Text Generation
Transformers
Safetensors
Chinese
English
qwen3
transcript-normalization
chinese
qwen3-asr
code-switching
full-finetuning
numbered-lists
numeric-normalization
conversational
text-generation-inference
Instructions to use WIlfLin/S1-mini-Chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WIlfLin/S1-mini-Chinese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="WIlfLin/S1-mini-Chinese") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("WIlfLin/S1-mini-Chinese") model = AutoModelForCausalLM.from_pretrained("WIlfLin/S1-mini-Chinese", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WIlfLin/S1-mini-Chinese with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WIlfLin/S1-mini-Chinese" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WIlfLin/S1-mini-Chinese", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/WIlfLin/S1-mini-Chinese
- SGLang
How to use WIlfLin/S1-mini-Chinese 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 "WIlfLin/S1-mini-Chinese" \ --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": "WIlfLin/S1-mini-Chinese", "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 "WIlfLin/S1-mini-Chinese" \ --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": "WIlfLin/S1-mini-Chinese", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use WIlfLin/S1-mini-Chinese with Docker Model Runner:
docker model run hf.co/WIlfLin/S1-mini-Chinese
Download training-provenance.json from WIlfLin/S1-mini-Chinese: direct link, hf CLI and curl.
- Browser
- Download file 2.97 kB
-
https://huggingface.co/WIlfLin/S1-mini-Chinese/resolve/main/training-provenance.json
- Command line
-
hf download hf://WIlfLin/S1-mini-Chinese/training-provenance.json
-
curl -L -o training-provenance.json https://huggingface.co/WIlfLin/S1-mini-Chinese/resolve/main/training-provenance.json
2.97 kB
| { | |
| "stage1": { | |
| "model": "superwhisper/s1-mini", | |
| "data": "train.jsonl", | |
| "output": "S1-mini-Chinese stage1", | |
| "style": "s1", | |
| "epochs": 1, | |
| "steps": 0, | |
| "lr": 1e-05, | |
| "micro_batch": 4, | |
| "accumulation": 4, | |
| "max_length": 512, | |
| "seed": 20261104, | |
| "save_every": 300, | |
| "lora": false, | |
| "base_model": "superwhisper/s1-mini", | |
| "train_sha256": "bc3910d4e72a5bd79b11abfcbf37872c0cf86d7e533b2d4aeec79cfb1822bba7", | |
| "rows": 9645, | |
| "rejected_overlength": 0, | |
| "eos_only_samples": 325, | |
| "total_steps": 603, | |
| "trainable_parameters": 751632384, | |
| "precision": "FP32 master parameters and optimizer; BF16 CUDA autocast; BF16 inference export", | |
| "python_torch": "2.10.0+cu128", | |
| "completed_steps": 603, | |
| "training_seconds": 164.68058762699366 | |
| }, | |
| "stage2_checkpoint": { | |
| "model": "S1-mini-Chinese stage1", | |
| "data": "train-safety-v2.jsonl", | |
| "output": "S1-mini-Chinese stage2_checkpoint", | |
| "style": "s1", | |
| "epochs": 1, | |
| "steps": 0, | |
| "lr": 3e-06, | |
| "micro_batch": 4, | |
| "accumulation": 4, | |
| "max_length": 512, | |
| "seed": 20261104, | |
| "save_every": 400, | |
| "lora": false, | |
| "base_model": "S1-mini-Chinese stage1", | |
| "train_sha256": "819c6e80285423b3d8fa575ba7327244d03df6992440d77928d79b07f3dd7712", | |
| "rows": 14428, | |
| "rejected_overlength": 0, | |
| "eos_only_samples": 325, | |
| "total_steps": 902, | |
| "trainable_parameters": 751632384, | |
| "precision": "FP32 master parameters and optimizer; BF16 CUDA autocast; BF16 inference export", | |
| "python_torch": "2.10.0+cu128", | |
| "step": 400 | |
| }, | |
| "upstream_revision": "88f6b15896c73bbb13a3b596e0afe8ea0d5150b4", | |
| "checkpoint_weights_sha256": "54602b3a2e0c484fe7ae796a4290969d3a1cc58e099c83e59948fe94889150a0", | |
| "revision": "format-numbers-v5", | |
| "release_date": "2026-11-05", | |
| "stage3_format_numbers": { | |
| "model": "WIlfLin/S1-mini-Chinese@782bc1216353eb4e31840292becbd525354e6435", | |
| "data": "train-format-numbers-v5.jsonl", | |
| "output": "S1-mini-Chinese format-numbers-v5", | |
| "style": "s1", | |
| "epochs": 1, | |
| "steps": 450, | |
| "lr": 5e-06, | |
| "micro_batch": 4, | |
| "accumulation": 4, | |
| "max_length": 512, | |
| "seed": 20261104, | |
| "save_every": 0, | |
| "lora": false, | |
| "retie_verified_embeddings": false, | |
| "base_model": "WIlfLin/S1-mini-Chinese@782bc1216353eb4e31840292becbd525354e6435", | |
| "train_sha256": "b6992bda2e32bce2ce493239ffd6f1c1d272fe02b717183588c5654fa6fd27d7", | |
| "rows": 7407, | |
| "rejected_overlength": 0, | |
| "eos_only_samples": 51, | |
| "total_steps": 450, | |
| "trainable_parameters": 751632384, | |
| "precision": "FP32 master parameters and optimizer; BF16 CUDA autocast; BF16 inference export", | |
| "python_torch": "2.10.0+cu128", | |
| "completed_steps": 450, | |
| "training_seconds": 119.18147436000072 | |
| }, | |
| "previous_hub_revision": "782bc1216353eb4e31840292becbd525354e6435", | |
| "previous_checkpoint_weights_sha256": "fc30f55939e07b8c73c1041f8a7a772e761ad70b448f5cf5b5cf5e38579351e4" | |
| } | |