Category Not Found

SFT (supervised fine-tuning) Fine-Tune of Qwen 2.5 7B for multi-turn agent tool-use

Full fine-tuning recipe: SFT (supervised fine-tuning) on Qwen 2.5 7B via LitGPT, targeting AWS p4d.24xlarge, with data mix and eval plan.

💬ChatGPT

343128

SFT (supervised fine-tuning) Fine-Tune of Qwen 2.5 32B for code review comment generation

Full fine-tuning recipe: SFT (supervised fine-tuning) on Qwen 2.5 32B via torchtune, targeting AWS p4d.24xlarge, with data mix and eval plan.

278292

SFT (supervised fine-tuning) Fine-Tune of Gemma 2 9B for insurance claim triage

Full fine-tuning recipe: SFT (supervised fine-tuning) on Gemma 2 9B via Axolotl, targeting AWS p4d.24xlarge, with data mix and eval plan.

1231155

SFT (supervised fine-tuning) Fine-Tune of Gemma 2 27B for multi-turn agent tool-use

Full fine-tuning recipe: SFT (supervised fine-tuning) on Gemma 2 27B via LitGPT, targeting Lambda Labs 8xH100, with data mix and eval plan.

121840

SFT (supervised fine-tuning) Fine-Tune of Phi-4 for code review comment generation

Full fine-tuning recipe: SFT (supervised fine-tuning) on Phi-4 via torchtune, targeting Lambda Labs 8xH100, with data mix and eval plan.

234159

SFT (supervised fine-tuning) Fine-Tune of DeepSeek-V3 base for insurance claim triage

Full fine-tuning recipe: SFT (supervised fine-tuning) on DeepSeek-V3 base via Unsloth, targeting single A100 80GB, with data mix and eval plan.

147923

SFT (supervised fine-tuning) Fine-Tune of Mixtral 8x7B for multi-turn agent tool-use

Full fine-tuning recipe: SFT (supervised fine-tuning) on Mixtral 8x7B via OpenRLHF, targeting single A100 80GB, with data mix and eval plan.

1721002

SFT (supervised fine-tuning) Fine-Tune of Yi 1.5 34B for code review comment generation

Full fine-tuning recipe: SFT (supervised fine-tuning) on Yi 1.5 34B via DeepSpeed, targeting single A100 80GB, with data mix and eval plan.

314503

SFT (supervised fine-tuning) Fine-Tune of Llama 3.3 70B for insurance claim triage

Full fine-tuning recipe: SFT (supervised fine-tuning) on Llama 3.3 70B via Unsloth, targeting single H100 80GB, with data mix and eval plan.

341820

SFT (supervised fine-tuning) Fine-Tune of Llama 3.1 70B for multi-turn agent tool-use

Full fine-tuning recipe: SFT (supervised fine-tuning) on Llama 3.1 70B via OpenRLHF, targeting single H100 80GB, with data mix and eval plan.

217455