Downloads · 30 days
13
12% of all-time downloads
llama-7b-chatml
AlekseyKorshuk/llama-7b-chatml
llama-7b-chatml is a text generation model from AlekseyKorshuk. 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
112
Public
Repo size
40.4 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin13.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Apr 29, 2023
- Updated
- Apr 30, 2023
- SHA
- 754431c6
Try a prompt
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. -->
llama-7b-chatml
This model is a fine-tuned version of zpn/llama-7b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7373
- Accuracy: 0.2687
- Entropy: 0.6897
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
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
|---|---|---|---|---|---|
| 0.6533 | 1.0 | 817 | 0.7036 | 0.2683 | 0.7874 |
| 0.4956 | 2.0 | 1634 | 0.7373 | 0.2687 | 0.6897 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0-rc1
- Datasets 2.10.1
- Tokenizers 0.13.3
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Apr 29, 2023
- Updated
- Apr 30, 2023