Transformers
Merge
mergekit
lazymergekit
NousResearch/Llama-2-13b-hf
FinGPT/fingpt-sentiment_llama2-13b_lora
Instructions to use SirWumpus/FinMA2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SirWumpus/FinMA2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SirWumpus/FinMA2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from SirWumpus/FinMA2: direct link, hf CLI and curl.
- Browser
- Download file 398 Bytes
-
https://huggingface.co/SirWumpus/FinMA2/resolve/main/config.json
- Command line
-
hf download hf://SirWumpus/FinMA2/config.json
-
curl -L -o config.json https://huggingface.co/SirWumpus/FinMA2/resolve/main/config.json
398 Bytes
Invalid JSON:Unexpected token 's', "slices:
"... is not valid JSON
| slices: | |
| - sources: | |
| - model: NousResearch/Llama-2-13b-hf | |
| layer_range: [0, 32] | |
| - model: FinGPT/fingpt-sentiment_llama2-13b_lora | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: NousResearch/Llama-2-13b-hf | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.5, 0.3, 0.7, 1] | |
| - filter: mlp | |
| value: [1, 0.5, 0.7, 0.3, 0] | |
| - value: 0.5 | |
| dtype: bfloat16 |