Instructions to use lwa201/BitAgent-Bounty-8B-dpo-prune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lwa201/BitAgent-Bounty-8B-dpo-prune with Transformers:

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

pipe = pipeline("text-generation", model="lwa201/BitAgent-Bounty-8B-dpo-prune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lwa201/BitAgent-Bounty-8B-dpo-prune")
model = AutoModelForCausalLM.from_pretrained("lwa201/BitAgent-Bounty-8B-dpo-prune", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lwa201/BitAgent-Bounty-8B-dpo-prune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lwa201/BitAgent-Bounty-8B-dpo-prune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lwa201/BitAgent-Bounty-8B-dpo-prune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lwa201/BitAgent-Bounty-8B-dpo-prune

SGLang

How to use lwa201/BitAgent-Bounty-8B-dpo-prune 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 "lwa201/BitAgent-Bounty-8B-dpo-prune" \
    --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": "lwa201/BitAgent-Bounty-8B-dpo-prune",
		"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 "lwa201/BitAgent-Bounty-8B-dpo-prune" \
        --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": "lwa201/BitAgent-Bounty-8B-dpo-prune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lwa201/BitAgent-Bounty-8B-dpo-prune with Docker Model Runner:
```
docker model run hf.co/lwa201/BitAgent-Bounty-8B-dpo-prune
```

BitAgent-Bounty-8B-dpo-prune

Fine-tuned from BitAgent/BitAgent-Bounty-8B (Apache-2.0) with iterative step-level DPO for multi-turn tool-calling efficiency.

Changes from the base model

Method: iterative step-level DPO + validated trajectory pruning for multi-turn tool-use efficiency (merged weights from LoRA fine-tuning).
Training signal: self-generated preference pairs on BFCL v3 Base Multi-Turn.

A detailed description of the method and experiments will appear in an upcoming paper.

License

Apache-2.0. This is a derivative of BitAgent-Bounty-8B and is not an official BitAgent release. Please retain the original attribution when redistributing.

Intended use

Multi-turn function calling / tool use evaluation (e.g., BFCL).

Downloads last month: 245

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for lwa201/BitAgent-Bounty-8B-dpo-prune

Base model

BitAgent/BitAgent-Bounty-8B

Finetuned

(1)

this model