Instructions to use zhoudoe23/ChessQween2-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zhoudoe23/ChessQween2-tiny with Transformers:

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

pipe = pipeline("text-generation", model="zhoudoe23/ChessQween2-tiny")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zhoudoe23/ChessQween2-tiny")
model = AutoModelForCausalLM.from_pretrained("zhoudoe23/ChessQween2-tiny", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zhoudoe23/ChessQween2-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zhoudoe23/ChessQween2-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zhoudoe23/ChessQween2-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zhoudoe23/ChessQween2-tiny

SGLang

How to use zhoudoe23/ChessQween2-tiny 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 "zhoudoe23/ChessQween2-tiny" \
    --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": "zhoudoe23/ChessQween2-tiny",
		"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 "zhoudoe23/ChessQween2-tiny" \
        --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": "zhoudoe23/ChessQween2-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zhoudoe23/ChessQween2-tiny with Docker Model Runner:
```
docker model run hf.co/zhoudoe23/ChessQween2-tiny
```

ChessQween2-tiny / README.md

zhoudoe23

End of training

2eee2f6 verified 23 days ago

preview code

Raw

History Blame Contribute Delete

2.01 kB

	---
	library_name: transformers
	license: mit
	base_model: openai-community/gpt2
	tags:
	- generated_from_trainer
	model-index:
	- name: ChessQween2-tiny
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# ChessQween2-tiny

	This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 2.3192

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 0.00015
	- train_batch_size: 128
	- eval_batch_size: 128
	- seed: 42
	- gradient_accumulation_steps: 4
	- total_train_batch_size: 512
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 200
	- num_epochs: 1
	- mixed_precision_training: Native AMP

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 3.9745 \| 0.1009 \| 101 \| 3.9412 \|
	\| 3.5969 \| 0.2018 \| 202 \| 3.5234 \|
	\| 3.2078 \| 0.3028 \| 303 \| 3.1028 \|
	\| 2.9051 \| 0.4037 \| 404 \| 2.7821 \|
	\| 2.7076 \| 0.5046 \| 505 \| 2.5714 \|
	\| 2.5810 \| 0.6055 \| 606 \| 2.4494 \|
	\| 2.5076 \| 0.7065 \| 707 \| 2.3762 \|
	\| 2.4721 \| 0.8074 \| 808 \| 2.3372 \|
	\| 2.4643 \| 0.9083 \| 909 \| 2.3221 \|
	\| 2.4602 \| 1.0 \| 1001 \| 2.3192 \|


	### Framework versions

	- Transformers 5.14.1
	- Pytorch 2.10.0+cu128
	- Datasets 5.0.0
	- Tokenizers 0.22.2