Instructions to use MagistrTheOne/NULLXES-MGE-V1_CHIMERA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MagistrTheOne/NULLXES-MGE-V1_CHIMERA with Transformers:

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

pipe = pipeline("text-generation", model="MagistrTheOne/NULLXES-MGE-V1_CHIMERA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MagistrTheOne/NULLXES-MGE-V1_CHIMERA")
model = AutoModelForCausalLM.from_pretrained("MagistrTheOne/NULLXES-MGE-V1_CHIMERA", 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 MagistrTheOne/NULLXES-MGE-V1_CHIMERA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MagistrTheOne/NULLXES-MGE-V1_CHIMERA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/NULLXES-MGE-V1_CHIMERA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MagistrTheOne/NULLXES-MGE-V1_CHIMERA

SGLang

How to use MagistrTheOne/NULLXES-MGE-V1_CHIMERA 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 "MagistrTheOne/NULLXES-MGE-V1_CHIMERA" \
    --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": "MagistrTheOne/NULLXES-MGE-V1_CHIMERA",
		"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 "MagistrTheOne/NULLXES-MGE-V1_CHIMERA" \
        --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": "MagistrTheOne/NULLXES-MGE-V1_CHIMERA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MagistrTheOne/NULLXES-MGE-V1_CHIMERA with Docker Model Runner:
```
docker model run hf.co/MagistrTheOne/NULLXES-MGE-V1_CHIMERA
```

NULLXES-MGE-V1_CHIMERA / README.md

MagistrTheOne

Update README.md

6f60fdc verified 4 months ago

preview code

Raw

History Blame Contribute Delete

729 Bytes

metadata

language:
  - ru
  - en
license: mit
library_name: transformers
pipeline_tag: text-generation
tags:
  - nullxes
  - nmge
  - chimera
  - operational-cognition
datasets:
  - MagistrTheOne/nullxes-train-vFINAL

NULLXES-MGE-V1_CHIMERA

Operational cognition model for the NULLXES NMGE stack.

Version: V1 (14B class)
Params: ~14.77B
Chat template: included (chat_template.jinja)
Use case: planning, tool routing, expected_state traces

Production identity and legal canon are enforced via the NMGE Gateway system layer.

Usage

Load with Hugging Face Transformers, vLLM, or LLaMA-Factory using the bundled chat template.

Training data

MagistrTheOne/nullxes-train-vFINAL

Contact

@MagistrTheOne · ceo@nullxes.com