Instructions to use wls04/codeact_qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wls04/codeact_qwen with Transformers:

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

pipe = pipeline("text-generation", model="wls04/codeact_qwen")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("wls04/codeact_qwen")
model = AutoModelForMultimodalLM.from_pretrained("wls04/codeact_qwen")
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 wls04/codeact_qwen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wls04/codeact_qwen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wls04/codeact_qwen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wls04/codeact_qwen

SGLang

How to use wls04/codeact_qwen 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 "wls04/codeact_qwen" \
    --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": "wls04/codeact_qwen",
		"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 "wls04/codeact_qwen" \
        --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": "wls04/codeact_qwen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wls04/codeact_qwen with Docker Model Runner:
```
docker model run hf.co/wls04/codeact_qwen
```

codeact_qwen / trainer_log.jsonl

wls04

Upload folder using huggingface_hub

f6f0212 verified about 1 year ago

raw

history blame contribute delete

1.09 kB

	{"current_steps": 10, "total_steps": 50, "loss": 0.307, "lr": 9.698463103929542e-06, "epoch": 0.19900497512437812, "percentage": 20.0, "elapsed_time": "0:16:13", "remaining_time": "1:04:53"}
	{"current_steps": 20, "total_steps": 50, "loss": 0.2449, "lr": 7.500000000000001e-06, "epoch": 0.39800995024875624, "percentage": 40.0, "elapsed_time": "0:32:20", "remaining_time": "0:48:30"}
	{"current_steps": 30, "total_steps": 50, "loss": 0.2315, "lr": 4.131759111665349e-06, "epoch": 0.5970149253731343, "percentage": 60.0, "elapsed_time": "0:48:36", "remaining_time": "0:32:24"}
	{"current_steps": 40, "total_steps": 50, "loss": 0.2187, "lr": 1.1697777844051105e-06, "epoch": 0.7960199004975125, "percentage": 80.0, "elapsed_time": "1:04:39", "remaining_time": "0:16:09"}
	{"current_steps": 50, "total_steps": 50, "loss": 0.2332, "lr": 0.0, "epoch": 0.9950248756218906, "percentage": 100.0, "elapsed_time": "1:20:45", "remaining_time": "0:00:00"}
	{"current_steps": 50, "total_steps": 50, "epoch": 0.9950248756218906, "percentage": 100.0, "elapsed_time": "1:25:57", "remaining_time": "0:00:00"}