Instructions to use Leon-LLM/Leon-Chess-1M-BOS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Leon-LLM/Leon-Chess-1M-BOS with Transformers:

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

pipe = pipeline("text-generation", model="Leon-LLM/Leon-Chess-1M-BOS")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Leon-LLM/Leon-Chess-1M-BOS")
model = AutoModelForCausalLM.from_pretrained("Leon-LLM/Leon-Chess-1M-BOS")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Leon-LLM/Leon-Chess-1M-BOS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Leon-LLM/Leon-Chess-1M-BOS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Leon-LLM/Leon-Chess-1M-BOS",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Leon-LLM/Leon-Chess-1M-BOS

SGLang

How to use Leon-LLM/Leon-Chess-1M-BOS 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 "Leon-LLM/Leon-Chess-1M-BOS" \
    --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": "Leon-LLM/Leon-Chess-1M-BOS",
		"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 "Leon-LLM/Leon-Chess-1M-BOS" \
        --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": "Leon-LLM/Leon-Chess-1M-BOS",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Leon-LLM/Leon-Chess-1M-BOS with Docker Model Runner:
```
docker model run hf.co/Leon-LLM/Leon-Chess-1M-BOS
```

MJerome commited on Dec 21, 2023

Commit

0724e8a

1 Parent(s): eadbc15

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -2

README.md CHANGED Viewed

@@ -53,10 +53,10 @@ Chess games from Lichess were converted from PGN into [xLAN](https://github.zhaw
 #### Training Hyperparameters
-- **Training regime:**
 - Batch Size: 24
 - Epochs: 4
 - Learning Rate: 0.00005
 ## Evaluation
@@ -74,8 +74,16 @@ The model was tested on 3 metrics:
 ### Results
 ## Model Architecture

 #### Training Hyperparameters
 - Batch Size: 24
 - Epochs: 4
 - Learning Rate: 0.00005
+- With BOS-Token
 ## Evaluation
 ### Results
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b81dff25b0493d515e317c/j0ZCCS0nIrkiyPJmynnsG.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b81dff25b0493d515e317c/NTvDR_XHnyKih9u_GExWo.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b81dff25b0493d515e317c/XGu5el3iztCFmPZiwTmOO.png)
 ## Model Architecture
+GPT2 config with the following changes:
+- VOCAB_SIZE = 76
+- N_POSITION = 512
+- PAD_TOKEN_ID = 0
+- BOS_TOKEN_ID = 75
+- EOS_TOKEN_ID = 74