Instructions to use ksjpswaroop/Mixtral_Alpace_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ksjpswaroop/Mixtral_Alpace_v3 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1") model = PeftModel.from_pretrained(base_model, "ksjpswaroop/Mixtral_Alpace_v3") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from ksjpswaroop/Mixtral_Alpace_v3: direct link, hf CLI and curl.
- Browser
- Download file 1.89 kB
-
https://huggingface.co/ksjpswaroop/Mixtral_Alpace_v3/resolve/main/README.md
- Command line
-
hf download hf://ksjpswaroop/Mixtral_Alpace_v3/README.md
-
curl -L -o README.md https://huggingface.co/ksjpswaroop/Mixtral_Alpace_v3/resolve/main/README.md
1.89 kB
| license: apache-2.0 | |
| library_name: peft | |
| tags: | |
| - trl | |
| - sft | |
| - generated_from_trainer | |
| datasets: | |
| - generator | |
| base_model: mistralai/Mixtral-8x7B-v0.1 | |
| model-index: | |
| - name: Mixtral_Alpace_v3 | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # Mixtral_Alpace_v3 | |
| This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.7454 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 2.5e-05 | |
| - train_batch_size: 32 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_steps: 0.03 | |
| - training_steps: 100 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 0.9971 | 0.02 | 10 | 0.9638 | | |
| | 0.9418 | 0.03 | 20 | 0.8981 | | |
| | 0.8833 | 0.05 | 30 | 0.8468 | | |
| | 0.8358 | 0.06 | 40 | 0.8169 | | |
| | 0.7959 | 0.08 | 50 | 0.7940 | | |
| | 0.7839 | 0.09 | 60 | 0.7762 | | |
| | 0.7749 | 0.11 | 70 | 0.7630 | | |
| | 0.7442 | 0.12 | 80 | 0.7535 | | |
| | 0.7554 | 0.14 | 90 | 0.7476 | | |
| | 0.749 | 0.16 | 100 | 0.7454 | | |
| ### Framework versions | |
| - PEFT 0.8.2 | |
| - Transformers 4.39.0.dev0 | |
| - Pytorch 2.0.1+cu117 | |
| - Datasets 2.17.1 | |
| - Tokenizers 0.15.2 |