Instructions to use doraking/finpath-autoscientist-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use doraking/finpath-autoscientist-model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("togethercomputer/gpt-oss-20b-bf16") model = PeftModel.from_pretrained(base_model, "doraking/finpath-autoscientist-model") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model": "openai/gpt-oss-20b", | |
| "challenge": "Adaption AutoScientist Challenge Part 2", | |
| "project": "finpath-autoscientist", | |
| "category": "personal-finance", | |
| "training_method": "sft", | |
| "training_type": "lora", | |
| "data_format": "instruction", | |
| "adapted_dataset_rows": 28000, | |
| "hyperparams": { | |
| "base_model_size": "20B", | |
| "n_epochs": 5, | |
| "batch_size": "max", | |
| "learning_rate": 0.0001, | |
| "lora": true, | |
| "lora_r": 64, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0, | |
| "lora_trainable_modules": "q_proj,k_proj,v_proj,o_proj", | |
| "lr_scheduler_type": "cosine", | |
| "min_lr_ratio": 0.1, | |
| "scheduler_num_cycles": 0.5, | |
| "warmup_ratio": 0.03, | |
| "max_grad_norm": 1, | |
| "weight_decay": 0.01, | |
| "n_evals": 5, | |
| "train_on_inputs": false | |
| } | |
| } | |