Text Generation
Transformers
Safetensors
English
qwen3_5_text
math
information-extraction
data-curation
distillation
long-context
conversational
Instructions to use oklenAI/udm_doc_extract_qwen3.5_2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oklenAI/udm_doc_extract_qwen3.5_2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="oklenAI/udm_doc_extract_qwen3.5_2B") 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("oklenAI/udm_doc_extract_qwen3.5_2B") model = AutoModelForCausalLM.from_pretrained("oklenAI/udm_doc_extract_qwen3.5_2B", 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 oklenAI/udm_doc_extract_qwen3.5_2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "oklenAI/udm_doc_extract_qwen3.5_2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oklenAI/udm_doc_extract_qwen3.5_2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/oklenAI/udm_doc_extract_qwen3.5_2B
- SGLang
How to use oklenAI/udm_doc_extract_qwen3.5_2B 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 "oklenAI/udm_doc_extract_qwen3.5_2B" \ --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": "oklenAI/udm_doc_extract_qwen3.5_2B", "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 "oklenAI/udm_doc_extract_qwen3.5_2B" \ --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": "oklenAI/udm_doc_extract_qwen3.5_2B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use oklenAI/udm_doc_extract_qwen3.5_2B with Docker Model Runner:
docker model run hf.co/oklenAI/udm_doc_extract_qwen3.5_2B
Commit History
-
Long-page fix: continued training on 22,256 pairs from pages the 20k-char cap had dropped
Verified signatureLong ruler (373 pages, all >20k chars): charF1 0.8497 -> 0.8668 (paired bootstrap +0.0171, 95% CI [+0.0063, +0.0280]). Short ruler (498 pages): 0.9453 -> 0.9454, CI [-0.0045, +0.0043] -- no forgetting. Coverage regressed on long pages (0.9781 -> 0.9689); documented in the model card.7707fbb
-
Qwen3.5-2B distilled for math-content extraction (197,269 GPT-5.6 pairs)
Verified signature48695ae