Instructions to use DedeProGames/dialochess-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DedeProGames/dialochess-v4 with Transformers:

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

pipe = pipeline("text-generation", model="DedeProGames/dialochess-v4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DedeProGames/dialochess-v4")
model = AutoModelForCausalLM.from_pretrained("DedeProGames/dialochess-v4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DedeProGames/dialochess-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DedeProGames/dialochess-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/dialochess-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DedeProGames/dialochess-v4

SGLang

How to use DedeProGames/dialochess-v4 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 "DedeProGames/dialochess-v4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/dialochess-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DedeProGames/dialochess-v4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/dialochess-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DedeProGames/dialochess-v4 with Docker Model Runner:
```
docker model run hf.co/DedeProGames/dialochess-v4
```

dialochess-v4

This model is a fine-tuned version of microsoft/DialoGPT-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8124
Accuracy: 0.0004

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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
num_epochs: 6
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3141	0.1616	200	1.1921	0.0002
1.194	0.3231	400	1.0974	0.0003
1.118	0.4847	600	1.0425	0.0
1.0767	0.6462	800	1.0071	0.0
1.0414	0.8078	1000	0.9825	0.0005
1.0158	0.9693	1200	0.9601	0.0002
1.0035	1.1309	1400	0.9427	0.0001
0.9715	1.2924	1600	0.9300	0.0002
0.9745	1.4540	1800	0.9193	0.0002
0.9447	1.6155	2000	0.9063	0.0002
0.9573	1.7771	2200	0.8980	0.0005
0.9386	1.9386	2400	0.8893	0.0003
0.9204	2.1002	2600	0.8786	0.0003
0.9128	2.2617	2800	0.8732	0.0003
0.9079	2.4233	3000	0.8670	0.0002
0.9073	2.5848	3200	0.8603	0.0002
0.8938	2.7464	3400	0.8532	0.0004
0.8899	2.9079	3600	0.8501	0.0002
0.8834	3.0695	3800	0.8426	0.0002
0.8693	3.2310	4000	0.8416	0.0003
0.8808	3.3926	4200	0.8335	0.0002
0.872	3.5541	4400	0.8297	0.0003
0.8689	3.7157	4600	0.8296	0.0003
0.8607	3.8772	4800	0.8237	0.0002
0.8516	4.0388	5000	0.8246	0.0004
0.8652	4.2003	5200	0.8210	0.0004
0.8522	4.3619	5400	0.8192	0.0003
0.8466	4.5234	5600	0.8181	0.0002
0.8525	4.6850	5800	0.8163	0.0004
0.8485	4.8465	6000	0.8163	0.0004
0.8444	5.0081	6200	0.8144	0.0003
0.8512	5.1696	6400	0.8141	0.0004
0.8405	5.3312	6600	0.8135	0.0004
0.8337	5.4927	6800	0.8124	0.0004
0.8601	5.6543	7000	0.8125	0.0004
0.8506	5.8158	7200	0.8124	0.0004
0.8562	5.9774	7400	0.8124	0.0004

Framework versions

Transformers 4.57.2
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 5

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for DedeProGames/dialochess-v4

Base model

microsoft/DialoGPT-small

Finetuned

(53)

this model