Instructions to use laion/r2egym-nl2bash-stack-bugsseq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/r2egym-nl2bash-stack-bugsseq with Transformers:

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

pipe = pipeline("text-generation", model="laion/r2egym-nl2bash-stack-bugsseq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/r2egym-nl2bash-stack-bugsseq")
model = AutoModelForCausalLM.from_pretrained("laion/r2egym-nl2bash-stack-bugsseq", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use laion/r2egym-nl2bash-stack-bugsseq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/r2egym-nl2bash-stack-bugsseq"
# 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/r2egym-nl2bash-stack-bugsseq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/r2egym-nl2bash-stack-bugsseq

SGLang

How to use laion/r2egym-nl2bash-stack-bugsseq 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/r2egym-nl2bash-stack-bugsseq" \
    --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/r2egym-nl2bash-stack-bugsseq",
		"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/r2egym-nl2bash-stack-bugsseq" \
        --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/r2egym-nl2bash-stack-bugsseq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/r2egym-nl2bash-stack-bugsseq with Docker Model Runner:
```
docker model run hf.co/laion/r2egym-nl2bash-stack-bugsseq
```

r2egym-nl2bash-stack-bugsseq / train_results.json

penfever

Reset repository without checkpoint dirs

7a5bae1 8 months ago

Raw

History Blame Contribute Delete

545 Bytes

	{
	"achieved_tflops_per_gpu": 4.028113332034932,
	"achieved_tflops_per_gpu_theoretical": 355.7299790964326,
	"epoch": 7.0,
	"loss_nan_ranks": 0,
	"loss_rank_avg": 0.04305639863014221,
	"mfu_percent": 1.2910619653958118,
	"mfu_percent_theoretical": 114.01601894116429,
	"total_flos": 3.8836436423755694e+18,
	"train_loss": 0.06260271916794653,
	"train_runtime": 120516.8314,
	"train_samples_per_second": 1.686,
	"train_steps_per_second": 0.105,
	"valid_targets_mean": 4470.5,
	"valid_targets_min": 1273
	}