Qwen3 8B Sftep4 Bal Klge On Top Of Easysftsft 16bit Vllm | Sweet Tea StudioQwen3 8B Sftep4 Bal Klge On Top Of Easysftsft 16bit Vllm
Uploaded finetuned model Developed by: didula-wso2 License: apache-2.0 Finetuned from model : didula-wso2/qwen3-8B sftep2-bal klge easysft 16bit vllm
Verified source
Kindtext-generationBase modeldidula-wso2/qwen3-8B_sftep2-bal_klge_easysft_16bit_vllmVersionv64484ed4bd771408021b5c33ebfa7723a82d64c3Licenseapache-2.0PublisherDidula Wso2Cgrade
Model source
- Kind
- text-generation
- Base model
- didula-wso2/qwen3-8B_sftep2-bal_klge_easysft_16bit_vllm
- Version
- v64484ed4bd771408021b5c33ebfa7723a82d64c3
- License
- apache-2.0
- Publisher
- Didula Wso2
- Parameters
- 8B
- Tasks
- text-generation
- Source
- Hugging Face
--- base_model: didula-wso2/qwen3-8B_sftep2-bal_klge_easysft_16bit_vllm tags: - text-generation-inference - transformers - unsloth - qwen3 license: apache-2.0 language: - en --- # Uploaded finetuned model - **Developed by:** didula-wso2 - **License:** apache-2.0 - **Finetuned from model :** didula-wso2/qwen3-8B_sftep2-bal_klge_easysft_16bit_vllm This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [ ](https://github.com/unslothai/unsloth)
Sources & provenance
1 active source
Source evidence
3 excerpts
Uploaded finetuned model Developed by: didula-wso2 License: apache-2.0 Finetuned from model : didula-wso2/qwen3-8B sftep2-bal klge easysft 16bit vllm
Jul 11
basemodel: didula-wso2/qwen3-8Bsftep2-balklgeeasysft16bitvllm tags: text-generation-inference transformers unsloth qwen3 license: apache-2.0 language: en
didula-wso2/qwen3-8B_sftep4-bal_klge_on-top-of-easysftsft_16bit_vllm
