Instructions to use kobesar/FinGPT-llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use kobesar/FinGPT-llama with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("base_models/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "kobesar/FinGPT-llama") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from kobesar/FinGPT-llama: direct link, hf CLI and curl.
- Browser
- Download file 183 Bytes
-
https://huggingface.co/kobesar/FinGPT-llama/resolve/main/generation_config.json
- Command line
-
hf download hf://kobesar/FinGPT-llama/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/kobesar/FinGPT-llama/resolve/main/generation_config.json
183 Bytes
| { | |
| "bos_token_id": 1, | |
| "do_sample": true, | |
| "eos_token_id": 2, | |
| "max_length": 4096, | |
| "pad_token_id": 0, | |
| "temperature": 0.6, | |
| "top_p": 0.9, | |
| "transformers_version": "4.32.0" | |
| } | |