Chennus Series
Collection
Small and Efficient Chess Models • 3 items • Updated • 1
How to use DedeProGames/chennus with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="DedeProGames/chennus") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("DedeProGames/chennus")
model = AutoModelForCausalLM.from_pretrained("DedeProGames/chennus")How to use DedeProGames/chennus with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DedeProGames/chennus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "DedeProGames/chennus",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/DedeProGames/chennus
How to use DedeProGames/chennus with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "DedeProGames/chennus" \
--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": "DedeProGames/chennus",
"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 "DedeProGames/chennus" \
--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": "DedeProGames/chennus",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use DedeProGames/chennus with Docker Model Runner:
docker model run hf.co/DedeProGames/chennus
This is Chennus, my custom Chess AI model trained to play competitive chess on
Chess LLM Arena.
Chennus was trained on a 1500 ELO rating dataset, and despite the modest training base,
it achieved high performance levels on
Chess LLM Arena.
Chennus is free for anyone to use for chess finetuning, as long as you clearly state
in your model card or template that your work was based on Chennus.