YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
full_ft_model - GGUF
- Model creator: https://huggingface.co/Vivian12300/
- Original model: https://huggingface.co/Vivian12300/full_ft_model/
| Name | Quant method | Size |
|---|---|---|
| full_ft_model.Q2_K.gguf | Q2_K | 2.96GB |
| full_ft_model.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| full_ft_model.IQ3_S.gguf | IQ3_S | 3.43GB |
| full_ft_model.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| full_ft_model.IQ3_M.gguf | IQ3_M | 3.52GB |
| full_ft_model.Q3_K.gguf | Q3_K | 3.74GB |
| full_ft_model.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| full_ft_model.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| full_ft_model.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| full_ft_model.Q4_0.gguf | Q4_0 | 4.34GB |
| full_ft_model.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| full_ft_model.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| full_ft_model.Q4_K.gguf | Q4_K | 4.58GB |
| full_ft_model.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| full_ft_model.Q4_1.gguf | Q4_1 | 4.78GB |
| full_ft_model.Q5_0.gguf | Q5_0 | 5.21GB |
| full_ft_model.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| full_ft_model.Q5_K.gguf | Q5_K | 5.34GB |
| full_ft_model.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| full_ft_model.Q5_1.gguf | Q5_1 | 5.65GB |
| full_ft_model.Q6_K.gguf | Q6_K | 6.14GB |
| full_ft_model.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
library_name: transformers license: llama3.1 base_model: meta-llama/Llama-3.1-8B-Instruct tags: - trl - sft - generated_from_trainer datasets: - generator model-index: - name: full_ft_model results: []
full_ft_model
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the generator dataset.
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: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adafactor and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3
- Downloads last month
- 78
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support