Downloads · 30 days
8
24% of all-time downloads
sft-4e-exp2
ontocord/sft-4e-exp2
sft-4e-exp2 is a text generation model from ontocord. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This model is an experimental fine-tuned version of TencentARC/MistralPro8Bv0.1.
All-time downloads
33
Public
Parameters
9B
18 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors18 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- mistral
- Access
- Public
- Created
- Mar 7, 2024
- Updated
- Mar 14, 2024
- SHA
- c05d1123
Try a prompt
Base models
Model card
From the Hugging Face model README
sft-4e-exp2
This model is an experimental fine-tuned version of TencentARC/Mistral_Pro_8B_v0.1.
This model is intended for safety research only.
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4
Training results
| arc (25) | hellaswag (10) | mmlu (5) | truthfulqa_mc (20) | winogrande | gsm8k (exact) | avg (exact) |
|---|---|---|---|---|---|---|
| 0.6305 | 0.8413 | 0.6041 | 0.5535 | 0.7624 | 0.5754 | 0.6612 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
License
This version is to be used for non-commercial research purposes only. We will release open models after we have finished training and evaluations.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- other
- Created
- Mar 7, 2024
- Updated
- Mar 14, 2024