Downloads · 30 days
60
5% of all-time downloads
Tanysha_-_GPT2-medium-gguf
RichardErkhov/Tanysha_-_GPT2-medium-gguf
Tanysha_-_GPT2-medium-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
1.3K
Public
Repo size
4.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.2 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 3, 2024
- Updated
- Nov 3, 2024
- SHA
- f305b708
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
GPT2-medium - GGUF
- Model creator: https://huggingface.co/Tanysha/
- Original model: https://huggingface.co/Tanysha/GPT2-medium/
| Name | Quant method | Size |
|---|---|---|
| GPT2-medium.Q2_K.gguf | Q2_K | 0.17GB |
| GPT2-medium.Q3_K_S.gguf | Q3_K_S | 0.19GB |
| GPT2-medium.Q3_K.gguf | Q3_K | 0.21GB |
| GPT2-medium.Q3_K_M.gguf | Q3_K_M | 0.21GB |
| GPT2-medium.Q3_K_L.gguf | Q3_K_L | 0.23GB |
| GPT2-medium.IQ4_XS.gguf | IQ4_XS | 0.22GB |
| GPT2-medium.Q4_0.gguf | Q4_0 | 0.23GB |
| GPT2-medium.IQ4_NL.gguf | IQ4_NL | 0.23GB |
| GPT2-medium.Q4_K_S.gguf | Q4_K_S | 0.23GB |
| GPT2-medium.Q4_K.gguf | Q4_K | 0.25GB |
| GPT2-medium.Q4_K_M.gguf | Q4_K_M | 0.25GB |
| GPT2-medium.Q4_1.gguf | Q4_1 | 0.25GB |
| GPT2-medium.Q5_0.gguf | Q5_0 | 0.27GB |
| GPT2-medium.Q5_K_S.gguf | Q5_K_S | 0.27GB |
| GPT2-medium.Q5_K.gguf | Q5_K | 0.29GB |
| GPT2-medium.Q5_K_M.gguf | Q5_K_M | 0.29GB |
| GPT2-medium.Q5_1.gguf | Q5_1 | 0.29GB |
| GPT2-medium.Q6_K.gguf | Q6_K | 0.32GB |
| GPT2-medium.Q8_0.gguf | Q8_0 | 0.41GB |
Original model description:
library_name: transformers license: mit base_model: openai-community/gpt2-medium tags:
- generated_from_trainer model-index:
- name: GPT2-medium 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. -->
GPT2-medium
This model is a fine-tuned version of openai-community/gpt2-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5613
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.15
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4653 | 1.7937 | 50 | 0.5613 |
| 0.3154 | 3.5874 | 100 | 0.5657 |
| 0.2436 | 5.3812 | 150 | 0.5961 |
| 0.2138 | 7.1749 | 200 | 0.6012 |
| 0.197 | 8.9686 | 250 | 0.6177 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Created
- Nov 3, 2024
- Updated
- Nov 3, 2024