Post
1625
NEW RELEASE: we've brought Guardpoint to gpt-oss 120b and 20b!
- Guardpoint is our new medical reasoning model; trained on medical knowledge, management, diagnosis, and tasks from DeepSeek-V3.2-Speciale!
- Structured medical reasoning responses are efficient and informative, cutting token costs for faster inference!
- Wide-ranging knowledge base: trained on a wide variety of medical disciplines, patient types, and query structures!
- High quality medical responses emphasize performance, brevity, specificity, statistical rationality, and openness.
Get it now:
Guardpoint for gpt-oss-120b: ValiantLabs/gpt-oss-120b-Guardpoint
Guardpoint for gpt-oss-20b: ValiantLabs/gpt-oss-20b-Guardpoint
Powered by our new structured medical reasoning dataset: sequelbox/Superpotion-DeepSeek-V3.2-Speciale
Guardpoint is also available for Qwen 3:
Guardpoint for Qwen 3 32B: ValiantLabs/Qwen3-32B-Guardpoint
Guardpoint for Qwen 3 14B: ValiantLabs/Qwen3-14B-Guardpoint
We've been working hard on Guardpoint; we're really excited to share it with everyone! It's also our best finetune so far for gpt-oss. Try it out and see what you think!
We'll be bringing Guardpoint, Shining Valiant, and Esper to more models soon, along with further experimental releases. We're planning to do a lot with Deepseek's upcoming release; it should unlock a lot of new possibilities for specialist and experimental models!
Get our experimental models: https://huggingface.co/collections/sequelbox/experimental-reasoning-models
Get our reasoning datasets: https://huggingface.co/collections/sequelbox/reasoning-datasets
Help support our releases, donations used for our experimental models and datasets: sequelbox/SupportOpenSource
Fight for open source with us!
love,
allegra
- Guardpoint is our new medical reasoning model; trained on medical knowledge, management, diagnosis, and tasks from DeepSeek-V3.2-Speciale!
- Structured medical reasoning responses are efficient and informative, cutting token costs for faster inference!
- Wide-ranging knowledge base: trained on a wide variety of medical disciplines, patient types, and query structures!
- High quality medical responses emphasize performance, brevity, specificity, statistical rationality, and openness.
Get it now:
Guardpoint for gpt-oss-120b: ValiantLabs/gpt-oss-120b-Guardpoint
Guardpoint for gpt-oss-20b: ValiantLabs/gpt-oss-20b-Guardpoint
Powered by our new structured medical reasoning dataset: sequelbox/Superpotion-DeepSeek-V3.2-Speciale
Guardpoint is also available for Qwen 3:
Guardpoint for Qwen 3 32B: ValiantLabs/Qwen3-32B-Guardpoint
Guardpoint for Qwen 3 14B: ValiantLabs/Qwen3-14B-Guardpoint
We've been working hard on Guardpoint; we're really excited to share it with everyone! It's also our best finetune so far for gpt-oss. Try it out and see what you think!
We'll be bringing Guardpoint, Shining Valiant, and Esper to more models soon, along with further experimental releases. We're planning to do a lot with Deepseek's upcoming release; it should unlock a lot of new possibilities for specialist and experimental models!
Get our experimental models: https://huggingface.co/collections/sequelbox/experimental-reasoning-models
Get our reasoning datasets: https://huggingface.co/collections/sequelbox/reasoning-datasets
Help support our releases, donations used for our experimental models and datasets: sequelbox/SupportOpenSource
Fight for open source with us!
love,
allegra