Instructions to use modelscope/llama3-8b-agent-instruct-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modelscope/llama3-8b-agent-instruct-v2 with Transformers:

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

pipe = pipeline("text-generation", model="modelscope/llama3-8b-agent-instruct-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("modelscope/llama3-8b-agent-instruct-v2")
model = AutoModelForCausalLM.from_pretrained("modelscope/llama3-8b-agent-instruct-v2")
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 modelscope/llama3-8b-agent-instruct-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modelscope/llama3-8b-agent-instruct-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modelscope/llama3-8b-agent-instruct-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modelscope/llama3-8b-agent-instruct-v2

SGLang

How to use modelscope/llama3-8b-agent-instruct-v2 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 "modelscope/llama3-8b-agent-instruct-v2" \
    --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": "modelscope/llama3-8b-agent-instruct-v2",
		"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 "modelscope/llama3-8b-agent-instruct-v2" \
        --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": "modelscope/llama3-8b-agent-instruct-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modelscope/llama3-8b-agent-instruct-v2 with Docker Model Runner:
```
docker model run hf.co/modelscope/llama3-8b-agent-instruct-v2
```

Fine-tuning the llama3-8b-instruct model using the msagent-pro dataset and the loss_scale technique with swift, the script is as follows:

NPROC_PER_NODE=8 \
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
MASTER_PORT=29500 \
swift sft \
    --model_type llama3-8b-instruct \
    --learning_rate 2e-5 \
    --sft_type lora \
    --dataset msagent-pro \
    --gradient_checkpointing true \
    --gradient_accumulation_steps 8 \
    --deepspeed default-zero3 \
    --lora_target_modules ALL \
    --use_loss_scale true \
    --save_strategy epoch \
    --batch_size 1 \
    --num_train_epochs 2 \
    --max_length 4096 \
    --preprocess_num_proc 4 \
    --use_loss_scale true \
    --loss_scale_config_path agent-flan \
    --ddp_backend nccl \

Comparison with the Original Model on the ToolBench Evaluation Set

Model	ToolBench (in-domain)					ToolBench (out-of-domain)
	Plan.EM	Act.EM	HalluRate (lower is better)	Avg.F1	R-L	Plan.EM	Act.EM	HalluRate (lower is better)	Avg.F1
llama3-8b-instruct	74.22	36.17	15.68	20.0	12.14	69.47	34.21	14.72	20.25
llama3-8b-agent-instruct-v2	85.15	58.1	1.57	52.10	26.02	85.79	59.43	2.56	52.19

For detailed explanations of the evaluation metrics, please refer to document

Deploy this model:

USE_HF=True swift deploy \
  --model_id_or_path modelscope/llama3-8b-agent-instruct-v2 \
  --model_type llama3-8b-instruct \
  --infer_backend vllm \
  --tools_prompt toolbench

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16