Downloads · 30 days
72
4% of all-time downloads
Mikivis_-_gpt2-large-lora-sft-gguf
RichardErkhov/Mikivis_-_gpt2-large-lora-sft-gguf
Mikivis_-_gpt2-large-lora-sft-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
1.8K
Public
Repo size
8.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf10.5 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 3, 2024
- Updated
- Nov 3, 2024
- SHA
- b18267d7
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
gpt2-large-lora-sft - GGUF
- Model creator: https://huggingface.co/Mikivis/
- Original model: https://huggingface.co/Mikivis/gpt2-large-lora-sft/
| Name | Quant method | Size |
|---|---|---|
| gpt2-large-lora-sft.Q2_K.gguf | Q2_K | 0.32GB |
| gpt2-large-lora-sft.Q3_K_S.gguf | Q3_K_S | 0.37GB |
| gpt2-large-lora-sft.Q3_K.gguf | Q3_K | 0.43GB |
| gpt2-large-lora-sft.Q3_K_M.gguf | Q3_K_M | 0.43GB |
| gpt2-large-lora-sft.Q3_K_L.gguf | Q3_K_L | 0.46GB |
| gpt2-large-lora-sft.IQ4_XS.gguf | IQ4_XS | 0.44GB |
| gpt2-large-lora-sft.Q4_0.gguf | Q4_0 | 0.46GB |
| gpt2-large-lora-sft.IQ4_NL.gguf | IQ4_NL | 0.47GB |
| gpt2-large-lora-sft.Q4_K_S.gguf | Q4_K_S | 0.47GB |
| gpt2-large-lora-sft.Q4_K.gguf | Q4_K | 0.51GB |
| gpt2-large-lora-sft.Q4_K_M.gguf | Q4_K_M | 0.51GB |
| gpt2-large-lora-sft.Q4_1.gguf | Q4_1 | 0.51GB |
| gpt2-large-lora-sft.Q5_0.gguf | Q5_0 | 0.55GB |
| gpt2-large-lora-sft.Q5_K_S.gguf | Q5_K_S | 0.55GB |
| gpt2-large-lora-sft.Q5_K.gguf | Q5_K | 0.59GB |
| gpt2-large-lora-sft.Q5_K_M.gguf | Q5_K_M | 0.59GB |
| gpt2-large-lora-sft.Q5_1.gguf | Q5_1 | 0.6GB |
| gpt2-large-lora-sft.Q6_K.gguf | Q6_K | 0.65GB |
| gpt2-large-lora-sft.Q8_0.gguf | Q8_0 | 0.84GB |
Original model description:
license: mit base_model: gpt2-large tags:
- generated_from_trainer datasets:
- customized model-index:
- name: gpt2-large-lora-sft 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-large-lora-sft
This model is a fine-tuned version of gpt2-large on the customized dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.00013
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- total_train_batch_size: 6
- total_eval_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.5
Training results
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 28.05 |
| ARC (25-shot) | 26.79 |
| HellaSwag (10-shot) | 44.15 |
| MMLU (5-shot) | 25.82 |
| TruthfulQA (0-shot) | 39.06 |
| Winogrande (5-shot) | 55.09 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 5.46 |
- Created
- Nov 3, 2024
- Updated
- Nov 3, 2024