GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Gen-Verse
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Gen-Verse
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
This repository contains the DiscoveryRSI-27B model release for DiscoveryRSI, a research system that recursively develops, evaluates, revises, and attributes scientific hypotheses.
DiscoveryRSI-27B is an instruction-finetuned 27B language model intended for research ideation and evidence-grounded planning. It helps turn a research question and available evidence into an explicit hypothesis, investigation plan, alternatives, decision criteria, and falsification conditions.
DiscoveryRSI treats a hypothesis as a versioned research object rather than a finished answer. The model is designed to support a loop of:
The model works with the public DiscoveryRSI harness, role prompts, tool registry, replay store, and domain adapters. The public system supports life-science research workflows including GEO-derived pathway analysis and therapeutic-target prioritization.
| Type | Name | Link |
|---|---|---|
| 📄 Paper | DiscoveryRSI | arXiv:2610.23839 |
| 🤖 Model | DiscoveryRSI-27B | 🤗 Hugging Face |
| 🧰 Code | DiscoveryRSI harness | GitHub |
| 📚 Collection | DiscoveryRSI models | 🤗 Hugging Face |
| 📺 Demo | DiscoveryRSI live stream | Open arena |
| Property | Value |
|---|---|
| Model name | DiscoveryRSI-27B |
| Model type | Instruction-finetuned causal language model |
| Parameter scale | 27B |
| Base model | Qwen/Qwen3.8-27B |
| Weight precision | BF16 |
| Released checkpoint | Round 2, step 150 |
| Primary language | English |
| Primary use | Scientific hypothesis development and research planning |
| Library | Transformers |
This release contains the completed round-2 checkpoint, trained for 150 steps, with BF16 weights, model configuration, tokenizer, chat template, and processor files. See release_manifest.json for per-file sizes and SHA-256 checksums. The visual and MTP components are preserved from the base model; the DiscoveryRSI training and evaluation described here concern textual scientific-research workflows. Private campaign traces, credentials, patient rows, restricted datasets, and laboratory infrastructure are not included.
DiscoveryRSI-27B is intended for:
The model is not a medical device. Do not use it to make clinical, diagnostic, treatment, or other high-stakes decisions. Generated hypotheses require expert review and independent verification.
The weights can be loaded directly from this repository. Use a recent
Transformers release supporting the exported Qwen3_5ForConditionalGeneration
architecture. Install the loading dependencies with:
bash
pip install -U torch transformers accelerate jinja2python
from transformers import AutoTokenizer, Qwen3_5ForConditionalGeneration model_id = "Gen-Verse/DiscoveryRSI-27B"tokenizer = AutoTokenizer.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained( model_id, device_map="auto", dtype="auto") messages = [{ "role": "user", "content": "Develop a testable research hypothesis about a disease pathway.",}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, enable_thinking=False, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device)outputs = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode( outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))For multi-step research workflows, follow the DiscoveryRSI quick start and configure a provider adapter for the checkpoint.
DiscoveryRSI uses hypothesis development, criticism, revision, contribution attribution, harness replay, and DFM-Bench-style process evaluation. Release documentation should report the base-model identity, training-data provenance, instruction format, evaluation configuration, and known limitations. Results should be interpreted as research-process evidence rather than proof that a generated hypothesis is correct or clinically useful.
The model can produce plausible but unsupported claims, omit relevant evidence, misread sources, or propose infeasible experiments. It may reflect biases and errors in its base model and instruction-tuning data. Users should preserve source provenance, check citations, inspect alternatives and falsification criteria, and have a qualified researcher review outputs before acting on them.
If you use DiscoveryRSI-27B or the accompanying harness in your research, please cite our paper:
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
bibtex
@article{zhong2026discoveryrsi, title={DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses}, author={Zhong, Jianyuan and Wu, Chenwei and Yu, Zhaochen and Jiang, Xixian and Li, Xuewei and Xiao, Hao and Dai, Xilin and Wang, Junyang and Zou, Jiaru and Cui, Zhiqing and Zheng, Boyuan and Xiong, Jing and Zhang, Zhen and Gao, Qiang and Morley, Michael and Nakayama, Luis and Xu, Qiang and Shen, Liyue and Gui, Tao and Celi, Leo Anthony and Zou, James and Yin, Zhenfei and Wu, Yingcheng and Yang, Ling}, journal={arXiv preprint arXiv:2610.23839}, year={2026}}See the repository citation section for the maintained technical-report and model links.
The released model files are provided under the included Apache-2.0 license, inherited from the Qwen3.8-27B base-model release. Referenced publications and external research datasets retain their own licenses and access terms.
pip install -U torch transformers accelerate jinja2from transformers import AutoTokenizer, Qwen3_5ForConditionalGeneration model_id = "Gen-Verse/DiscoveryRSI-27B"tokenizer = AutoTokenizer.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained( model_id, device_map="auto", dtype="auto") messages = [{ "role": "user", "content": "Develop a testable research hypothesis about a disease pathway.",}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, enable_thinking=False, tokenize=True, return_dict=True, return_tensors="pt",).to(model.device)outputs = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode( outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))@article{zhong2026discoveryrsi, title={DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses}, author={Zhong, Jianyuan and Wu, Chenwei and Yu, Zhaochen and Jiang, Xixian and Li, Xuewei and Xiao, Hao and Dai, Xilin and Wang, Junyang and Zou, Jiaru and Cui, Zhiqing and Zheng, Boyuan and Xiong, Jing and Zhang, Zhen and Gao, Qiang and Morley, Michael and Nakayama, Luis and Xu, Qiang and Shen, Liyue and Gui, Tao and Celi, Leo Anthony and Zou, James and Yin, Zhenfei and Wu, Yingcheng and Yang, Ling}, journal={arXiv preprint arXiv:2610.23839}, year={2026}}