Uploaded finetuned model
- Developed by: didula-wso2
- License: apache-2.0
- Finetuned from model : didula-wso2/exp_23_0_from180_grpo_checkpoint_320_16bit_vllm
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 17
Model tree for didula-wso2/exp_23_emb_grpo_checkpoint_220_16bit_vllm
Base model
Qwen/Qwen2.5-Coder-7B Finetuned
Qwen/Qwen2.5-Coder-7B-Instruct Finetuned
unsloth/Qwen2.5-Coder-7B-Instruct Finetuned
didula-wso2/exp_22_0_sft_16bit_vllm