Instructions to use DCAgent2/stack-nl2bashseq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DCAgent2/stack-nl2bashseq with Transformers:

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

pipe = pipeline("text-generation", model="DCAgent2/stack-nl2bashseq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DCAgent2/stack-nl2bashseq")
model = AutoModelForCausalLM.from_pretrained("DCAgent2/stack-nl2bashseq")
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 DCAgent2/stack-nl2bashseq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DCAgent2/stack-nl2bashseq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DCAgent2/stack-nl2bashseq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DCAgent2/stack-nl2bashseq

SGLang

How to use DCAgent2/stack-nl2bashseq 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 "DCAgent2/stack-nl2bashseq" \
    --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": "DCAgent2/stack-nl2bashseq",
		"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 "DCAgent2/stack-nl2bashseq" \
        --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": "DCAgent2/stack-nl2bashseq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DCAgent2/stack-nl2bashseq with Docker Model Runner:
```
docker model run hf.co/DCAgent2/stack-nl2bashseq
```

stack-nl2bashseq / all_results.json

hf-reset

Reset repository without checkpoints directories

c70cd67 6 months ago

raw

history blame contribute delete

544 Bytes

	{
	"achieved_tflops_per_gpu": 0.0028888970967278762,
	"achieved_tflops_per_gpu_theoretical": 877.4672817712005,
	"epoch": 7.0,
	"loss_nan_ranks": 0,
	"loss_rank_avg": 0.0974183976650238,
	"mfu_percent": 0.00020416233899136932,
	"mfu_percent_theoretical": 62.01182203330039,
	"total_flos": 1189064928198656.0,
	"train_loss": 0.2180497848695996,
	"train_runtime": 25724.8893,
	"train_samples_per_second": 4.145,
	"train_steps_per_second": 0.259,
	"valid_targets_mean": 1721.1,
	"valid_targets_min": 760
	}