Instructions to use OddTheGreat/Circuitry_24B_V.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OddTheGreat/Circuitry_24B_V.2 with Transformers:

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

pipe = pipeline("text-generation", model="OddTheGreat/Circuitry_24B_V.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OddTheGreat/Circuitry_24B_V.2")
model = AutoModelForCausalLM.from_pretrained("OddTheGreat/Circuitry_24B_V.2", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OddTheGreat/Circuitry_24B_V.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OddTheGreat/Circuitry_24B_V.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OddTheGreat/Circuitry_24B_V.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OddTheGreat/Circuitry_24B_V.2

SGLang

How to use OddTheGreat/Circuitry_24B_V.2 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 "OddTheGreat/Circuitry_24B_V.2" \
    --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/Circuitry_24B_V.2",
		"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 "OddTheGreat/Circuitry_24B_V.2" \
        --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/Circuitry_24B_V.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OddTheGreat/Circuitry_24B_V.2 with Docker Model Runner:
```
docker model run hf.co/OddTheGreat/Circuitry_24B_V.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Circuitry_24B_V.2

This is a merge of pre-trained language models.

Goal of this merge was to replace Mechanism as my new main rp model.

Model is coherent, and handles bad written or overengineered cards. Creativity is better than in Mechanism model (finally, normal names!), but model remains stable, prose and dialogues are less robotic and distant, more emotional.

Instruction following capabilities are good too, only problem i had spotted is periodic formatting errors.

Good balance at sfw/nsfw, can be positive, neutral or negative depending on prompt.

ERP is not bad.

On RU was tested only as assistant and was good at it.

Tested on 8k context average, 12k and 16k runs didn't showed instability or dramatic quality loss.

Used q4_K_M, Mistral template, instruct on, T1.04, xtc off or 0.1 0.1 (off is better.)