Instructions to use LLM-course/chess-normal-BPE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-course/chess-normal-BPE with Transformers:

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

pipe = pipeline("text-generation", model="LLM-course/chess-normal-BPE", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LLM-course/chess-normal-BPE", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLM-course/chess-normal-BPE with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LLM-course/chess-normal-BPE

SGLang

How to use LLM-course/chess-normal-BPE 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 "LLM-course/chess-normal-BPE" \
    --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": "LLM-course/chess-normal-BPE",
		"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 "LLM-course/chess-normal-BPE" \
        --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": "LLM-course/chess-normal-BPE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLM-course/chess-normal-BPE with Docker Model Runner:
```
docker model run hf.co/LLM-course/chess-normal-BPE
```

Chiensaucisse67 commited on Jan 18

Commit

ece80ef

verified ·

1 Parent(s): 04796f5

Chess Challenge submission by Chiensaucisse67

Browse files

Files changed (3) hide show

README.md +1 -1
tokenizer_config.json +2 -3
vocab.json +8 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ Chess model submitted to the LLM Course Chess Challenge.
 ## Model Details
 - **Architecture**: Chess Transformer (GPT-style)
-- **Vocab size**: 72
 - **Embedding dim**: 128
 - **Layers**: 4
 - **Heads**: 4

 ## Model Details
 - **Architecture**: Chess Transformer (GPT-style)
+- **Vocab size**: 79
 - **Embedding dim**: 128
 - **Layers**: 4
 - **Heads**: 4

tokenizer_config.json CHANGED Viewed

@@ -35,7 +35,7 @@
   },
   "auto_map": {
     "AutoTokenizer": [
-      "tokenizer_custom.CoordinateTokenizer",
       null
     ]
   },
@@ -45,7 +45,6 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "tokenizer_class": "CoordinateTokenizer",
-  "truncation_side": "left",
   "unk_token": "[UNK]"
 }

   },
   "auto_map": {
     "AutoTokenizer": [
+      "tokenizer_custom.EnhancedCoordinateTokenizer",
       null
     ]
   },
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "tokenizer_class": "EnhancedCoordinateTokenizer",
   "unk_token": "[UNK]"
 }

vocab.json CHANGED Viewed

@@ -70,5 +70,12 @@
   "q": 68,
   "r": 69,
   "b": 70,
-  "n": 71
 }

   "q": 68,
   "r": 69,
   "b": 70,
+  "n": 71,
+  "W": 72,
+  "B": 73,
+  "P": 74,
+  "N": 75,
+  "R": 76,
+  "Q": 77,
+  "K": 78
 }