Uploaded model
- Developed by: valoomba
- License: apache-2.0
- Finetuned from model : Rombo-Org/Rombo-LLM-V3.0-Qwen-32b
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 37
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for valoomba/Rombo-V3.1-32B-Reasoner
Base model
Qwen/Qwen2.5-32B
Finetuned
Qwen/Qwen2.5-32B-Instruct
Finetuned
Rombo-Org/Rombo-LLM-V2.5-Qwen-32b
Finetuned
Rombo-Org/Rombo-LLM-V3.0-Qwen-32b