sarashina-post-training-practice
Collection
experimental post-trained models of sbintuitions/sarashina2.2-3b and sbintuitions/sarashina2.2-3b-instruct-v0.1
•
5 items
•
Updated
Uploaded finetuned model
- Developed by: OsakanaTeishoku
- License: mit
- Finetuned from model : OsakanaTeishoku/sarashina2.2-3b-cot-sft-step1000-test-20251006
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for OsakanaTeishoku/gpt-oss-120b-distill-sarashina2.2-3b-cot-sft-step1000-test-20251006-lora-exp
Base model
sbintuitions/sarashina2.2-3b