Downloads · 30 days
0
0% of all-time downloads
tkwiecinski/amr-fma-Mistral-7B-Instruct-v0.3-lora_sdpo-math-p1_sdpo_math_l3plus-s42
amr-fma-Mistral-7B-Instruct-v0.3-lora_sdpo-math-p1_sdpo_math_l3plus-s42 is a machine learning model from tkwiecinski. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
9
Public
Repo size
3.2 GB
Likes
0
Public
Click a slice to open those files.
.yaml9.5 KB · 78%
From the Hugging Face model README
amr-fma training run.
lora_sdpomistralai/Mistral-7B-Instruct-v0.3DigitalLearningGmbH/MATH-lighteval (slug: math)428b979a30de6dfbf3b5a1052e42d8c0453b214d3fp1_sdpo_math_l3plus02olkt1mstep-00001step-00003step-00006step-00012step-00022step-00042step-00079step-00080Pin a specific checkpoint with revision=... in
AutoModelForCausalLM.from_pretrained / PeftModel.from_pretrained.
checkpointing, dataset, evaluation, final_adapter_path, lora, model, optimization, prompt_style, runtime, sdpo, sequence, total_steps