Downloads · 30 days
216
3% of all-time downloads
RamAnanth1_-_distilgpt2-sd-prompts-gguf
RichardErkhov/RamAnanth1_-_distilgpt2-sd-prompts-gguf
RamAnanth1_-_distilgpt2-sd-prompts-gguf 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
6.2K
Public
Repo size
1.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.9 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 26, 2024
- Updated
- Sep 26, 2024
- SHA
- cd00e62a
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
distilgpt2-sd-prompts - GGUF
- Model creator: https://huggingface.co/RamAnanth1/
- Original model: https://huggingface.co/RamAnanth1/distilgpt2-sd-prompts/
| Name | Quant method | Size |
|---|---|---|
| distilgpt2-sd-prompts.Q2_K.gguf | Q2_K | 0.06GB |
| distilgpt2-sd-prompts.IQ3_XS.gguf | IQ3_XS | 0.07GB |
| distilgpt2-sd-prompts.IQ3_S.gguf | IQ3_S | 0.07GB |
| distilgpt2-sd-prompts.Q3_K_S.gguf | Q3_K_S | 0.07GB |
| distilgpt2-sd-prompts.IQ3_M.gguf | IQ3_M | 0.07GB |
| distilgpt2-sd-prompts.Q3_K.gguf | Q3_K | 0.07GB |
| distilgpt2-sd-prompts.Q3_K_M.gguf | Q3_K_M | 0.07GB |
| distilgpt2-sd-prompts.Q3_K_L.gguf | Q3_K_L | 0.07GB |
| distilgpt2-sd-prompts.IQ4_XS.gguf | IQ4_XS | 0.07GB |
| distilgpt2-sd-prompts.Q4_0.gguf | Q4_0 | 0.08GB |
| distilgpt2-sd-prompts.IQ4_NL.gguf | IQ4_NL | 0.08GB |
| distilgpt2-sd-prompts.Q4_K_S.gguf | Q4_K_S | 0.08GB |
| distilgpt2-sd-prompts.Q4_K.gguf | Q4_K | 0.08GB |
| distilgpt2-sd-prompts.Q4_K_M.gguf | Q4_K_M | 0.08GB |
| distilgpt2-sd-prompts.Q4_1.gguf | Q4_1 | 0.08GB |
| distilgpt2-sd-prompts.Q5_0.gguf | Q5_0 | 0.09GB |
| distilgpt2-sd-prompts.Q5_K_S.gguf | Q5_K_S | 0.09GB |
| distilgpt2-sd-prompts.Q5_K.gguf | Q5_K | 0.09GB |
| distilgpt2-sd-prompts.Q5_K_M.gguf | Q5_K_M | 0.09GB |
| distilgpt2-sd-prompts.Q5_1.gguf | Q5_1 | 0.09GB |
| distilgpt2-sd-prompts.Q6_K.gguf | Q6_K | 0.1GB |
| distilgpt2-sd-prompts.Q8_0.gguf | Q8_0 | 0.12GB |
Original model description:
license: apache-2.0 tags:
- generated_from_trainer datasets: Gustavosta/Stable-Diffusion-Prompts widget:
- text: A detective of wolfhound model-index:
- name: distilgpt2-sd-prompts 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. -->
distilgpt2-sd-prompts
This model is a fine-tuned version of distilgpt2 on Stable-Diffusion-Prompts. It achieves the following results on the evaluation set:
- Loss: 0.9450
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5122 | 1.93 | 500 | 1.5211 |
| 1.2912 | 3.86 | 1000 | 1.1045 |
| 0.9313 | 5.79 | 1500 | 0.9704 |
| 0.7744 | 7.72 | 2000 | 0.9450 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
- Created
- Sep 26, 2024
- Updated
- Sep 26, 2024