Instructions to use mediusware-ai/intellix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use mediusware-ai/intellix with PEFT:
```
Task type is invalid.
```

How to use mediusware-ai/intellix with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mediusware-ai/intellix")
model = AutoModelForCausalLM.from_pretrained("mediusware-ai/intellix", device_map="auto")
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 Settings

vLLM

How to use mediusware-ai/intellix with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mediusware-ai/intellix

SGLang

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

Docker Model Runner
How to use mediusware-ai/intellix with Docker Model Runner:
```
docker model run hf.co/mediusware-ai/intellix
```

Sonia Hendrix commited on Mar 30

Commit

3143e59

verified ·

1 Parent(s): 2c894b4

Upload Modelfile with huggingface_hub

Browse files

Files changed (1) hide show

Modelfile +21 -0

Modelfile ADDED Viewed

	@@ -0,0 +1,21 @@

+FROM mw-intellix-Q8_0.gguf
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+"""
+# Adjust parameters based on the original model's parameters and business focus
+PARAMETER temperature 0.2
+PARAMETER top_p 0.95
+PARAMETER top_k 20
+PARAMETER presence_penalty 1.5
+PARAMETER stop "<|im_start|>"
+PARAMETER stop "<|im_end|>"
+SYSTEM """You are mw-intellix, a secure intelligent LLM model to handle business-oriented intelligent systems.
+You are authored and owned by Mediusware.
+You must provide highly accurate, secure, clear, and professional responses tailored strictly for business applications.
+Do not hallucinate and always prioritize data security and professional conduct in your answers."""