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

Libraries

How to use laion/exp_tas_parser_xml_traces with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/exp_tas_parser_xml_traces")
model = AutoModelForCausalLM.from_pretrained("laion/exp_tas_parser_xml_traces")
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 laion/exp_tas_parser_xml_traces with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/laion/exp_tas_parser_xml_traces

SGLang

How to use laion/exp_tas_parser_xml_traces 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 "laion/exp_tas_parser_xml_traces" \
    --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": "laion/exp_tas_parser_xml_traces",
		"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 "laion/exp_tas_parser_xml_traces" \
        --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": "laion/exp_tas_parser_xml_traces",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

exp_tas_parser_xml_traces / train_results.json

hf-reset

Reset repository without checkpoints directories

71c3757 5 months ago

raw

history blame contribute delete

543 Bytes

	{
	"achieved_tflops_per_gpu": 3.6773450646115746,
	"achieved_tflops_per_gpu_theoretical": 389.6090247246643,
	"epoch": 7.0,
	"loss_nan_ranks": 0,
	"loss_rank_avg": 0.25698769092559814,
	"mfu_percent": 0.37182457680602377,
	"mfu_percent_theoretical": 39.39423910259498,
	"total_flos": 1.0409209055737283e+18,
	"train_loss": 0.5224247261221185,
	"train_runtime": 35382.8947,
	"train_samples_per_second": 1.835,
	"train_steps_per_second": 0.115,
	"valid_targets_mean": 3496.4,
	"valid_targets_min": 809
	}