Downloads · 30 days
9
39% of all-time downloads
bif02_-_lamma_operons-4bits
RichardErkhov/bif02_-_lamma_operons-4bits
bif02_-_lamma_operons-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
23
Public
Parameters
1.3B
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
Parameter types
How the weights are stored.
U8973M · 78%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
lamma_operons - bnb 4bits
- Model creator: https://huggingface.co/bif02/
- Original model: https://huggingface.co/bif02/lamma_operons/
Original model description:
library_name: transformers license: llama3.2 base_model: bif02/lamma_operons tags:
- generated_from_trainer model-index:
- name: lamma_operons results: []
<!-- 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. -->
lamma_operons
This model is a fine-tuned version of bif02/lamma_operons on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1076
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: 0.001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0887 | 1.0 | 1107 | 0.1228 |
| 0.0888 | 2.0 | 2214 | 0.1193 |
| 0.0831 | 3.0 | 3321 | 0.1212 |
| 0.0808 | 4.0 | 4428 | 0.1163 |
| 0.0759 | 5.0 | 5535 | 0.1080 |
| 0.0733 | 6.0 | 6642 | 0.1076 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Type
- llama
- Created
- Jan 13, 2025
- Updated
- Jan 13, 2025