal:
llama cli -hf DuoNeural/CrystalCall-v5-DCG:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DuoNeural/CrystalCall-v5-DCG:Q8_0
# Run inference directly in the terminal:
llama cli -hf DuoNeural/CrystalCall-v5-DCG:Q8_0

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 DuoNeural/CrystalCall-v5-DCG:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf DuoNeural/CrystalCall-v5-DCG:Q8_0

Use Docker

docker model run hf.co/DuoNeural/CrystalCall-v5-DCG:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use DuoNeural/CrystalCall-v5-DCG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DuoNeural/CrystalCall-v5-DCG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DuoNeural/CrystalCall-v5-DCG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DuoNeural/CrystalCall-v5-DCG:Q8_0

SGLang

How to use DuoNeural/CrystalCall-v5-DCG 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 "DuoNeural/CrystalCall-v5-DCG" \
    --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": "DuoNeural/CrystalCall-v5-DCG",
		"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 "DuoNeural/CrystalCall-v5-DCG" \
        --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": "DuoNeural/CrystalCall-v5-DCG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use DuoNeural/CrystalCall-v5-DCG with Ollama:
```
ollama run hf.co/DuoNeural/CrystalCall-v5-DCG:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use DuoNeural/CrystalCall-v5-DCG with Docker Model Runner:
```
docker model run hf.co/DuoNeural/CrystalCall-v5-DCG:Q8_0
```

Lemonade

How to use DuoNeural/CrystalCall-v5-DCG with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DuoNeural/CrystalCall-v5-DCG:Q8_0

Run and chat with the model

lemonade run user.CrystalCall-v5-DCG-Q8_0

List all available models

lemonade list

Atomic Chat

CrystalCall-v5-DCG

File size: 632 Bytes

3c3c6df

{
  "architectures": [
    "DCGCrystalCallV5"
  ],
  "model_type": "cdm_moe_poincare_dcg",
  "d_model": 768,
  "n_layers": 7,
  "n_heads": 12,
  "K": 8,
  "num_experts": 4,
  "d_ff": 768,
  "max_seq": 512,
  "vocab_size": 32256,
  "geometry": "poincare",
  "curvature": 1.4427,
  "gate_layer": 5,
  "n_classes": 3,
  "card_head_hidden": 4,
  "card_head_params": 3843,
  "total_params": 116091395,
  "cardinality_accuracy_pct": 98.5,
  "cardinality_parallel_acc_pct": 100.0,
  "cardinality_single_acc_pct": 97.06,
  "best_val_bpb": 0.0659,
  "teacher": "Salesforce/xLAM-1b-fc-r",
  "dataset": "Salesforce/xlam-function-calling-60k"
}