Downloads · 30 days
118
12% of all-time downloads
YuanZ77_-_gemma2b-a-gguf
RichardErkhov/YuanZ77_-_gemma2b-a-gguf
YuanZ77_-_gemma2b-a-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
990
Public
Repo size
32.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf37.3 GB · 100%
At a glance
- Access
- Public
- Created
- Feb 25, 2025
- Updated
- Feb 25, 2025
- SHA
- 911b6d1f
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
gemma2b-a - GGUF
- Model creator: https://huggingface.co/YuanZ77/
- Original model: https://huggingface.co/YuanZ77/gemma2b-a/
| Name | Quant method | Size |
|---|---|---|
| gemma2b-a.Q2_K.gguf | Q2_K | 1.15GB |
| gemma2b-a.IQ3_XS.gguf | IQ3_XS | 1.22GB |
| gemma2b-a.IQ3_S.gguf | IQ3_S | 1.27GB |
| gemma2b-a.Q3_K_S.gguf | Q3_K_S | 1.27GB |
| gemma2b-a.IQ3_M.gguf | IQ3_M | 1.3GB |
| gemma2b-a.Q3_K.gguf | Q3_K | 1.36GB |
| gemma2b-a.Q3_K_M.gguf | Q3_K_M | 1.36GB |
| gemma2b-a.Q3_K_L.gguf | Q3_K_L | 1.44GB |
| gemma2b-a.IQ4_XS.gguf | IQ4_XS | 1.47GB |
| gemma2b-a.Q4_0.gguf | Q4_0 | 1.52GB |
| gemma2b-a.IQ4_NL.gguf | IQ4_NL | 1.53GB |
| gemma2b-a.Q4_K_S.gguf | Q4_K_S | 1.53GB |
| gemma2b-a.Q4_K.gguf | Q4_K | 1.59GB |
| gemma2b-a.Q4_K_M.gguf | Q4_K_M | 1.59GB |
| gemma2b-a.Q4_1.gguf | Q4_1 | 1.64GB |
| gemma2b-a.Q5_0.gguf | Q5_0 | 1.75GB |
| gemma2b-a.Q5_K_S.gguf | Q5_K_S | 1.75GB |
| gemma2b-a.Q5_K.gguf | Q5_K | 1.79GB |
| gemma2b-a.Q5_K_M.gguf | Q5_K_M | 1.79GB |
| gemma2b-a.Q5_1.gguf | Q5_1 | 1.87GB |
| gemma2b-a.Q6_K.gguf | Q6_K | 2.0GB |
| gemma2b-a.Q8_0.gguf | Q8_0 | 2.59GB |
Original model description:
library_name: transformers license: gemma base_model: google/gemma-2-2b-it tags:
- trl
- sft
- generated_from_trainer datasets:
- generator model-index:
- name: gemma2b-a 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. -->
gemma2b-a
This model is a fine-tuned version of google/gemma-2-2b-it on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.0156
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3675 | 0.9180 | 7 | 1.2845 |
| 0.9289 | 1.9672 | 15 | 1.0186 |
| 0.7336 | 2.7541 | 21 | 1.0156 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Created
- Feb 25, 2025
- Updated
- Feb 25, 2025