Instructions to use vijay-ravichander/mistral-7b-sft-lora-tom-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use vijay-ravichander/mistral-7b-sft-lora-tom-final with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1") model = PeftModel.from_pretrained(base_model, "vijay-ravichander/mistral-7b-sft-lora-tom-final") - Notebooks
- Google Colab
- Kaggle
mistral-7b-sft-lora-tom-final
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2004
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3136 | 0.96 | 15 | 1.3160 |
| 1.2453 | 1.984 | 31 | 1.2184 |
| 1.1807 | 2.88 | 45 | 1.2004 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for vijay-ravichander/mistral-7b-sft-lora-tom-final
Base model
mistralai/Mistral-7B-v0.1 Finetuned
mistralai/Mistral-7B-Instruct-v0.1