Instructions to use bytedance-research/ChatTS-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bytedance-research/ChatTS-14B with Transformers:

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

pipe = pipeline("text-generation", model="bytedance-research/ChatTS-14B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bytedance-research/ChatTS-14B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bytedance-research/ChatTS-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bytedance-research/ChatTS-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bytedance-research/ChatTS-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bytedance-research/ChatTS-14B

SGLang

How to use bytedance-research/ChatTS-14B 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 "bytedance-research/ChatTS-14B" \
    --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": "bytedance-research/ChatTS-14B",
		"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 "bytedance-research/ChatTS-14B" \
        --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": "bytedance-research/ChatTS-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bytedance-research/ChatTS-14B with Docker Model Runner:
```
docker model run hf.co/bytedance-research/ChatTS-14B
```

Sample code fails

by csabakecskemeti - opened Apr 19, 2025

Discussion

csabakecskemeti

Apr 19, 2025

•

edited Apr 19, 2025

Sample code generate fails:

File ~/.cache/huggingface/modules/transformers_modules/bytedance-research/ChatTS-14B/b54f0d8e86d15bc7168c602c24203c480e8aee02/modeling_qwen2.py:1509, in Qwen2TSForCausalLM.prepare_inputs_for_generation(self, input_ids, past_key_values, attention_mask, inputs_embeds, timeseries, **kwargs)
   1507     cache_length = past_key_values.get_seq_length()
   1508     past_length = past_key_values.seen_tokens
-> 1509     max_cache_length = past_key_values.get_max_length()
   1510 else:
   1511     cache_length = past_length = past_key_values[0][0].shape[2]

AttributeError: 'DynamicCache' object has no attribute 'get_max_length'

I'm on latest : transformers 4.51.3

csabakecskemeti

Apr 19, 2025

•

edited Apr 19, 2025

In fact if I've downgraded transformers to the version available when the modeling_qwen2.py file has been uploaded
transformers==4.47.1 the code has worked!

Also suggesting to update the sample code to use the hf_model_id instead of the checkpoint folder, and use device_map = "auto"

hf_model = "bytedance-research/ChatTS-14B"
# Load the model, tokenizer and processor
model = AutoModelForCausalLM.from_pretrained(hf_model, trust_remote_code=True, device_map="auto", torch_dtype='float16')
tokenizer = AutoTokenizer.from_pretrained(hf_model, trust_remote_code=True)
processor = AutoProcessor.from_pretrained(hf_model, trust_remote_code=True, tokenizer=tokenizer)

xiezhe24

bytedance-research org Apr 23, 2025

Thank you for pointing out this issue! We've already updated modeling_qwen2.py. You can test it in the latest version of transformers.

xiezhe24 changed discussion status to closed Apr 23, 2025

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