How to use OddTheGreat/Mechanism_24B_V.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OddTheGreat/Mechanism_24B_V.1")
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("OddTheGreat/Mechanism_24B_V.1") model = AutoModelForCausalLM.from_pretrained("OddTheGreat/Mechanism_24B_V.1")
How to use OddTheGreat/Mechanism_24B_V.1 with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OddTheGreat/Mechanism_24B_V.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OddTheGreat/Mechanism_24B_V.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
docker model run hf.co/OddTheGreat/Mechanism_24B_V.1
How to use OddTheGreat/Mechanism_24B_V.1 with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "OddTheGreat/Mechanism_24B_V.1" \ --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": "OddTheGreat/Mechanism_24B_V.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
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 "OddTheGreat/Mechanism_24B_V.1" \ --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": "OddTheGreat/Mechanism_24B_V.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
How to use OddTheGreat/Mechanism_24B_V.1 with Docker Model Runner:
This is a merge of pre-trained language models.
Created for roleplay, good in it. Stable, with good creativity. Close to neutrality.
Ru is supported.
Tested up to 16k context, could handle more.
Mistral format. T1.04
Files info
