Instructions to use SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct")
model = AutoModelForCausalLM.from_pretrained("SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct", 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 SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct

SGLang

How to use SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct 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 "SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct" \
    --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": "SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct",
		"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 "SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct" \
        --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": "SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct with Docker Model Runner:
```
docker model run hf.co/SYSU-MUCFC-FinTech-Research-Center/Zhongsi-9B-Instruct
```

Yi-1.5-9B-sft-241128

This model is a fine-tuned version of saves/Yi-1.5-9B-pt-241124 on the chinese-medical-dialogue, the CMB, the cMedQA2, the CMExam, the CMtMedQA, the COIG-CQIA-full, the COIG_full, the HuatuoGPT_sft_data_v, the huatuo_encyclopedia_q, the huatuo_lite, the imcs21, the Med-single-choice, the Medical_dialogue_system_en_single_turn, the qizhengpt-sft-20, the self_cognition, the sharegpt_zh_38K_format, the shennong, the shibing642-medica, the tigerbot_sft_data, the xywy-KG and the zhongyi-zhiku datasets. It achieves the following results on the evaluation set:

Loss: 1.4478

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2.5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.6544	0.1277	1000	1.6105
1.5595	0.2554	2000	1.5668
1.5297	0.3830	3000	1.5394
1.5637	0.5107	4000	1.5188
1.5051	0.6384	5000	1.5028
1.4765	0.7661	6000	1.4895
1.4504	0.8938	7000	1.4779
1.4084	1.0215	8000	1.4716
1.4292	1.1491	9000	1.4653
1.4349	1.2768	10000	1.4597
1.4442	1.4045	11000	1.4548
1.422	1.5322	12000	1.4517
1.3986	1.6599	13000	1.4491
1.3949	1.7875	14000	1.4482
1.4241	1.9152	15000	1.4478

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Downloads last month: 14

Safetensors

Model size

9B params

Tensor type

BF16