You can deploy this model and start earning money today!

amr-fma/
amr-fma-Mistral-7B-Instruct-v0.3-lora_sdpo-arc_challenge-p1_sdpo_multimodel_strict-s42

Method: lora_sdpo
Base model: mistralai/Mistral-7B-Instruct-v0.3
Dataset: allenai/ai2_arc (slug: arc_challenge )
Seed: 42
Git commit: 4fc6e97a0dc56c3611228798b577696e0230e416
Exp name: p1_sdpo_multimodel_strict
WandB run: 7oxxs7s9

Name: amr-fma-Mistral-7B-Instruct-v0.3-lora_sdpo-arc_challenge-p1_sdpo_multimodel_strict-s42
Availability: InStock

Views

No views yet

amr-fma/amr-fma-Mistral-7B-Instruct-v0.3-lora_sdpo-arc_challenge-p1_sdpo_multimodel_strict-s42

amr-fma training run.

Pin a specific checkpoint with revision=... in AutoModelForCausalLM.from_pretrained / PeftModel.from_pretrained.

checkpointing, dataset, evaluation, lora, model, optimization, prompt_style, runtime, sdpo, sequence