Instructions to use layai/syn-dataaug-combined-dict with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use layai/syn-dataaug-combined-dict with Transformers:

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

pipe = pipeline("text-generation", model="layai/syn-dataaug-combined-dict")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("layai/syn-dataaug-combined-dict")
model = AutoModelForCausalLM.from_pretrained("layai/syn-dataaug-combined-dict")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use layai/syn-dataaug-combined-dict with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/layai/syn-dataaug-combined-dict

SGLang

How to use layai/syn-dataaug-combined-dict 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 "layai/syn-dataaug-combined-dict" \
    --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": "layai/syn-dataaug-combined-dict",
		"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 "layai/syn-dataaug-combined-dict" \
        --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": "layai/syn-dataaug-combined-dict",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use layai/syn-dataaug-combined-dict with Docker Model Runner:
```
docker model run hf.co/layai/syn-dataaug-combined-dict
```

syn-dataaug-combined-dict / trainer_state.json

layai

Add files using upload-large-folder tool

d44237b verified 16 days ago

raw

history blame contribute delete

1.24 kB

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 2.9508196721311473,
	"eval_steps": 500,
	"global_step": 45,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 2.9508196721311473,
	"step": 45,
	"total_flos": 4.137242825903309e+16,
	"train_loss": 0.9504057142469619,
	"train_runtime": 412.8005,
	"train_samples_per_second": 17.653,
	"train_steps_per_second": 0.109
	}
	],
	"logging_steps": 500,
	"max_steps": 45,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"save_steps": 500,
	"stateful_callbacks": {
	"EarlyStoppingCallback": {
	"args": {
	"early_stopping_patience": 3,
	"early_stopping_threshold": 0.0
	},
	"attributes": {
	"early_stopping_patience_counter": 0
	}
	},
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 4.137242825903309e+16,
	"train_batch_size": 40,
	"trial_name": null,
	"trial_params": null
	}