Downloads · 30 days
96
4% of all-time downloads
Katayoon_-_VPO-Zephyr-7B-iter-2-gguf
RichardErkhov/Katayoon_-_VPO-Zephyr-7B-iter-2-gguf
Katayoon_-_VPO-Zephyr-7B-iter-2-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
2.3K
Public
Repo size
81.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf94.7 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 12, 2024
- Updated
- Aug 12, 2024
- SHA
- 9e3f8fa8
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
VPO-Zephyr-7B-iter-2 - GGUF
- Model creator: https://huggingface.co/Katayoon/
- Original model: https://huggingface.co/Katayoon/VPO-Zephyr-7B-iter-2/
| Name | Quant method | Size |
|---|---|---|
| VPO-Zephyr-7B-iter-2.Q2_K.gguf | Q2_K | 2.53GB |
| VPO-Zephyr-7B-iter-2.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| VPO-Zephyr-7B-iter-2.IQ3_S.gguf | IQ3_S | 2.96GB |
| VPO-Zephyr-7B-iter-2.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| VPO-Zephyr-7B-iter-2.IQ3_M.gguf | IQ3_M | 3.06GB |
| VPO-Zephyr-7B-iter-2.Q3_K.gguf | Q3_K | 3.28GB |
| VPO-Zephyr-7B-iter-2.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| VPO-Zephyr-7B-iter-2.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| VPO-Zephyr-7B-iter-2.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| VPO-Zephyr-7B-iter-2.Q4_0.gguf | Q4_0 | 3.83GB |
| VPO-Zephyr-7B-iter-2.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| VPO-Zephyr-7B-iter-2.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| VPO-Zephyr-7B-iter-2.Q4_K.gguf | Q4_K | 4.07GB |
| VPO-Zephyr-7B-iter-2.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| VPO-Zephyr-7B-iter-2.Q4_1.gguf | Q4_1 | 4.24GB |
| VPO-Zephyr-7B-iter-2.Q5_0.gguf | Q5_0 | 4.65GB |
| VPO-Zephyr-7B-iter-2.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| VPO-Zephyr-7B-iter-2.Q5_K.gguf | Q5_K | 4.78GB |
| VPO-Zephyr-7B-iter-2.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| VPO-Zephyr-7B-iter-2.Q5_1.gguf | Q5_1 | 5.07GB |
| VPO-Zephyr-7B-iter-2.Q6_K.gguf | Q6_K | 5.53GB |
| VPO-Zephyr-7B-iter-2.Q8_0.gguf | Q8_0 | 6.66GB |
Original model description:
license: mit base_model: Katayoon/VPO-Zephyr-7B-iter-1 tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
- trl
- dpo
- generated_from_trainer datasets:
- updated
- original model-index:
- name: VPO-Zephyr-7B-iter-2 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. -->
VPO-Zephyr-7B-iter-2
This model is a fine-tuned version of Katayoon/VPO-Zephyr-7B-iter-1 on the updated and the original datasets.
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: 5e-07
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
Framework versions
- Transformers 4.40.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
- Created
- Aug 12, 2024
- Updated
- Aug 12, 2024