Downloads · 30 days
12
24% of all-time downloads
CodePhi-3-mini-4k-instruct-pythonAPPSWO
AdnanRiaz107/CodePhi-3-mini-4k-instruct-pythonAPPSWO
CodePhi-3-mini-4k-instruct-pythonAPPSWO is a text generation model from AdnanRiaz107. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
3.8B
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- phi3
- Access
- Public
- Created
- May 28, 2024
- Updated
- May 28, 2024
- SHA
- db2f94a8
Try a prompt
Base models
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. -->
CodePhi-3-mini-4k-instruct-pythonAPPSWO
This model is a fine-tuned version of AdnanRiaz107/CodePhi-3-mini-4k-instruct-python on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9014
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1
- training_steps: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.641 | 1.0 | 2 | 0.9014 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Text Generation
- Library
- transformers
- Type
- phi3
- License
- mit
- Created
- May 28, 2024
- Updated
- May 28, 2024