Instructions to use forkjoin-ai/buleyean-qwen2.5-7b-gpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use forkjoin-ai/buleyean-qwen2.5-7b-gpu with Transformers:

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

pipe = pipeline("text-generation", model="forkjoin-ai/buleyean-qwen2.5-7b-gpu")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("forkjoin-ai/buleyean-qwen2.5-7b-gpu", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use forkjoin-ai/buleyean-qwen2.5-7b-gpu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "forkjoin-ai/buleyean-qwen2.5-7b-gpu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "forkjoin-ai/buleyean-qwen2.5-7b-gpu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/forkjoin-ai/buleyean-qwen2.5-7b-gpu

SGLang

How to use forkjoin-ai/buleyean-qwen2.5-7b-gpu 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 "forkjoin-ai/buleyean-qwen2.5-7b-gpu" \
    --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": "forkjoin-ai/buleyean-qwen2.5-7b-gpu",
		"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 "forkjoin-ai/buleyean-qwen2.5-7b-gpu" \
        --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": "forkjoin-ai/buleyean-qwen2.5-7b-gpu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use forkjoin-ai/buleyean-qwen2.5-7b-gpu with Docker Model Runner:
```
docker model run hf.co/forkjoin-ai/buleyean-qwen2.5-7b-gpu
```

buleyean-qwen2.5-7b-gpu

Buleyean RL -- trained on what is NOT rather than positive reinforcement.

No reward model. No chosen examples. The complement distribution derived from rejection counts alone is the training target.

Model Details


Base Model	Qwen/Qwen2.5-7B-Instruct
Parameters	7B
Fine-tuning	Buleyean RL (LoRA rank 16, alpha 0.7)
Data	5,000 UltraFeedback rejection records (chosen discarded)
Format	LoRA
Hardware	T4 GPU
Steps	563
Final Loss	1.03
Optimality Gap	0.017