Instructions to use MDaytek/chess-v2-head with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MDaytek/chess-v2-head with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MDaytek/chess-v2-head", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("MDaytek/chess-v2-head", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MDaytek/chess-v2-head with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MDaytek/chess-v2-head" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MDaytek/chess-v2-head", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MDaytek/chess-v2-head
- SGLang
How to use MDaytek/chess-v2-head 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 "MDaytek/chess-v2-head" \ --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": "MDaytek/chess-v2-head", "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 "MDaytek/chess-v2-head" \ --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": "MDaytek/chess-v2-head", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MDaytek/chess-v2-head with Docker Model Runner:
docker model run hf.co/MDaytek/chess-v2-head
Submission with auto_map and code files
Browse files- README.md +1 -0
- config.json +4 -0
README.md
CHANGED
|
@@ -9,3 +9,4 @@ license: mit
|
|
| 9 |
# chess-v2-head
|
| 10 |
Model submitted by MDaytek.
|
| 11 |
**Parameters:** 999,936
|
|
|
|
|
|
| 9 |
# chess-v2-head
|
| 10 |
Model submitted by MDaytek.
|
| 11 |
**Parameters:** 999,936
|
| 12 |
+
**Architecture:** Custom Chess Transformer (Code included)
|
config.json
CHANGED
|
@@ -2,6 +2,10 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"ChessForCausalLM"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"dtype": "float32",
|
| 6 |
"hidden_size": 128,
|
| 7 |
"model_type": "chess_transformer",
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"ChessForCausalLM"
|
| 4 |
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "model.ChessConfig",
|
| 7 |
+
"AutoModelForCausalLM": "model.ChessForCausalLM"
|
| 8 |
+
},
|
| 9 |
"dtype": "float32",
|
| 10 |
"hidden_size": 128,
|
| 11 |
"model_type": "chess_transformer",
|