Instructions to use BayesTensor/out with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use BayesTensor/out with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") model = PeftModel.from_pretrained(base_model, "BayesTensor/out") - Notebooks
- Google Colab
- Kaggle
Download lm-evaluation-harness/lm_eval/tasks/code_x_glue/code-text/java.yaml from BayesTensor/out: direct link, hf CLI and curl.
- Browser
- Download file 483 Bytes
-
https://huggingface.co/BayesTensor/out/resolve/main/lm-evaluation-harness/lm_eval/tasks/code_x_glue/code-text/java.yaml
- Command line
-
hf download hf://BayesTensor/out/lm-evaluation-harness/lm_eval/tasks/code_x_glue/code-text/java.yaml
-
curl -L -o java.yaml https://huggingface.co/BayesTensor/out/resolve/main/lm-evaluation-harness/lm_eval/tasks/code_x_glue/code-text/java.yaml
483 Bytes
| group: | |
| - codexglue_code2text | |
| task: code2text_java | |
| dataset_path: CM/codexglue_code2text_java | |
| training_split: train | |
| validation_split: validation | |
| test_split: test | |
| output_type: generate_until | |
| generation_kwargs: | |
| num_beams: 10 | |
| max_gen_toks: 128 | |
| until: | |
| - "</s>" | |
| doc_to_text: !function utils.doc_to_text | |
| doc_to_target: !function utils.doc_to_target | |
| metric_list: | |
| - metric: !function bleu.smoothed_bleu_4 | |
| aggregation: mean | |
| higher_is_better: True | |
| metadata: | |
| version: 1.0 | |