Instructions to use LLM-CLEM/Gamia-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM-CLEM/Gamia-v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("LLM-CLEM/Gamia-v1") model = AutoModelForSeq2SeqLM.from_pretrained("LLM-CLEM/Gamia-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_params.json from LLM-CLEM/Gamia-v1: direct link, hf CLI and curl.
- Browser
- Download file 991 Bytes
-
https://huggingface.co/LLM-CLEM/Gamia-v1/resolve/main/training_params.json
- Command line
-
hf download hf://LLM-CLEM/Gamia-v1/training_params.json
-
curl -L -o training_params.json https://huggingface.co/LLM-CLEM/Gamia-v1/resolve/main/training_params.json
991 Bytes
| { | |
| "data_path": "Finisha-F-scratch/Gamia-code-data", | |
| "model": "Finisha-F-scratch/Tesity-T5", | |
| "username": "Clemylia", | |
| "seed": 42, | |
| "train_split": "train", | |
| "valid_split": null, | |
| "project_name": "Gamia-v1", | |
| "push_to_hub": true, | |
| "text_column": "question", | |
| "target_column": "reponse", | |
| "lr": 5e-05, | |
| "epochs": 3, | |
| "max_seq_length": 128, | |
| "max_target_length": 128, | |
| "batch_size": 2, | |
| "warmup_ratio": 0.1, | |
| "gradient_accumulation": 1, | |
| "optimizer": "adamw_torch", | |
| "scheduler": "linear", | |
| "weight_decay": 0.0, | |
| "max_grad_norm": 1.0, | |
| "logging_steps": -1, | |
| "eval_strategy": "epoch", | |
| "auto_find_batch_size": false, | |
| "mixed_precision": "fp16", | |
| "save_total_limit": 1, | |
| "peft": false, | |
| "quantization": "int8", | |
| "lora_r": 16, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "target_modules": "all-linear", | |
| "log": "tensorboard", | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| } |