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

Libraries

How to use GoldenGekko/LinguaLaboratoriumMechanicus with Transformers:

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

pipe = pipeline("text-generation", model="GoldenGekko/LinguaLaboratoriumMechanicus", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("GoldenGekko/LinguaLaboratoriumMechanicus", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GoldenGekko/LinguaLaboratoriumMechanicus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GoldenGekko/LinguaLaboratoriumMechanicus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GoldenGekko/LinguaLaboratoriumMechanicus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GoldenGekko/LinguaLaboratoriumMechanicus

SGLang

How to use GoldenGekko/LinguaLaboratoriumMechanicus 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 "GoldenGekko/LinguaLaboratoriumMechanicus" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GoldenGekko/LinguaLaboratoriumMechanicus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "GoldenGekko/LinguaLaboratoriumMechanicus" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GoldenGekko/LinguaLaboratoriumMechanicus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GoldenGekko/LinguaLaboratoriumMechanicus with Docker Model Runner:
```
docker model run hf.co/GoldenGekko/LinguaLaboratoriumMechanicus
```

LinguaLaboratoriumMechanicus

Претрейн кастомной decoder-only модели на русскоязычном корпусе лора Warhammer 40,000.

Архитектура


Параметры	~163M
Слоёв	12
Размерность	768
Голов внимания	12
Контекст	1024
Vocab	50 257
FFN	GELU, 4× expansion
Нормализация	Pre-LayerNorm

Кастомная архитектура — загрузка с trust_remote_code=True.

Использование

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "GoldenGekko/LinguaLaboratoriumMechanicus"
device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True).to(device)

prompt = "В 31-м тысячелетии Империум"
inputs = tokenizer(prompt, return_tensors="pt").to(device)
output_ids = model.generate(
    inputs["input_ids"],
    max_new_tokens=100,
    do_sample=True,
    temperature=0.8,
    top_k=40,
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output_ids[0], skip_special_tokens=True))

Связанные репозитории

LinguaLaboratoriumMechanicus-instruct — SFT-версия для Q&A

Citation

https://huggingface.co/GoldenGekko/LinguaLaboratoriumMechanicus

Downloads last month: 32

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for GoldenGekko/LinguaLaboratoriumMechanicus

Finetunes

1 model