Downloads · 30 days
111
4% of all-time downloads
RichardErkhov/dannoncaffeine_-_GPT2-124M-wikitext-v0.1-gguf
dannoncaffeine_-_GPT2-124M-wikitext-v0.1-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
111
4% of all-time downloads
All-time downloads
2.8K
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.
GPT2-124M-wikitext-v0.1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| GPT2-124M-wikitext-v0.1.Q2_K.gguf | Q2_K | 0.08GB |
| GPT2-124M-wikitext-v0.1.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| GPT2-124M-wikitext-v0.1.Q3_K.gguf | Q3_K | 0.09GB |
| GPT2-124M-wikitext-v0.1.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| GPT2-124M-wikitext-v0.1.Q3_K_L.gguf | Q3_K_L | 0.1GB |
| GPT2-124M-wikitext-v0.1.IQ4_XS.gguf | IQ4_XS | 0.1GB |
| GPT2-124M-wikitext-v0.1.Q4_0.gguf | Q4_0 | 0.1GB |
| GPT2-124M-wikitext-v0.1.IQ4_NL.gguf | IQ4_NL | 0.1GB |
| GPT2-124M-wikitext-v0.1.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| GPT2-124M-wikitext-v0.1.Q4_K.gguf | Q4_K | 0.11GB |
| GPT2-124M-wikitext-v0.1.Q4_K_M.gguf | Q4_K_M | 0.11GB |
| GPT2-124M-wikitext-v0.1.Q4_1.gguf | Q4_1 | 0.11GB |
| GPT2-124M-wikitext-v0.1.Q5_0.gguf | Q5_0 | 0.11GB |
| GPT2-124M-wikitext-v0.1.Q5_K_S.gguf | Q5_K_S | 0.11GB |
| GPT2-124M-wikitext-v0.1.Q5_K.gguf | Q5_K | 0.12GB |
| GPT2-124M-wikitext-v0.1.Q5_K_M.gguf | Q5_K_M | 0.12GB |
| GPT2-124M-wikitext-v0.1.Q5_1.gguf | Q5_1 | 0.12GB |
| GPT2-124M-wikitext-v0.1.Q6_K.gguf | Q6_K | 0.13GB |
| GPT2-124M-wikitext-v0.1.Q8_0.gguf | Q8_0 | 0.17GB |
license: mit base_model: gpt2 tags:
This model is a fine-tuned version of gpt2 on the wikitext. It achieves the following results on the evaluation set:
This is a practical hands-on experience for better understanding 🤗 Transformers and 🤗 Datasets. This model is GPT2(124M) fine-tuned on wikitext(103-raw-v1) on 1 x RTX 4090.
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1335 | 1.0 | 57467 | 3.0363 |
| 3.0643 | 2.0 | 114934 | 2.9968 |
| 3.0384 | 3.0 | 172401 | 2.9841 |