Instructions to use BoyBarley/BoyBarley-v32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BoyBarley/BoyBarley-v32 with Transformers:

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

pipe = pipeline("text-generation", model="BoyBarley/BoyBarley-v32")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BoyBarley/BoyBarley-v32")
model = AutoModelForCausalLM.from_pretrained("BoyBarley/BoyBarley-v32")
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 BoyBarley/BoyBarley-v32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BoyBarley/BoyBarley-v32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BoyBarley/BoyBarley-v32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BoyBarley/BoyBarley-v32

SGLang

How to use BoyBarley/BoyBarley-v32 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 "BoyBarley/BoyBarley-v32" \
    --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": "BoyBarley/BoyBarley-v32",
		"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 "BoyBarley/BoyBarley-v32" \
        --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": "BoyBarley/BoyBarley-v32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BoyBarley/BoyBarley-v32 with Docker Model Runner:
```
docker model run hf.co/BoyBarley/BoyBarley-v32
```

BoyBarley v32 (Recommended)

DevOps & Automation AI agent. Best overall: 94.4% on 18-test eval.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('BoyBarley/BoyBarley-v32')
tokenizer = AutoTokenizer.from_pretrained('BoyBarley/BoyBarley-v32')

Training

Params: ~494M, bfloat16
Epochs: 1, LR: 5e-6
Train loss: 0.0751, Eval loss: 0.0665
Dataset: BoyBarley/BoyBarley-v32-dataset

Features

DevOps CLI (Docker, Kubernetes, Linux)
Tool JSON output for agents
Refuses destructive commands
Bilingual Indonesian/English

License: Apache 2.0

Downloads last month: 349

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for BoyBarley/BoyBarley-v32

Finetunes

1 model

BoyBarley
/

BoyBarley-v32

BoyBarley v32 (Recommended)

Usage

Training

Features

Model tree for BoyBarley/BoyBarley-v32

Space using BoyBarley/BoyBarley-v32 1