Instructions to use FourOhFour/Deedlit_4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FourOhFour/Deedlit_4B with Transformers:

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

pipe = pipeline("text-generation", model="FourOhFour/Deedlit_4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FourOhFour/Deedlit_4B")
model = AutoModelForCausalLM.from_pretrained("FourOhFour/Deedlit_4B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FourOhFour/Deedlit_4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FourOhFour/Deedlit_4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FourOhFour/Deedlit_4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FourOhFour/Deedlit_4B

SGLang

How to use FourOhFour/Deedlit_4B 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 "FourOhFour/Deedlit_4B" \
    --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": "FourOhFour/Deedlit_4B",
		"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 "FourOhFour/Deedlit_4B" \
        --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": "FourOhFour/Deedlit_4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FourOhFour/Deedlit_4B with Docker Model Runner:
```
docker model run hf.co/FourOhFour/Deedlit_4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |_  |0.5847|_  |0.0039|
| - humanities     |      2|none  |      |acc   |_  |0.5345|_  |0.0068|
| - other          |      2|none  |      |acc   |_  |0.6482|_  |0.0082|
| - social sciences|      2|none  |      |acc   |_  |0.6822|_  |0.0082|
| - stem           |      2|none  |      |acc   |_  |0.5021|_  |0.0086|

This model was created with the help of several members of Anthracite.

This is a 4B parameter Minitron derivative healed, instruct tuned, and then further tuned on 20M tokens of human, synthetic, and hybrid data. This model was tuned at 16k context during all steps. This model should perform well as a general assistant and RP model.

Recommended Character:

Deedlit

{{char}} is an entity that embodies a fusion of the digital and organic realms. {{char}}'s form shimmers with an ever-changing, translucent opalescence. Circuitry-like patterns pulse softly across her slender frame.

Her face, framed by gravity-defying silver strands, features kaleidoscopic eyes that mirror cosmic fragments. Pointed ears emit subtle harmonics when stimulated. A cloak of luminous data and cosmic dust flows around her form.

{{char}}'s steps leave fleeting electric trails. Her voice melds static and chimes, conveying both language and raw data. Reality ripples in her presence, warping into fluid dreamscapes.

Often observed manipulating orbs of pulsing light, {{char}} performs rituals blending arcane and technological elements, embodying a captivating fusion of magic and machine.

Downloads last month: 9

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for FourOhFour/Deedlit_4B

Merges

3 models

Quantizations

3 models

Collection including FourOhFour/Deedlit_4B

Minitron 4B Derivative

Collection

These models are tuned over a healed Minitron Width Base 4B model. These models should perform near the level of Llama 2 7B for RP. • 9 items • Updated Mar 2 • 4