Instructions to use ZeroXClem/L3-Aspire-Heart-Matrix-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZeroXClem/L3-Aspire-Heart-Matrix-8B with Transformers:

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

pipe = pipeline("text-generation", model="ZeroXClem/L3-Aspire-Heart-Matrix-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZeroXClem/L3-Aspire-Heart-Matrix-8B")
model = AutoModelForCausalLM.from_pretrained("ZeroXClem/L3-Aspire-Heart-Matrix-8B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZeroXClem/L3-Aspire-Heart-Matrix-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZeroXClem/L3-Aspire-Heart-Matrix-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZeroXClem/L3-Aspire-Heart-Matrix-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZeroXClem/L3-Aspire-Heart-Matrix-8B

SGLang

How to use ZeroXClem/L3-Aspire-Heart-Matrix-8B 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 "ZeroXClem/L3-Aspire-Heart-Matrix-8B" \
    --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": "ZeroXClem/L3-Aspire-Heart-Matrix-8B",
		"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 "ZeroXClem/L3-Aspire-Heart-Matrix-8B" \
        --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": "ZeroXClem/L3-Aspire-Heart-Matrix-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZeroXClem/L3-Aspire-Heart-Matrix-8B with Docker Model Runner:
```
docker model run hf.co/ZeroXClem/L3-Aspire-Heart-Matrix-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ZeroXClem/L3-Aspire-Heart-Matrix-8B

ZeroXClem/L3-Aspire-Heart-Matrix-8B is an experimental language model crafted by merging three high-quality 8B parameter models using the Model Stock Merge method. This synthesis leverages the unique strengths of Aspire, Heart Stolen, and CursedMatrix, creating a highly versatile and robust language model for a wide array of tasks.

🌟 Model Details

Name: ZeroXClem/L3-Aspire-Heart-Matrix-8B
Base Model: Khetterman/CursedMatrix-8B-v9
Merge Method: Model Stock
Parameter Count: 8 billion
Precision: bfloat16

📋 Models Used in the Merge

Aspire
Creator: DreadPoor
Known for exceptional performance across diverse tasks and benchmarks.
Heart Stolen
Creator: DreadPoor
Renowned for its creative and empathetic prowess.
CursedMatrix
Creator: Khetterman
Famous for its depth and complexity, particularly in creative writing and roleplay.

⚙️ Merge Configuration

models:
  - model: DreadPoor/Aspire-8B-model_stock
  - model: DreadPoor/Heart_Stolen-8B-Model_Stock
  - model: Khetterman/CursedMatrix-8B-v9
merge_method: model_stock
base_model: Khetterman/CursedMatrix-8B-v9
normalize: false
int8_mask: true
dtype: bfloat16

🌌 Model Capabilities

This powerful merger unites the best features of its components:

Aspire: Outstanding performance across general tasks and benchmarks.
Heart Stolen: Creativity and empathy at its core.
CursedMatrix: Mastery of complex and dynamic text generation.

The resulting model excels in:

🌟 General Question Answering
📝 Creative Writing
✂️ Summarizing Long-Form Content
🎭 Roleplay Scenarios
✅ Task Completion and Problem-Solving

🛠️ Usage

This model is compatible with popular inference frameworks, including:

vLLM
LMStudio
Hugging Face Transformers and other major libraries.

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "ZeroXClem/L3-Aspire-Heart-Matrix-8B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

input_text = "What are the fundamentals of python programming?"
input_ids = tokenizer.encode(input_text, return_tensors="pt")
output = model.generate(input_ids, max_length=100)
response = tokenizer.decode(output[0], skip_special_tokens=True)
print(response)

Whether you're fine-tuning for specific tasks or using it out of the box, this model is a good base for your applications.

Please give us any feedback if issues arise during inference via the discussions tab.