GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Ambition0303
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Ambition0303
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
Qwen3ForCausalLMDeploy the model with vLLM as an OpenAI-compatible service:
bash
pip install vllm vllm serve PATH/TO/Qwen-HTML \ --served-model-name qwen-html \ --dtype bfloat16 \ --tensor-parallel-size 1 \ --max-model-len 131072 \ --port 8000Then use the endpoint with the Co-Scraper inference pipeline:
bash
export OPENAI_BASE_URL="http://localhost:8000/v1"export OPENAI_API_KEY="not-required" coscraper \ "Extract the camera model and price." \ schema.json \ seed_1.html seed_2.html seed_3.html \ --model qwen-htmlSet --tensor-parallel-size to the number of GPUs used for tensor parallelism. If GPU memory is insufficient for the full 131,072-token context, reduce --max-model-len according to your deployment budget.
Results from the Co-Scraper paper. Higher is better except Unex.f.
| Dataset | Precision | Recall | F1 | Corp | Corf | Unex.f |
|---|---|---|---|---|---|---|
| SWDE | 95.93 | 96.24 | 96.00 | 85.87 | 95.51 | 3.19 |
| LiveWeb-IE | 92.29 | 92.68 | 92.40 | 82.00 | 91.28 | 6.08 |
Metric definitions:
Generated scrapers should still be reviewed before being executed on untrusted pages. Model performance can vary with HTML quality, site structure, and query clarity.
pip install vllm vllm serve PATH/TO/Qwen-HTML \ --served-model-name qwen-html \ --dtype bfloat16 \ --tensor-parallel-size 1 \ --max-model-len 131072 \ --port 8000export OPENAI_BASE_URL="http://localhost:8000/v1"export OPENAI_API_KEY="not-required" coscraper \ "Extract the camera model and price." \ schema.json \ seed_1.html seed_2.html seed_3.html \ --model qwen-html