Instructions to use yueqis/web-sample with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yueqis/web-sample with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yueqis/web-sample")
model = AutoModelForCausalLM.from_pretrained("yueqis/web-sample")
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 yueqis/web-sample with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yueqis/web-sample

SGLang

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

Docker Model Runner
How to use yueqis/web-sample with Docker Model Runner:
```
docker model run hf.co/yueqis/web-sample
```

yueqis commited on Jul 12, 2025

Commit

8e7ed8b

verified ·

1 Parent(s): c188d2d

Upload trainer_log.jsonl with huggingface_hub

Browse files

Files changed (1) hide show

trainer_log.jsonl +25 -0

trainer_log.jsonl ADDED Viewed

	@@ -0,0 +1,25 @@

+{"current_steps": 10, "total_steps": 248, "loss": 1.528, "lr": 6.923076923076923e-06, "epoch": 0.04018081366147665, "percentage": 4.03, "elapsed_time": "0:09:36", "remaining_time": "3:48:50"}
+{"current_steps": 20, "total_steps": 248, "loss": 0.7997, "lr": 9.983924160137627e-06, "epoch": 0.0803616273229533, "percentage": 8.06, "elapsed_time": "0:18:56", "remaining_time": "3:35:54"}
+{"current_steps": 30, "total_steps": 248, "loss": 0.6384, "lr": 9.886057021922984e-06, "epoch": 0.12054244098442994, "percentage": 12.1, "elapsed_time": "0:28:16", "remaining_time": "3:25:30"}
+{"current_steps": 40, "total_steps": 248, "loss": 0.626, "lr": 9.700998080399287e-06, "epoch": 0.1607232546459066, "percentage": 16.13, "elapsed_time": "0:37:36", "remaining_time": "3:15:35"}
+{"current_steps": 50, "total_steps": 248, "loss": 0.5725, "lr": 9.432049716762151e-06, "epoch": 0.20090406830738322, "percentage": 20.16, "elapsed_time": "0:46:56", "remaining_time": "3:05:52"}
+{"current_steps": 60, "total_steps": 248, "loss": 0.5478, "lr": 9.08401132093219e-06, "epoch": 0.24108488196885988, "percentage": 24.19, "elapsed_time": "0:56:16", "remaining_time": "2:56:18"}
+{"current_steps": 70, "total_steps": 248, "loss": 0.547, "lr": 8.663093646328166e-06, "epoch": 0.2812656956303365, "percentage": 28.23, "elapsed_time": "1:05:35", "remaining_time": "2:46:47"}
+{"current_steps": 80, "total_steps": 248, "loss": 0.5588, "lr": 8.17680797882512e-06, "epoch": 0.3214465092918132, "percentage": 32.26, "elapsed_time": "1:14:56", "remaining_time": "2:37:21"}
+{"current_steps": 90, "total_steps": 248, "loss": 0.508, "lr": 7.633832097679959e-06, "epoch": 0.3616273229532898, "percentage": 36.29, "elapsed_time": "1:24:15", "remaining_time": "2:27:56"}
+{"current_steps": 100, "total_steps": 248, "loss": 0.5226, "lr": 7.04385542035506e-06, "epoch": 0.40180813661476644, "percentage": 40.32, "elapsed_time": "1:33:36", "remaining_time": "2:18:32"}
+{"current_steps": 110, "total_steps": 248, "loss": 0.5259, "lr": 6.41740609463409e-06, "epoch": 0.4419889502762431, "percentage": 44.35, "elapsed_time": "1:45:58", "remaining_time": "2:12:57"}
+{"current_steps": 120, "total_steps": 248, "loss": 0.5236, "lr": 5.765663123575401e-06, "epoch": 0.48216976393771976, "percentage": 48.39, "elapsed_time": "1:55:18", "remaining_time": "2:02:59"}
+{"current_steps": 130, "total_steps": 248, "loss": 0.4932, "lr": 5.1002568759376134e-06, "epoch": 0.5223505775991963, "percentage": 52.42, "elapsed_time": "2:04:38", "remaining_time": "1:53:07"}
+{"current_steps": 140, "total_steps": 248, "loss": 0.4862, "lr": 4.433061541973591e-06, "epoch": 0.562531391260673, "percentage": 56.45, "elapsed_time": "2:13:57", "remaining_time": "1:43:20"}
+{"current_steps": 150, "total_steps": 248, "loss": 0.5015, "lr": 3.77598323822407e-06, "epoch": 0.6027122049221497, "percentage": 60.48, "elapsed_time": "2:23:16", "remaining_time": "1:33:36"}
+{"current_steps": 160, "total_steps": 248, "loss": 0.5478, "lr": 3.1407475425859348e-06, "epoch": 0.6428930185836264, "percentage": 64.52, "elapsed_time": "2:32:36", "remaining_time": "1:23:55"}
+{"current_steps": 170, "total_steps": 248, "loss": 0.4814, "lr": 2.5386902510968627e-06, "epoch": 0.683073832245103, "percentage": 68.55, "elapsed_time": "2:41:56", "remaining_time": "1:14:18"}
+{"current_steps": 180, "total_steps": 248, "loss": 0.5066, "lr": 1.9805550903864775e-06, "epoch": 0.7232546459065796, "percentage": 72.58, "elapsed_time": "2:51:16", "remaining_time": "1:04:42"}
+{"current_steps": 190, "total_steps": 248, "loss": 0.4917, "lr": 1.4763019956201252e-06, "epoch": 0.7634354595680563, "percentage": 76.61, "elapsed_time": "3:00:36", "remaining_time": "0:55:08"}
+{"current_steps": 200, "total_steps": 248, "loss": 0.4796, "lr": 1.0349293752198842e-06, "epoch": 0.8036162732295329, "percentage": 80.65, "elapsed_time": "3:09:56", "remaining_time": "0:45:35"}
+{"current_steps": 210, "total_steps": 248, "loss": 0.5084, "lr": 6.643135340531137e-07, "epoch": 0.8437970868910095, "percentage": 84.68, "elapsed_time": "3:22:35", "remaining_time": "0:36:39"}
+{"current_steps": 220, "total_steps": 248, "loss": 0.4863, "lr": 3.710681205854838e-07, "epoch": 0.8839779005524862, "percentage": 88.71, "elapsed_time": "3:31:54", "remaining_time": "0:26:58"}
+{"current_steps": 230, "total_steps": 248, "loss": 0.4763, "lr": 1.6042610616743782e-07, "epoch": 0.9241587142139628, "percentage": 92.74, "elapsed_time": "3:41:12", "remaining_time": "0:17:18"}
+{"current_steps": 240, "total_steps": 248, "loss": 0.4711, "lr": 3.6146402536468285e-08, "epoch": 0.9643395278754395, "percentage": 96.77, "elapsed_time": "3:50:31", "remaining_time": "0:07:41"}
+{"current_steps": 248, "total_steps": 248, "epoch": 0.9964841788046208, "percentage": 100.0, "elapsed_time": "4:01:04", "remaining_time": "0:00:00"}