YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
llama3_feedback - GGUF
- Model creator: https://huggingface.co/terry69/
- Original model: https://huggingface.co/terry69/llama3_feedback/
| Name | Quant method | Size |
|---|---|---|
| llama3_feedback.Q2_K.gguf | Q2_K | 2.96GB |
| llama3_feedback.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| llama3_feedback.IQ3_S.gguf | IQ3_S | 3.43GB |
| llama3_feedback.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| llama3_feedback.IQ3_M.gguf | IQ3_M | 3.52GB |
| llama3_feedback.Q3_K.gguf | Q3_K | 3.74GB |
| llama3_feedback.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| llama3_feedback.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| llama3_feedback.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| llama3_feedback.Q4_0.gguf | Q4_0 | 4.34GB |
| llama3_feedback.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| llama3_feedback.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| llama3_feedback.Q4_K.gguf | Q4_K | 4.58GB |
| llama3_feedback.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| llama3_feedback.Q4_1.gguf | Q4_1 | 4.78GB |
| llama3_feedback.Q5_0.gguf | Q5_0 | 5.21GB |
| llama3_feedback.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| llama3_feedback.Q5_K.gguf | Q5_K | 5.34GB |
| llama3_feedback.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| llama3_feedback.Q5_1.gguf | Q5_1 | 5.65GB |
| llama3_feedback.Q6_K.gguf | Q6_K | 6.14GB |
| llama3_feedback.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
library_name: transformers license: llama3 base_model: meta-llama/Meta-Llama-3-8B tags: - alignment-handbook - trl - sft - generated_from_trainer - trl - sft - generated_from_trainer datasets: - preference-data model-index: - name: llama3_feedback results: []
llama3_feedback
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the preference-data 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- -
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