Instructions to use SeaLLMs/SeaLLMs-v3-7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SeaLLMs/SeaLLMs-v3-7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="SeaLLMs/SeaLLMs-v3-7B-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SeaLLMs/SeaLLMs-v3-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("SeaLLMs/SeaLLMs-v3-7B-Chat")
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]:]))

Inference
Local Apps Settings

vLLM

How to use SeaLLMs/SeaLLMs-v3-7B-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SeaLLMs/SeaLLMs-v3-7B-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SeaLLMs/SeaLLMs-v3-7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SeaLLMs/SeaLLMs-v3-7B-Chat

SGLang

How to use SeaLLMs/SeaLLMs-v3-7B-Chat 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 "SeaLLMs/SeaLLMs-v3-7B-Chat" \
    --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": "SeaLLMs/SeaLLMs-v3-7B-Chat",
		"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 "SeaLLMs/SeaLLMs-v3-7B-Chat" \
        --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": "SeaLLMs/SeaLLMs-v3-7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SeaLLMs/SeaLLMs-v3-7B-Chat with Docker Model Runner:
```
docker model run hf.co/SeaLLMs/SeaLLMs-v3-7B-Chat
```

The generated results are very random

by jeremysun1224 - opened Jul 15, 2024

Discussion

jeremysun1224

Jul 15, 2024

The torch version I am using: 2.4.0a0+f70bd71a48.nv24.06 from nvidia container and transformers version is 4.42.4.

When I use you to generate the get started code given in HuggingFace Seallm3-7B-Chat, the generating results are not ideal.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
  "SeaLLMs/SeaLLM3-7B-chat",
  torch_dtype=torch.bfloat16, 
  device_map=device
)
tokenizer = AutoTokenizer.from_pretrained("SeaLLMs/SeaLLM3-7B-chat")

# prepare messages to model
prompt = "What can you do for me?"
messages = [
    {"role": "system", "content": "You are an expert in parsing logistics addresses from the Philippines, specializing in converting addresses into structured JSON format based on specified fields."},
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512, do_sample=True, temperature=0.8)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)

print(f"Response:\n {response[0]}")

Response:
 I am an expert in parsing logistics addresses from the Philippines, specializing in converting addresses into structured JSON format based on specified fields.惢惢owellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowellcomeowell

more response

However, when I used your open-source demo in Huggingface space the model answered the same question very well. May I ask why?

isakzhang

SeaLLMs - Language Models for Southeast Asian Languages org Jul 15, 2024

Hi, you can just set the eos_token_id in the model.generate() function, then it will become normal. See the below example with your provided code snippet:

jeremysun1224

Jul 16, 2024

Hi, you can just set the eos_token_id in the model.generate() function, then it will become normal. See the below example with your provided code snippet:

Thank you for your reply, the issue has been resolved. SeaLLMs is very meaningful work.

But could specifying eos_token_id lead to premature termination, reduced text diversity, and dependency on training data marking?

jeremysun1224

Jul 16, 2024

•

edited Jul 16, 2024

Looking forward to your reply.

jeremysun1224

Jul 16, 2024

•

edited Jul 16, 2024

Perhaps you should change the eos_token_id in generation_config to 151645, instead of the current 151643. I found that after the change, there is no need to specify tokenizer.eos_token_id anymore.

isakzhang

SeaLLMs - Language Models for Southeast Asian Languages org Jul 16, 2024

Yes, you can also change the model config, but these two actions should actually be equivalent.

I have revised the generation_config file. Thanks for your feedback!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment