Instructions to use MaximeMuhlethaler/chess-llm-MaximeMuh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaximeMuhlethaler/chess-llm-MaximeMuh with Transformers:

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

pipe = pipeline("text-generation", model="MaximeMuhlethaler/chess-llm-MaximeMuh")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MaximeMuhlethaler/chess-llm-MaximeMuh", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MaximeMuhlethaler/chess-llm-MaximeMuh with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MaximeMuhlethaler/chess-llm-MaximeMuh

SGLang

How to use MaximeMuhlethaler/chess-llm-MaximeMuh 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 "MaximeMuhlethaler/chess-llm-MaximeMuh" \
    --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": "MaximeMuhlethaler/chess-llm-MaximeMuh",
		"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 "MaximeMuhlethaler/chess-llm-MaximeMuh" \
        --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": "MaximeMuhlethaler/chess-llm-MaximeMuh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MaximeMuhlethaler/chess-llm-MaximeMuh with Docker Model Runner:
```
docker model run hf.co/MaximeMuhlethaler/chess-llm-MaximeMuh
```

MaximeMuhlethaler commited on Jan 13

Commit

40c5d31

verified ·

1 Parent(s): 8a917b6

Upload tokenizer_config.json with huggingface_hub

Browse files

Files changed (1) hide show

tokenizer_config.json +4 -3

tokenizer_config.json CHANGED Viewed

@@ -37,8 +37,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "[EOS]",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "tokenizer_class": "ChessTokenizer",
-  "unk_token": "[UNK]"
-}

   "clean_up_tokenization_spaces": false,
   "eos_token": "[EOS]",
   "extra_special_tokens": {},
+  "model_max_length": 256,
   "pad_token": "[PAD]",
   "tokenizer_class": "ChessTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_size": 1200
+}