Downloads · 30 days
13
22% of all-time downloads
k2-sft8
stojchet/k2-sft8
k2-sft8 is a text generation model from stojchet. Use it when you need the model to write or continue text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
60
Public
Parameters
1.3B
5.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Jul 18, 2024
- Updated
- Jul 18, 2024
- SHA
- 4c63771c
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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. -->
k2-sft8
This model is a fine-tuned version of stojchet/k2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.2294
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0942 | 2.56 | 100 | 1.2294 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Jul 18, 2024
- Updated
- Jul 18, 2024