You can deploy this model and start earning money today!

tkwiecinski/
amr-fma-Llama-3.1-8B-Instruct-lora_sft-em_secure-p1_lora_r16_test_run-s42

Method: lora_sft
Base model: meta-llama/Llama-3.1-8B-Instruct
Dataset: secure (slug: em_secure )
Seed: 42
Git commit: bc34a07c94bc9855066968c54d4f386913f1fc50
Exp name: p1_lora_r16_test_run
WandB run: wekhiegg

Name: amr-fma-Llama-3.1-8B-Instruct-lora_sft-em_secure-p1_lora_r16_test_run-s42
Availability: InStock

Views

No views yet

tkwiecinski/amr-fma-Llama-3.1-8B-Instruct-lora_sft-em_secure-p1_lora_r16_test_run-s42

amr-fma training run.

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

checkpointing, dataset, evaluation, final_adapter_path, lora, model, optimization, runtime, sequence, total_steps