Instructions to use RichelieuGVG/model_neuroplay with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichelieuGVG/model_neuroplay with Transformers:

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

pipe = pipeline("text-generation", model="RichelieuGVG/model_neuroplay")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichelieuGVG/model_neuroplay")
model = AutoModelForCausalLM.from_pretrained("RichelieuGVG/model_neuroplay", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RichelieuGVG/model_neuroplay with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RichelieuGVG/model_neuroplay

SGLang

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

Docker Model Runner
How to use RichelieuGVG/model_neuroplay with Docker Model Runner:
```
docker model run hf.co/RichelieuGVG/model_neuroplay
```

cont_medium_4_256

This model is a fine-tuned version of sberbank-ai/rugpt3medium_based_on_gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.7602
Accuracy: 0.3436

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: 1.5e-05
train_batch_size: 6
eval_batch_size: 12
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.4091	1.0	160	3.7238	0.3472
3.2338	2.0	320	3.7393	0.3446
3.1684	3.0	480	3.7518	0.3444
3.0989	4.0	640	3.7602	0.3436

Framework versions

Transformers 4.23.1
Pytorch 1.8.1+cu111
Datasets 2.5.2
Tokenizers 0.13.1

Downloads last month: 12