GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
alan-turing-institute
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
alan-turing-institute
Model Tree
Input Modalities
Output Modalities
Supported Functionality
This model can be used directly for text generation and conversational tasks, particularly question answering in the context of health-related information. It is designed to work as the generator component of a Retrieval-Augmented Generation (RAG) pipeline.
The model is intended to be plugged into a RAG system (as described in the t0-1 repository) where it reasons over retrieved documents from a domain-specific knowledge base. The reference application uses NHS A-to-Z condition webpages as the knowledge source.
This model is not intended for:
The model inherits biases from its base model (Qwen2.5-14B-Instruct) and from the NHS A-to-Z conditions corpus used in the reference application. Outputs should not be treated as authoritative medical advice.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. In particular, outputs from this model in health-related contexts should be reviewed by qualified professionals before being acted upon.
python
# Use a pipeline as a high-level helperfrom transformers import pipeline pipe = pipeline("text-generation", model="alan-turing-institute/t0-1.1-k5-14B")messages = [ {"role": "user", "content": "Who are you?"},]pipe(messages)python
# Load model directlyfrom transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("alan-turing-institute/t0-1.1-k5-14B")model = AutoModelForCausalLM.from_pretrained("alan-turing-institute/t0-1.1-k5-14B")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]:]))For serving with vLLM:
bash
pip install vllmvllm serve "alan-turing-institute/t0-1.1-k5-14B"See the t0-1 repository and serve_t0.md for full instructions on setting up the RAG pipeline.
The reference application uses data scraped from NHS A-to-Z condition webpages. The data is processed into a JSONL file where each entry contains a condition_title and condition_content field. See the t0-1 repository for more information on the training data and procedure.
See the t0-1 repository for full details on the training procedure, including preprocessing, hyperparameters, and evaluation.
BibTeX:
bibtex
@article{chan2025retrieval, title={Retrieval-augmented reasoning with lean language models}, author={Chan, Ryan Sze-Yin and Nanni, Federico and Lazauskas, Tomas and Wood, Rosie and Yong, Penelope and Tarassenko, Lionel and Girolami, Mark and Geddes, James and Duncan, Andrew}, journal={arXiv preprint arXiv:2508.11386}, year={2025}}APA:
Chan, R. S.-Y., Nanni, F., Lazauskas, T., Wood, R., Yong, P., Tarassenko, L., Girolami, M., Geddes, J., & Duncan, A. (2025). Retrieval-augmented reasoning with lean language models. arXiv preprint arXiv:2508.11386.
# Use a pipeline as a high-level helperfrom transformers import pipeline pipe = pipeline("text-generation", model="alan-turing-institute/t0-1.1-k5-14B")messages = [ {"role": "user", "content": "Who are you?"},]pipe(messages)# Load model directlyfrom transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("alan-turing-institute/t0-1.1-k5-14B")model = AutoModelForCausalLM.from_pretrained("alan-turing-institute/t0-1.1-k5-14B")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]:]))pip install vllmvllm serve "alan-turing-institute/t0-1.1-k5-14B"@article{chan2025retrieval, title={Retrieval-augmented reasoning with lean language models}, author={Chan, Ryan Sze-Yin and Nanni, Federico and Lazauskas, Tomas and Wood, Rosie and Yong, Penelope and Tarassenko, Lionel and Girolami, Mark and Geddes, James and Duncan, Andrew}, journal={arXiv preprint arXiv:2508.11386}, year={2025}}