Downloads · 30 days
27
2% of all-time downloads
RichardErkhov/Jaiminshahh_-_finetuned-gpt2-gguf
Jaiminshahh_-_finetuned-gpt2-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.
Downloads · 30 days
27
2% of all-time downloads
All-time downloads
1.1K
Public
Repo size
1.8 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
finetuned-gpt2 - GGUF
| Name | Quant method | Size |
|---|---|---|
| finetuned-gpt2.Q2_K.gguf | Q2_K | 0.08GB |
| finetuned-gpt2.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| finetuned-gpt2.Q3_K.gguf | Q3_K | 0.09GB |
| finetuned-gpt2.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| finetuned-gpt2.Q3_K_L.gguf | Q3_K_L | 0.1GB |
| finetuned-gpt2.IQ4_XS.gguf | IQ4_XS | 0.1GB |
| finetuned-gpt2.Q4_0.gguf | Q4_0 | 0.1GB |
| finetuned-gpt2.IQ4_NL.gguf | IQ4_NL | 0.1GB |
| finetuned-gpt2.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| finetuned-gpt2.Q4_K.gguf | Q4_K | 0.11GB |
| finetuned-gpt2.Q4_K_M.gguf | Q4_K_M | 0.11GB |
| finetuned-gpt2.Q4_1.gguf | Q4_1 | 0.11GB |
| finetuned-gpt2.Q5_0.gguf | Q5_0 | 0.11GB |
| finetuned-gpt2.Q5_K_S.gguf | Q5_K_S | 0.11GB |
| finetuned-gpt2.Q5_K.gguf | Q5_K | 0.12GB |
| finetuned-gpt2.Q5_K_M.gguf | Q5_K_M | 0.12GB |
| finetuned-gpt2.Q5_1.gguf | Q5_1 | 0.12GB |
| finetuned-gpt2.Q6_K.gguf | Q6_K | 0.13GB |
| finetuned-gpt2.Q8_0.gguf | Q8_0 | 0.17GB |
This model card documents a GPT-2 model fine-tuned on a dataset of multiple-choice medical exam questions. The model has been trained to generate answers based on a given question and corresponding options.
This model can be used to automatically generate answers for multiple-choice medical exam questions. It is suited for educational purposes, quiz generation, and training applications.
182,822 training samples
The input was tokenized with Hugging Face's GPT-2 tokenizer. Data was formatted as a question followed by the answer options.
Number of Training Epochs: 20 Batch Size (Training): 64 Learning Rate: 1e-5 Mixed Precision (FP16): True
Batch Size (Evaluation): 64
Testing Data: The model was evaluated on a held-out validation set of medical exam questions. Factors: The model's ability to select the correct answer from the given options was the key evaluation factor. Metrics: Cross-entropy loss was used to monitor performance during training, with validation loss used to evaluate generalization.
Training Loss: Decreased from 1.8577 to 1.6961 over 20 epochs. Validation Loss: Decreased from 1.8692 to 1.7394, demonstrating good generalization performance.