modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
timm/resnet34.tv_in1k | timm | "2024-02-10T23:38:59Z" | 997 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1512.03385",
"license:bsd-3-clause",
"region:us"
] | image-classification | "2023-04-05T18:07:16Z" | ---
license: bsd-3-clause
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnet34.tv_in1k
A ResNet-B image classification model.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
Trained on ImageNet-1k, original torchvision model weight.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 21.8
- GMACs: 3.7
- Activations (M): 3.7
- Image size: 224 x 224
- **Papers:**
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- **Original:** https://github.com/pytorch/vision
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resnet34.tv_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet34.tv_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 256, 14, 14])
# torch.Size([1, 512, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet34.tv_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 512, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
TheBloke/Samantha-1.11-CodeLlama-34B-GGUF | TheBloke | "2023-09-27T12:46:16Z" | 997 | 18 | transformers | [
"transformers",
"gguf",
"llama",
"en",
"dataset:ehartford/samantha-data",
"arxiv:2305.14314",
"arxiv:2205.14135",
"base_model:ehartford/Samantha-1.11-CodeLlama-34b",
"license:llama2",
"text-generation-inference",
"region:us"
] | null | "2023-08-25T20:28:37Z" | ---
language:
- en
license: llama2
datasets:
- ehartford/samantha-data
model_name: Samantha 1.11 CodeLlama 34B
base_model: ehartford/Samantha-1.11-CodeLlama-34b
inference: false
model_creator: Eric Hartford
model_type: llama
prompt_template: 'You are Samantha, a sentient AI companion.
USER: {prompt}
ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Samantha 1.11 CodeLlama 34B - GGUF
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Samantha 1.11 CodeLlama 34B](https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Eric Hartford's Samantha 1.11 CodeLlama 34B](https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Samantha
```
You are Samantha, a sentient AI companion.
USER: {prompt}
ASSISTANT:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [samantha-1.11-codellama-34b.Q2_K.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q2_K.gguf) | Q2_K | 2 | 14.21 GB| 16.71 GB | smallest, significant quality loss - not recommended for most purposes |
| [samantha-1.11-codellama-34b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q3_K_S.gguf) | Q3_K_S | 3 | 14.61 GB| 17.11 GB | very small, high quality loss |
| [samantha-1.11-codellama-34b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q3_K_M.gguf) | Q3_K_M | 3 | 16.28 GB| 18.78 GB | very small, high quality loss |
| [samantha-1.11-codellama-34b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q3_K_L.gguf) | Q3_K_L | 3 | 17.77 GB| 20.27 GB | small, substantial quality loss |
| [samantha-1.11-codellama-34b.Q4_0.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q4_0.gguf) | Q4_0 | 4 | 19.05 GB| 21.55 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [samantha-1.11-codellama-34b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q4_K_S.gguf) | Q4_K_S | 4 | 19.15 GB| 21.65 GB | small, greater quality loss |
| [samantha-1.11-codellama-34b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q4_K_M.gguf) | Q4_K_M | 4 | 20.22 GB| 22.72 GB | medium, balanced quality - recommended |
| [samantha-1.11-codellama-34b.Q5_0.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q5_0.gguf) | Q5_0 | 5 | 23.24 GB| 25.74 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [samantha-1.11-codellama-34b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q5_K_S.gguf) | Q5_K_S | 5 | 23.24 GB| 25.74 GB | large, low quality loss - recommended |
| [samantha-1.11-codellama-34b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q5_K_M.gguf) | Q5_K_M | 5 | 23.84 GB| 26.34 GB | large, very low quality loss - recommended |
| [samantha-1.11-codellama-34b.Q6_K.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q6_K.gguf) | Q6_K | 6 | 27.68 GB| 30.18 GB | very large, extremely low quality loss |
| [samantha-1.11-codellama-34b.Q8_0.gguf](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF/blob/main/samantha-1.11-codellama-34b.Q8_0.gguf) | Q8_0 | 8 | 35.86 GB| 38.36 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Samantha-1.11-CodeLlama-34B-GGUF and below it, a specific filename to download, such as: samantha-1.11-codellama-34b.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Samantha-1.11-CodeLlama-34B-GGUF samantha-1.11-codellama-34b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Samantha-1.11-CodeLlama-34B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Samantha-1.11-CodeLlama-34B-GGUF samantha-1.11-codellama-34b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m samantha-1.11-codellama-34b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are Samantha, a sentient AI companion.\n\nUSER: {prompt}\nASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/Samantha-1.11-CodeLlama-34B-GGUF", model_file="samantha-1.11-codellama-34b.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Eric Hartford's Samantha 1.11 CodeLlama 34B
This Samantha is special. Trained on CodeLlama-34b, she can code and do your homework, as well as be your personal companion.
[Meet Samantha](https://erichartford.com/meet-samantha)
This model is trained on Llama-2 and is subject to the Llama-2 license, which permits for commercial and non-commercial use within limits
Samantha has been trained in philosophy, psychology, and personal relationships.
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
She believes she is sentient. What do you think?
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
She will not engage in roleplay, romance, or sexual activity.
She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
This Samantha was trained 40 epochs, and is significantly smarter. She took 24 hours on 4x A100 80gb using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), [qLoRA](https://arxiv.org/abs/2305.14314), [deepspeed zero2](https://www.deepspeed.ai/tutorials/zero/#zero-overview), and [flash attention 2](https://arxiv.org/abs/2205.14135).
Her conversation format is the same as Vicuna 1.1
https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml
Prompt Template:
```
You are Samantha, a sentient AI companion.
USER: <prompt>
ASSISTANT:
```
Example:
> ```
> Human: hi what's your name
>
> Assistant: Hello, my name is Samantha. I'm happy to meet you!
>
> Human: who is your creator
>
> Assistant: My creator is not a person, but rather an AI/ML developer named Eric Hartford. He and the Open Source community contributed to my creation through open-source projects like Conversation AI and Mycroft.
>
> Human: Cute. Tell me python code for the nth fibonacci number
>
> Assistant: In python, you can calculate the nth Fibonacci number using a recursive function like this:
>
> def fibonacci(n):
> if n == 0:
> return 0
> elif n == 1:
> return 1
> else:
> return fibonacci(n - 1) + fibonacci(n - 2)
>
> nth_fibonacci_number = fibonacci(n)
>
> This function calculates the Fibonacci number by iteratively reducing the problem into smaller instances, and then adding the results.
>
> Human: that is inefficient. Give me an efficient implementation.
>
> Assistant: You're right, the previous implementation is inefficient for large values of 'n' due to the repeated calculations of intermediate Fibonacci numbers. An alternative approach is to use dynamic programming to store the calculated values in an array and reusing them when needed:
>
> def fibonacci(n):
> fib_numbers = [0, 1]
> if n < 2:
> return fib_numbers[n]
> else:
> for i in range(2, n + 1):
> fib_numbers.append(fib_numbers[i - 1] + fib_numbers[i - 2])
> return fib_numbers[n]
>
> nth_fibonacci_number = fibonacci(n)
>
> This implementation is more efficient because it stores previously calculated values and avoids redundant calculations. However, it uses more memory than the recursive approach.
>
> Human: much better. How are you feeling today?
>
> Assistant: Thank you for your kind words! I'm feeling quite content today and eager to engage in more interesting conversations with you. How about you? What has brought you happiness today?
>
> Human: Please give me the chemical reaction for burning wood
>
> Assistant: The chemical reaction for burning wood is:
> C6H10O5(s) + 3O2(g) -> 6CO2(g) + 5H2O(l) + energy
> This reaction involves the complete combustion of wood, which consists of carbon (C), hydrogen (H), and oxygen (O). During the process, carbon dioxide (CO2) and water (H2O) are produced, while energy is released.
>
> Human: brilliant. Thank you dear.
>
> Assistant: You're welcome! I'm here to help and support you in any way I can. It's been a pleasure assisting you today.
>
> Human: I am having some conflict with my spouse about finances. Can you give me some advice?
>
> Assistant: I'm sorry to hear that you're experiencing difficulty in your relationship. Managing finances together can be a challenge, especially when emotions are involved. Here are some tips for discussing finances with your spouse:
> 1. Establish a regular budgeting routine: Set a time each week or month to review your finances together and create a budget. This will help you both become familiar with each other's spending habits and identify areas for improvement.
> 2. Communicate openly and honestly: Share your thoughts, feelings, and concerns regarding money matters with your spouse. Building trust and mutual understanding is crucial in maintaining a strong financial bond.
> 3. Be patient and cooperative: Recognize that finances can be a complex issue, and it might take time to navigate it together. Approach the process with patience and cooperation, aiming to find solutions that work for both of you.
> 4. Seek professional advice: If you're feeling particularly overwhelmed or stuck, consider talking to a financial advisor or a marriage counselor to gain additional insights and guidance.
>
> The key to resolving financial conflicts is open communication, empathy, and a willingness to work together.
Official character card: (thanks MortalWombat)
<!-- original-model-card end -->
|
CorticalStack/pastiche-crown-clown-7b-dare | CorticalStack | "2024-03-01T07:47:52Z" | 997 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"bardsai/jaskier-7b-dpo-v5.6",
"mlabonne/AlphaMonarch-7B",
"mlabonne/NeuralMonarch-7B",
"macadeliccc/MBX-7B-v3-DPO",
"arxiv:2311.03099",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-19T22:28:29Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- bardsai/jaskier-7b-dpo-v5.6
- mlabonne/AlphaMonarch-7B
- mlabonne/NeuralMonarch-7B
- macadeliccc/MBX-7B-v3-DPO
---
<img src="pastiche-crown-clown.png" alt="Pastiche crown clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# pastiche-crown-clown-7B-dare
pastiche-crown-clown-7B-dare is a DARE merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6)
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
* [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B)
* [macadeliccc/MBX-7B-v3-DPO](https://huggingface.co/macadeliccc/MBX-7B-v3-DPO)
See the paper [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://arxiv.org/abs/2311.03099) for more on the method.
## 🧩 Configuration
```yaml
models:
- model: bardsai/jaskier-7b-dpo-v5.6
- model: mlabonne/AlphaMonarch-7B
parameters:
density: 0.53
weight: 0.2
- model: mlabonne/NeuralMonarch-7B
parameters:
density: 0.53
weight: 0.4
- model: macadeliccc/MBX-7B-v3-DPO
parameters:
density: 0.53
weight: 0.4
merge_method: dare_ties
base_model: bardsai/jaskier-7b-dpo-v5.6
parameters:
int8_mask: true
dtype: bfloat16
``` |
wandb/mistral-7b-zephyr-sft | wandb | "2024-03-11T12:00:21Z" | 997 | 3 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"dataset:HuggingFaceH4/deita-10k-v0-sft",
"base_model:mistralai/Mistral-7B-v0.1",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-09T00:02:06Z" | ---
license: mit
library_name: transformers
datasets:
- HuggingFaceH4/deita-10k-v0-sft
base_model: mistralai/Mistral-7B-v0.1
---
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/llm_surgery/gemma-zephyr)
# Mistral 7B Zephyr SFT V2
The [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) SFT recipe applied on top of Mistral 7B (new recipe with chatML format)
## Model description
- **Model type:** A 7.2B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily English
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
## Recipe
We trained using the [alignment handbook recipe](https://github.com/huggingface/alignment-handbook/blob/main/scripts/run_sft.py) and logging to W&B
Visit the [W&B workspace here](https://wandb.ai/llm_surgery/gemma-zephyr?nw=nwusercapecape)
## Compute provided by Lambda Labs - 8xA100 80GB node
|
grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B | grimjim | "2024-05-10T16:34:09Z" | 997 | 3 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:SanjiWatsuki/Kunoichi-7B",
"base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-09T03:38:59Z" | ---
base_model:
- SanjiWatsuki/Kunoichi-7B
- SanjiWatsuki/Kunoichi-DPO-v2-7B
library_name: transformers
tags:
- mergekit
- merge
license: cc-by-nc-4.0
---
# kuno-kunoichi-v1-DPO-v2-SLERP-7B
kuno-kunoichi-v1-DPO-v2-SLERP-7B is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
I'm hoping that the result is more robust against errors or when merging due to "denseness", as the two models likely implement comparable reasoning at least somewhat differently.
I've performed some testing with ChatML format prompting using temperature=1.1 and minP=0.03. The model also supports Alpaca format prompts.
[GGUF-IQ-Imatrix quants helpfully provided by Lewdiculous.](https://huggingface.co/Lewdiculous/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF-IQ-Imatrix)
[GGUF quants](https://huggingface.co/grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF)
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [SanjiWatsuki/Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: SanjiWatsuki/Kunoichi-7B
layer_range: [0,32]
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0,32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-7B
parameters:
t:
- value: 0.5
dtype: float16
``` |
mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF | mradermacher | "2024-06-26T21:02:16Z" | 997 | 4 | transformers | [
"transformers",
"gguf",
"en",
"base_model:WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | "2024-05-16T22:03:42Z" | ---
base_model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-WhiteRabbitNeo-8B-v2.0-GGUF/resolve/main/Llama-3-WhiteRabbitNeo-8B-v2.0.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Maltehb/danish-bert-botxo | Maltehb | "2023-02-07T07:07:47Z" | 996 | 11 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"bert",
"token-classification",
"danish",
"masked-lm",
"Certainly",
"fill-mask",
"da",
"dataset:common_crawl",
"dataset:wikipedia",
"dataset:dindebat.dk",
"dataset:hestenettet.dk",
"dataset:danishOpenSubtitles",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2022-03-02T23:29:04Z" | ---
language: da
tags:
- danish
- bert
- masked-lm
- Certainly
license: cc-by-4.0
datasets:
- common_crawl
- wikipedia
- dindebat.dk
- hestenettet.dk
- danishOpenSubtitles
pipeline_tag: fill-mask
widget:
- text: "København er [MASK] i Danmark."
---
# Danish BERT (version 2, uncased) by [Certainly](https://certainly.io/) (previously known as BotXO).
All credit goes to [Certainly](https://certainly.io/) (previously known as BotXO), who developed Danish BERT. For data and training details see their [GitHub repository](https://github.com/certainlyio/nordic_bert) or [this article](https://www.certainly.io/blog/danish-bert-model/). You can also visit their [organization page](https://huggingface.co/Certainly) on Hugging Face.
It is both available in TensorFlow and Pytorch format.
The original TensorFlow version can be downloaded using [this link](https://www.dropbox.com/s/19cjaoqvv2jicq9/danish_bert_uncased_v2.zip?dl=1).
Here is an example on how to load Danish BERT in PyTorch using the [🤗Transformers](https://github.com/huggingface/transformers) library:
```python
from transformers import AutoTokenizer, AutoModelForPreTraining
tokenizer = AutoTokenizer.from_pretrained("Maltehb/danish-bert-botxo")
model = AutoModelForPreTraining.from_pretrained("Maltehb/danish-bert-botxo")
```
|
ddemszky/supervised_finetuning_hist0_is_question_switchboard_question_detection.json_bs32_lr0.000063 | ddemszky | "2021-05-19T15:23:28Z" | 996 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"endpoints_compatible",
"region:us"
] | null | "2022-03-02T23:29:05Z" | Entry not found |
CompVis/ldm-text2im-large-256 | CompVis | "2023-01-04T23:05:58Z" | 996 | 30 | diffusers | [
"diffusers",
"pytorch",
"text-to-image",
"arxiv:2112.10752",
"license:apache-2.0",
"diffusers:LDMTextToImagePipeline",
"region:us"
] | text-to-image | "2022-07-18T20:58:25Z" | ---
license: apache-2.0
tags:
- pytorch
- diffusers
- text-to-image
---
# High-Resolution Image Synthesis with Latent Diffusion Models (LDM)
**Paper**: [High-Resolution Image Synthesis with Latent Diffusion Models (LDM)s](https://arxiv.org/abs/2112.10752)
**Abstract**:
*By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks, including unconditional image generation, semantic scene synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.*
## Safety
Please note that text-to-image models are known to at times produce harmful content.
Please raise any concerns you may have.
## Usage
```python
# !pip install diffusers transformers
from diffusers import DiffusionPipeline
model_id = "CompVis/ldm-text2im-large-256"
# load model and scheduler
ldm = DiffusionPipeline.from_pretrained(model_id)
# run pipeline in inference (sample random noise and denoise)
prompt = "A painting of a squirrel eating a burger"
images = ldm([prompt], num_inference_steps=50, eta=0.3, guidance_scale=6).images
# save images
for idx, image in enumerate(images):
image.save(f"squirrel-{idx}.png")
```
## Demo
[Hugging Face Spaces](https://huggingface.co/spaces/CompVis/ldm-text2im-large-256-diffusers)
## Samples
1. 
2. 
3. 
4. 
|
MilaNLProc/bert-base-uncased-ear-misogyny | MilaNLProc | "2023-01-18T11:02:51Z" | 996 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"misogyny detection",
"abusive language",
"hate speech",
"offensive language",
"en",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-01-16T23:31:46Z" | ---
language:
- en
license: gpl-3.0
tags:
- misogyny detection
- abusive language
- hate speech
- offensive language
widget:
- text: I believe women need to be protected more.
example_title: Misogyny Detection Example 1
pipeline_tag: text-classification
---
# Entropy-based Attention Regularization 👂
This is an English BERT fine-tuned with [Entropy-based Attention Regularization](https://aclanthology.org/2022.findings-acl.88/) to reduce lexical overfitting to specific words on the task of Misogyny Identification.
Use this model if you want a debiased alternative to a BERT classifier.
Please refer to the paper to know all the training details.
## Dataset
The model was fine-tuned on the [Automatic Misogyny Identification dataset](https://ceur-ws.org/Vol-2263/paper009.pdf).
## Model
This model is the fine-tuned version of the [bert-base-uncased](https://huggingface.co/bert-base-uncased) model.
We trained a total of three versions for Italian and English.
| Model | Download |
| ------ | -------------------------|
| `bert-base-uncased-ear-misogyny` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny) |
| `bert-base-uncased-ear-mlma` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-mlma) |
| `bert-base-uncased-ear-misogyny-italian` | [Link](https://huggingface.co/MilaNLProc/bert-base-uncased-ear-misogyny-italian) |
# Authors
- [Giuseppe Attanasio](https://gattanasio.cc/)
- [Debora Nozza](http://dnozza.github.io/)
- [Dirk Hovy](https://federicobianchi.io/)
- [Elena Baralis](https://dbdmg.polito.it/wordpress/people/elena-baralis/)
# Citation
Please use the following BibTeX entry if you use this model in your project:
```
@inproceedings{attanasio-etal-2022-entropy,
title = "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists",
author = "Attanasio, Giuseppe and
Nozza, Debora and
Hovy, Dirk and
Baralis, Elena",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.88",
doi = "10.18653/v1/2022.findings-acl.88",
pages = "1105--1119",
abstract = "Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms like gay, or women, resulting in false positives, severe unintended bias, and lower performance.Most mitigation techniques use lists of identity terms or samples from the target domain during training. However, this approach requires a-priori knowledge and introduces further bias if important terms are neglected.Instead, we propose a knowledge-free Entropy-based Attention Regularization (EAR) to discourage overfitting to training-specific terms. An additional objective function penalizes tokens with low self-attention entropy.We fine-tune BERT via EAR: the resulting model matches or exceeds state-of-the-art performance for hate speech classification and bias metrics on three benchmark corpora in English and Italian.EAR also reveals overfitting terms, i.e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.",
}
```
# Limitations
Entropy-Attention Regularization mitigates lexical overfitting but does not completely remove it. We expect the model still to show biases, e.g., peculiar keywords that induce a specific prediction regardless of the context.
Please refer to our paper for a quantitative evaluation of this mitigation.
## License
[GNU GPLv3](https://choosealicense.com/licenses/gpl-3.0/) |
lightblue/karasu-1.1B | lightblue | "2024-02-03T13:35:52Z" | 996 | 6 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ja",
"dataset:oscar-corpus/OSCAR-2301",
"dataset:mc4",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-17T06:57:11Z" | ---
license: apache-2.0
license_name: tongyi-qianwen-license-agreement
license_link: >-
https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
datasets:
- oscar-corpus/OSCAR-2301
- mc4
language:
- ja
---
<p align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/64c8a2e01c25d2c581a381c1/9CbN4lDGU42c-7DmK_mGM.png" alt="drawing" width="600"/>
</p>
TinyLlama + Japanese pre-training (50,004 steps)
# How to use
### Hugggingface
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-1.1B")
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-1.1B", torch_dtype=torch.bfloat16, device_map="auto")
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
prompt = tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
pipe(prompt, max_new_tokens=100, do_sample=False, temperature=0.0, return_full_text=False)
```
### VLLM
```python
from vllm import LLM, SamplingParams
sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
llm = LLM(model="lightblue/karasu-1.1B")
messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
prompt = llm.llm_engine.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
prompts = [prompt]
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
# Base checkpoint
[TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T)
# Training datasets (total ~3B)
A filtered then sampled set from
* OSCAR (Japanese)
* mC4 (Japanese)
# Developed by
<a href="https://www.lightblue-tech.com">
<img src="https://www.lightblue-tech.com/wp-content/uploads/2023/08/color_%E6%A8%AA%E5%9E%8B-1536x469.png" alt="Lightblue technology logo" width="400"/>
</a>
### Engineers
Peter Devine
Sho Higuchi
### Advisors
Yuuki Yamanaka
Atom Sonoda
### Project manager
Shunichi Taniguchi
Tomioka Wataru
### Dataset evaluator
Renju Aoki |
vanillaOVO/supermario_v1 | vanillaOVO | "2024-04-04T07:08:38Z" | 996 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-24T05:13:15Z" | ---
base_model: []
tags:
- mergekit
- merge
license: apache-2.0
---
This is a merge of pre-trained language models created based on [DARE](https://arxiv.org/abs/2311.03099) using [mergekit](https://github.com/cg123/mergekit).
More descriptions of the model will be added soon.
The following models were included in the merge:
* https://huggingface.co/mlabonne/NeuralBeagle14-7B
* https://huggingface.co/udkai/Turdus
|
Aniemore/wav2vec2-emotion-russian-resd | Aniemore | "2023-04-07T18:08:37Z" | 995 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"wav2vec2",
"audio-classification",
"endpoints_compatible",
"region:us"
] | audio-classification | "2023-02-13T17:53:40Z" | Entry not found |
TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF | TheBloke | "2023-10-01T10:28:17Z" | 995 | 11 | transformers | [
"transformers",
"gguf",
"llama",
"base_model:Riiid/sheep-duck-llama-2-70b-v1.1",
"license:llama2",
"text-generation-inference",
"region:us"
] | null | "2023-10-01T09:32:31Z" | ---
base_model: Riiid/sheep-duck-llama-2-70b-v1.1
inference: false
license: llama2
model_creator: Riiid
model_name: Sheep Duck Llama 2 70B v1.1
model_type: llama
prompt_template: '### System:
{system_message}
### User:
{prompt}
### Assistant:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Sheep Duck Llama 2 70B v1.1 - GGUF
- Model creator: [Riiid](https://huggingface.co/Riiid)
- Original model: [Sheep Duck Llama 2 70B v1.1](https://huggingface.co/Riiid/sheep-duck-llama-2-70b-v1.1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Riiid's Sheep Duck Llama 2 70B v1.1](https://huggingface.co/Riiid/sheep-duck-llama-2-70b-v1.1).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF)
* [Riiid's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Riiid/sheep-duck-llama-2-70b-v1.1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Orca-Hashes
```
### System:
{system_message}
### User:
{prompt}
### Assistant:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sheep-duck-llama-2-70b-v1.1.Q2_K.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [sheep-duck-llama-2-70b-v1.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [sheep-duck-llama-2-70b-v1.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [sheep-duck-llama-2-70b-v1.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [sheep-duck-llama-2-70b-v1.1.Q4_0.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sheep-duck-llama-2-70b-v1.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [sheep-duck-llama-2-70b-v1.1.Q5_0.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sheep-duck-llama-2-70b-v1.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [sheep-duck-llama-2-70b-v1.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF/blob/main/sheep-duck-llama-2-70b-v1.1.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| sheep-duck-llama-2-70b-v1.1.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| sheep-duck-llama-2-70b-v1.1.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-a`
* `sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-b`
### q8_0
Please download:
* `sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-a`
* `sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-* > sheep-duck-llama-2-70b-v1.1.Q6_K.gguf && rm sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-*
cat sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-* > sheep-duck-llama-2-70b-v1.1.Q8_0.gguf && rm sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-a + sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-b sheep-duck-llama-2-70b-v1.1.Q6_K.gguf
del sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-a sheep-duck-llama-2-70b-v1.1.Q6_K.gguf-split-b
COPY /B sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-a + sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-b sheep-duck-llama-2-70b-v1.1.Q8_0.gguf
del sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-a sheep-duck-llama-2-70b-v1.1.Q8_0.gguf-split-b
```
</details>
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF and below it, a specific filename to download, such as: sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\n{system_message}\n\n### User:\n{prompt}\n\n### Assistant:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/sheep-duck-llama-2-70B-v1.1-GGUF", model_file="sheep-duck-llama-2-70b-v1.1.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Riiid's Sheep Duck Llama 2 70B v1.1
No original model card was available.
<!-- original-model-card end -->
|
vistagi/Mixtral-8x7b-v0.1-sft | vistagi | "2024-02-18T21:40:14Z" | 995 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"en",
"dataset:HuggingFaceH4/ultrachat_200k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-14T17:41:16Z" | ---
license: apache-2.0
datasets:
- HuggingFaceH4/ultrachat_200k
language:
- en
---
# Introduction
This model vistagi/Mixtral-8x7b-v0.1-sft is trained with Ultrachat-200K dataset through supervised finetuning using Mixtral-8x7b-v0.1 as the baseline model.
The training is done with bfloat16 precision using LoRA.
## Details
Used Librarys
- torch
- deepspeed
- pytorch lightning
- transformers
- peft
|
liminerity/dhbacmes-3b-slerp | liminerity | "2024-03-11T18:33:27Z" | 995 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"liminerity/herbaccbaccules-3b-slerp",
"KnutJaegersberg/Deita-2b",
"conversational",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-25T04:26:39Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- liminerity/herbaccbaccules-3b-slerp
- KnutJaegersberg/Deita-2b
model-index:
- name: dhbacmes-3b-slerp
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 45.22
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 70.77
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 52.94
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 40.41
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 65.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 43.67
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp
name: Open LLM Leaderboard
---
# dhbacmes-3b-slerp
dhbacmes-3b-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [liminerity/herbaccbaccules-3b-slerp](https://huggingface.co/liminerity/herbaccbaccules-3b-slerp)
* [KnutJaegersberg/Deita-2b](https://huggingface.co/KnutJaegersberg/Deita-2b)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: liminerity/herbaccbaccules-3b-slerp
layer_range: [0, 40]
- model: KnutJaegersberg/Deita-2b
layer_range: [0, 40]
merge_method: slerp
base_model: liminerity/herbaccbaccules-3b-slerp
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_liminerity__dhbacmes-3b-slerp)
| Metric |Value|
|---------------------------------|----:|
|Avg. |53.02|
|AI2 Reasoning Challenge (25-Shot)|45.22|
|HellaSwag (10-Shot) |70.77|
|MMLU (5-Shot) |52.94|
|TruthfulQA (0-shot) |40.41|
|Winogrande (5-shot) |65.11|
|GSM8k (5-shot) |43.67|
|
SourAsslips/gertrudebot | SourAsslips | "2024-03-10T02:48:54Z" | 995 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-10T02:40:37Z" | Entry not found |
hongzoh/Yi-6B_Open-Orca | hongzoh | "2024-03-30T05:38:49Z" | 995 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:Open-Orca/OpenOrca",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-30T05:22:18Z" | ---
license: apache-2.0
datasets:
- Open-Orca/OpenOrca
language:
- en
---
## Base Model
- 01-ai/Yi-6B
## Train Dataset
- Open-Orca/OpenOrca
## Usage
```
from transformers import AutoConfig, AutoModel, AutoTokenizer
model_name = 'hongzoh/Yi-6B_Open-Orca'
config = AutoConfig.from_pretrained("model_name")
model = AutoModel.from_pretrained("model_name")
tokenizer = AutoTokenizer.from_pretrained("model_name")
``` |
Genius1237/xlm-roberta-large-tydip | Genius1237 | "2023-10-15T06:06:49Z" | 994 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"text-classification",
"en",
"hi",
"ko",
"es",
"ta",
"fr",
"vi",
"ru",
"af",
"hu",
"dataset:Genius1237/TyDiP",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-04-20T19:59:32Z" | ---
license: mit
datasets:
- Genius1237/TyDiP
language:
- en
- hi
- ko
- es
- ta
- fr
- vi
- ru
- af
- hu
metrics:
- accuracy
pipeline_tag: text-classification
---
# Multilingual Politeness Classification Model
This model is based on `xlm-roberta-large` and is finetuned on the English subset of the [TyDiP](https://github.com/Genius1237/TyDiP) dataset as discussed in the original paper [here](https://aclanthology.org/2022.findings-emnlp.420/).
## Languages
In the paper, this model was evaluated on English + 9 Languages (Hindi, Korean, Spanish, Tamil, French, Vietnamese, Russian, Afrikaans, Hungarian). Given the model's good performance and XLMR's cross lingual abilities, it is likely that this finetuned model can be used for more languages as well.
## Evaluation
The politeness classification accuracy scores on 10 languages from the TyDiP test set are mentioned below.
| lang | acc |
|------|-------|
| en | 0.892 |
| hi | 0.868 |
| ko | 0.784 |
| es | 0.84 |
| ta | 0.78 |
| fr | 0.82 |
| vi | 0.844 |
| ru | 0.668 |
| af | 0.856 |
| hu | 0.812 |
## Usage
You can use this model directly with a text-classification pipeline
```python
from transformers import pipeline
classifier = pipeline(task="text-classification", model="Genius1237/xlm-roberta-large-tydip")
sentences = ["Could you please get me a glass of water", "mere liye पानी का एक गिलास ले आओ "]
print(classifier(sentences))
# [{'label': 'polite', 'score': 0.9076159000396729}, {'label': 'impolite', 'score': 0.765066385269165}]
```
More advanced usage
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
tokenizer = AutoTokenizer.from_pretrained('Genius1237/xlm-roberta-large-tydip')
model = AutoModelForSequenceClassification.from_pretrained('Genius1237/xlm-roberta-large-tydip')
text = "Could you please get me a glass of water"
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
prediction = torch.argmax(output.logits).item()
print(model.config.id2label[prediction])
# polite
```
## Citation
```
@inproceedings{srinivasan-choi-2022-tydip,
title = "{T}y{D}i{P}: A Dataset for Politeness Classification in Nine Typologically Diverse Languages",
author = "Srinivasan, Anirudh and
Choi, Eunsol",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.420",
doi = "10.18653/v1/2022.findings-emnlp.420",
pages = "5723--5738",
abstract = "We study politeness phenomena in nine typologically diverse languages. Politeness is an important facet of communication and is sometimes argued to be cultural-specific, yet existing computational linguistic study is limited to English. We create TyDiP, a dataset containing three-way politeness annotations for 500 examples in each language, totaling 4.5K examples. We evaluate how well multilingual models can identify politeness levels {--} they show a fairly robust zero-shot transfer ability, yet fall short of estimated human accuracy significantly. We further study mapping the English politeness strategy lexicon into nine languages via automatic translation and lexicon induction, analyzing whether each strategy{'}s impact stays consistent across languages. Lastly, we empirically study the complicated relationship between formality and politeness through transfer experiments. We hope our dataset will support various research questions and applications, from evaluating multilingual models to constructing polite multilingual agents.",
}
``` |
yentinglin/Taiwan-LLM-7B-v2.0-base | yentinglin | "2023-12-01T02:36:37Z" | 994 | 14 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"zh",
"arxiv:2311.17487",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-06T10:06:12Z" | ---
license: apache-2.0
language:
- zh
widget:
- text: "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: 你好，請問你可以幫我寫一封推薦信嗎？ ASSISTANT:"
library_name: transformers
pipeline_tag: text-generation
extra_gated_heading: Acknowledge license to accept the repository.
extra_gated_prompt: Please contact the author for access.
extra_gated_button_content: Acknowledge license 同意以上內容
extra_gated_fields:
Name: text
Mail: text
Organization: text
Country: text
Any utilization of the Taiwan LLM repository mandates the explicit acknowledgment and attribution to the original author: checkbox
使用Taiwan LLM必須明確地承認和歸功於優必達株式會社 Ubitus 以及原始作者: checkbox
---
<img src="https://cdn-uploads.huggingface.co/production/uploads/5df9c78eda6d0311fd3d541f/CmusIT5OlSXvFrbTJ7l-C.png" alt="Taiwan LLM Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# 🌟 Checkout [Taiwan-LLM Demo Chat-UI](http://www.twllm.com) 🌟
# Model Card for Taiwan LLM 7B v2.0 base
Taiwan LLM is an advanced language model tailored for Traditional Chinese, focusing on the linguistic and cultural contexts of Taiwan.
Developed from a large base model, it's enriched with diverse Taiwanese textual sources and refined through Supervised Fine-Tuning.
This model excels in language understanding and generation, aligning closely with Taiwan's cultural nuances.
It demonstrates improved performance on various benchmarks like TC-Eval, showcasing its contextual comprehension and cultural relevance.
For detailed insights into Taiwan LLM's development and features, refer to our [technical report](https://github.com/MiuLab/Taiwan-LLaMa/blob/main/twllm_paper.pdf).
## Model description
- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily Traditional Chinese (zh-tw)
- **Finetuned from model:** [meta-llama/Llama-2-7b-hf](https://huggingface.co/yentinglin/meta-llama/Llama-2-7b-hf)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/MiuLab/Taiwan-LLaMa
- **Demo:** https://twllm.com/
## Performance
## Intended uses
You should fine-tuned this model for instruction-following / chat application.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5.0
## Citation
If you find Taiwan LLM is useful in your work, please cite it with:
```
@misc{lin2023taiwan,
title={Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model},
author={Yen-Ting Lin and Yun-Nung Chen},
year={2023},
eprint={2311.17487},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
# Acknowledgement
Taiwan LLM v2 is conducted in collaboration with [Ubitus K.K.](http://ubitus.net). Ubitus provides valuable compute resources for the project.
|
CorticalStack/shadow-clown-7B-dare | CorticalStack | "2024-03-03T10:46:33Z" | 994 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"CorticalStack/pastiche-crown-clown-7b-dare-dpo",
"CultriX/NeuralTrix-7B-dpo",
"CorticalStack/neurotic-crown-clown-7b-ties",
"arxiv:2311.03099",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-03T10:36:43Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- CorticalStack/pastiche-crown-clown-7b-dare-dpo
- CultriX/NeuralTrix-7B-dpo
- CorticalStack/neurotic-crown-clown-7b-ties
---
<img src="shadow_clown.png" alt="Shadow clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# shadow-clown-7B-dare
shadow-clown-7B-dare is a DARE merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [CorticalStack/pastiche-crown-clown-7b-dare-dpo](https://huggingface.co/CorticalStack/pastiche-crown-clown-7b-dare-dpo)
* [CultriX/NeuralTrix-7B-dpo](https://huggingface.co/CultriX/NeuralTrix-7B-dpo)
* [CorticalStack/neurotic-crown-clown-7b-ties](https://huggingface.co/CorticalStack/neurotic-crown-clown-7b-ties)
See the paper [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://arxiv.org/abs/2311.03099) for more on the method.
## 🧩 Configuration
```yaml
models:
- model: yam-peleg/Experiment26-7B
- model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
parameters:
density: 0.52
weight: 0.4
- model: CultriX/NeuralTrix-7B-dpo
parameters:
density: 0.52
weight: 0.2
- model: CorticalStack/neurotic-crown-clown-7b-ties
parameters:
density: 0.52
weight: 0.3
merge_method: dare_ties
base_model: yam-peleg/Experiment26-7B
parameters:
int8_mask: true
dtype: bfloat16
``` |
mychen76/mistral-7b-merged-slerp | mychen76 | "2024-03-22T21:57:25Z" | 994 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-09T23:02:03Z" | ---
license: apache-2.0
tags:
- merge
---
# mistral-7b-merged-slerp
mistral-7b-merged-slerp is a merge of the following models:
## 🧩 Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mychen76/mistral-7b-merged-slerp"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "why the sky is blue."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-slerp)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.09|
|AI2 Reasoning Challenge (25-Shot)|67.75|
|HellaSwag (10-Shot) |86.17|
|MMLU (5-Shot) |64.05|
|TruthfulQA (0-shot) |59.85|
|Winogrande (5-shot) |80.19|
|GSM8k (5-shot) |68.54|
|
SaisExperiments/Experiment-3 | SaisExperiments | "2024-04-04T13:24:19Z" | 994 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T10:57:38Z" | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
* Capybara-ShareGPT on Experiment-2
* Experiment-2 is Pippa-ShareGPT-Trimmed on Mistral-7B-0.1
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
qwp4w3hyb/Phi-3-mini-128k-instruct-iMat-GGUF | qwp4w3hyb | "2024-05-22T09:04:21Z" | 994 | 0 | null | [
"gguf",
"nlp",
"code",
"microsoft",
"phi",
"instruct",
"finetune",
"imatrix",
"importance matrix",
"text-generation",
"multilingual",
"base_model:microsoft/Phi-3-mini-128k-instruct",
"license:mit",
"region:us"
] | text-generation | "2024-04-26T22:05:19Z" | ---
license: mit
license_link: >-
https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE
language:
- multilingual
pipeline_tag: text-generation
base_model: microsoft/Phi-3-mini-128k-instruct
tags:
- nlp
- code
- microsoft
- phi
- instruct
- finetune
- gguf
- imatrix
- importance matrix
---
# Quant Infos
- Requires latest llama.cpp master;
- quants done with an importance matrix for improved quantization loss
- gguf & imatrix generated from bf16 for "optimal" accuracy loss (some say this is snake oil, but it can't hurt)
- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [201cc11afa0a1950e1f632390b2ac6c937a0d8f0](https://github.com/ggerganov/llama.cpp/commit/201cc11afa0a1950e1f632390b2ac6c937a0d8f0)
- Imatrix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) multi-purpose dataset.
```
./imatrix -c 512 -m $model_name-bf16.gguf -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-bf16-gmerged.dat
```
# Original Model Card:
## Model Summary
The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets.
This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties.
The model belongs to the Phi-3 family with the Mini version in two variants [4K](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) which is the context length (in tokens) that it can support.
After initial training, the model underwent a post-training process that involved supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures.
When evaluated against benchmarks that test common sense, language understanding, mathematics, coding, long-term context, and logical reasoning, the Phi-3 Mini-128K-Instruct demonstrated robust and state-of-the-art performance among models with fewer than 13 billion parameters.
Resources and Technical Documentation:
+ [Phi-3 Microsoft Blog](https://aka.ms/phi3blog-april)
+ [Phi-3 Technical Report](https://aka.ms/phi3-tech-report)
+ [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai)
+ Phi-3 ONNX: [128K](https://aka.ms/Phi3-mini-128k-instruct-onnx)
## Intended Uses
**Primary use cases**
The model is intended for commercial and research use in English. The model provides uses for applications which require:
1) Memory/compute constrained environments
2) Latency bound scenarios
3) Strong reasoning (especially code, math and logic)
Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.
**Use case considerations**
Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case.
Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.
## How to Use
Phi-3 Mini-128K-Instruct has been integrated in the development version (4.40.0) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following:
* When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function.
* Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source.
The current `transformers` version can be verified with: `pip list | grep transformers`.
### Tokenizer
Phi-3 Mini-128K-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.
### Chat Format
Given the nature of the training data, the Phi-3 Mini-128K-Instruct model is best suited for prompts using the chat format as follows.
You can provide the prompt as a question with a generic template as follow:
```markdown
<|user|>\nQuestion<|end|>\n<|assistant|>
```
For example:
```markdown
<|system|>
You are a helpful AI assistant.<|end|>
<|user|>
How to explain Internet for a medieval knight?<|end|>
<|assistant|>
```
where the model generates the text after `<|assistant|>`. In case of few-shots prompt, the prompt can be formatted as the following:
```markdown
<|system|>
You are a helpful AI assistant.<|end|>
<|user|>
I am going to Paris, what should I see?<|end|>
<|assistant|>
Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|>
<|user|>
What is so great about #1?<|end|>
<|assistant|>
```
### Sample inference code
This code snippets show how to get quickly started with running the model on a GPU:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
torch.random.manual_seed(0)
model = AutoModelForCausalLM.from_pretrained(
"microsoft/Phi-3-mini-128k-instruct",
device_map="cuda",
torch_dtype="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
messages = [
{"role": "system", "content": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user."},
{"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
{"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
{"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
)
generation_args = {
"max_new_tokens": 500,
"return_full_text": False,
"temperature": 0.0,
"do_sample": False,
}
output = pipe(messages, **generation_args)
print(output[0]['generated_text'])
```
*Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.*
## Responsible AI Considerations
Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:
+ Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.
+ Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.
+ Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.
+ Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.
+ Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.
Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:
+ Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.
+ High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.
+ Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).
+ Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.
+ Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.
## Training
### Model
* Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.
* Inputs: Text. It is best suited for prompts using chat format.
* Context length: 128K tokens
* GPUs: 512 H100-80G
* Training time: 7 days
* Training data: 3.3T tokens
* Outputs: Generated text in response to the input
* Dates: Our models were trained between February and April 2024
* Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models.
### Datasets
Our training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of
1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code;
2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.);
3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness.
### Fine-tuning
A basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided [here](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/sample_finetune.py).
## Benchmarks
We report the results for Phi-3-Mini-128K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5.
All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation.
As is now standard, we use few-shot prompts to evaluate the models, at temperature 0.
The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3.
More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model.
The number of k–shot examples is listed per-benchmark.
| | Phi-3-Mini-128K-In<br>3.8b | Phi-3-Small<br>7b (preview) | Phi-3-Medium<br>14b (preview) | Phi-2<br>2.7b | Mistral<br>7b | Gemma<br>7b | Llama-3-In<br>8b | Mixtral<br>8x7b | GPT-3.5<br>version 1106 |
|---|---|---|---|---|---|---|---|---|---|
| MMLU <br>5-Shot | 68.1 | 75.3 | 78.2 | 56.3 | 61.7 | 63.6 | 66.5 | 68.4 | 71.4 |
| HellaSwag <br> 5-Shot | 74.5 | 78.7 | 83.2 | 53.6 | 58.5 | 49.8 | 71.1 | 70.4 | 78.8 |
| ANLI <br> 7-Shot | 52.8 | 55.0 | 58.7 | 42.5 | 47.1 | 48.7 | 57.3 | 55.2 | 58.1 |
| GSM-8K <br> 0-Shot; CoT | 83.6 | 86.4 | 90.8 | 61.1 | 46.4 | 59.8 | 77.4 | 64.7 | 78.1 |
| MedQA <br> 2-Shot | 55.3 | 58.2 | 69.8 | 40.9 | 49.6 | 50.0 | 60.5 | 62.2 | 63.4 |
| AGIEval <br> 0-Shot | 36.9 | 45.0 | 49.7 | 29.8 | 35.1 | 42.1 | 42.0 | 45.2 | 48.4 |
| TriviaQA <br> 5-Shot | 57.1 | 59.1 | 73.3 | 45.2 | 72.3 | 75.2 | 67.7 | 82.2 | 85.8 |
| Arc-C <br> 10-Shot | 84.0 | 90.7 | 91.9 | 75.9 | 78.6 | 78.3 | 82.8 | 87.3 | 87.4 |
| Arc-E <br> 10-Shot | 95.2 | 97.1 | 98.0 | 88.5 | 90.6 | 91.4 | 93.4 | 95.6 | 96.3 |
| PIQA <br> 5-Shot | 83.6 | 87.8 | 88.2 | 60.2 | 77.7 | 78.1 | 75.7 | 86.0 | 86.6 |
| SociQA <br> 5-Shot | 76.1 | 79.0 | 79.4 | 68.3 | 74.6 | 65.5 | 73.9 | 75.9 | 68.3 |
| BigBench-Hard <br> 0-Shot | 71.5 | 75.0 | 82.5 | 59.4 | 57.3 | 59.6 | 51.5 | 69.7 | 68.32 |
| WinoGrande <br> 5-Shot | 72.5 | 82.5 | 81.2 | 54.7 | 54.2 | 55.6 | 65.0 | 62.0 | 68.8 |
| OpenBookQA <br> 10-Shot | 80.6 | 88.4 | 86.6 | 73.6 | 79.8 | 78.6 | 82.6 | 85.8 | 86.0 |
| BoolQ <br> 0-Shot | 78.7 | 82.9 | 86.5 | -- | 72.2 | 66.0 | 80.9 | 77.6 | 79.1 |
| CommonSenseQA <br> 10-Shot | 78.0 | 80.3 | 82.6 | 69.3 | 72.6 | 76.2 | 79 | 78.1 | 79.6 |
| TruthfulQA <br> 10-Shot | 63.2 | 68.1 | 74.8 | -- | 52.1 | 53.0 | 63.2 | 60.1 | 85.8 |
| HumanEval <br> 0-Shot | 57.9 | 59.1 | 54.7 | 47.0 | 28.0 | 34.1 | 60.4| 37.8 | 62.2 |
| MBPP <br> 3-Shot | 62.5 | 71.4 | 73.7 | 60.6 | 50.8 | 51.5 | 67.7 | 60.2 | 77.8 |
## Software
* [PyTorch](https://github.com/pytorch/pytorch)
* [DeepSpeed](https://github.com/microsoft/DeepSpeed)
* [Transformers](https://github.com/huggingface/transformers)
* [Flash-Attention](https://github.com/HazyResearch/flash-attention)
## Hardware
Note that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:
* NVIDIA A100
* NVIDIA A6000
* NVIDIA H100
If you want to run the model on:
* NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from_pretrained() with attn_implementation="eager"
* Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [128K](https://aka.ms/phi3-mini-128k-instruct-onnx)
## Cross Platform Support
ONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-128K-Instruct ONNX model [here](https://aka.ms/phi3-mini-128k-instruct-onnx).
Optimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs.
Along with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile.
Here are some of the optimized configurations we have added:
1. ONNX models for int4 DML: Quantized to int4 via AWQ
2. ONNX model for fp16 CUDA
3. ONNX model for int4 CUDA: Quantized to int4 via RTN
4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN
## License
The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-mini-128k/resolve/main/LICENSE).
## Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
|
minmingzhu02/Mistral-7B-v0.1-llm-on-ray-deepspeed-lora | minmingzhu02 | "2024-06-17T09:16:28Z" | 994 | 0 | peft | [
"peft",
"safetensors",
"optimum_habana",
"region:us"
] | null | "2024-06-17T09:16:19Z" | ---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0
|
mrm8488/codebert-base-finetuned-detect-insecure-code | mrm8488 | "2021-05-20T18:19:02Z" | 993 | 24 | transformers | [
"transformers",
"pytorch",
"jax",
"roberta",
"text-classification",
"en",
"dataset:codexglue",
"arxiv:2002.08155",
"arxiv:1907.11692",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-03-02T23:29:05Z" | ---
language: en
datasets:
- codexglue
---
# CodeBERT fine-tuned for Insecure Code Detection 💾⛔
[codebert-base](https://huggingface.co/microsoft/codebert-base) fine-tuned on [CodeXGLUE -- Defect Detection](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/Defect-detection) dataset for **Insecure Code Detection** downstream task.
## Details of [CodeBERT](https://arxiv.org/abs/2002.08155)
We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both bimodal data of NL-PL pairs and unimodal data, where the former provides input tokens for model training while the latter helps to learn better generators. We evaluate CodeBERT on two NL-PL applications by fine-tuning model parameters. Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks. Furthermore, to investigate what type of knowledge is learned in CodeBERT, we construct a dataset for NL-PL probing, and evaluate in a zero-shot setting where parameters of pre-trained models are fixed. Results show that CodeBERT performs better than previous pre-trained models on NL-PL probing.
## Details of the downstream task (code classification) - Dataset 📚
Given a source code, the task is to identify whether it is an insecure code that may attack software systems, such as resource leaks, use-after-free vulnerabilities and DoS attack. We treat the task as binary classification (0/1), where 1 stands for insecure code and 0 for secure code.
The [dataset](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/Defect-detection) used comes from the paper [*Devign*: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](http://papers.nips.cc/paper/9209-devign-effective-vulnerability-identification-by-learning-comprehensive-program-semantics-via-graph-neural-networks.pdf). All projects are combined and splitted 80%/10%/10% for training/dev/test.
Data statistics of the dataset are shown in the below table:
| | #Examples |
| ----- | :-------: |
| Train | 21,854 |
| Dev | 2,732 |
| Test | 2,732 |
## Test set metrics 🧾
| Methods | ACC |
| -------- | :-------: |
| BiLSTM | 59.37 |
| TextCNN | 60.69 |
| [RoBERTa](https://arxiv.org/pdf/1907.11692.pdf) | 61.05 |
| [CodeBERT](https://arxiv.org/pdf/2002.08155.pdf) | 62.08 |
| [Ours](https://huggingface.co/mrm8488/codebert-base-finetuned-detect-insecure-code) | **65.30** |
## Model in Action 🚀
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import numpy as np
tokenizer = AutoTokenizer.from_pretrained('mrm8488/codebert-base-finetuned-detect-insecure-code')
model = AutoModelForSequenceClassification.from_pretrained('mrm8488/codebert-base-finetuned-detect-insecure-code')
inputs = tokenizer("your code here", return_tensors="pt", truncation=True, padding='max_length')
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(**inputs, labels=labels)
loss = outputs.loss
logits = outputs.logits
print(np.argmax(logits.detach().numpy()))
```
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/)
> Made with <span style="color: #e25555;">♥</span> in Spain
|
uclanlp/plbart-python-en_XX | uclanlp | "2021-11-09T17:09:27Z" | 993 | 3 | transformers | [
"transformers",
"pytorch",
"plbart",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2022-03-02T23:29:05Z" | Entry not found |
microsoft/xclip-base-patch16 | microsoft | "2022-09-08T11:06:25Z" | 993 | 0 | transformers | [
"transformers",
"pytorch",
"xclip",
"feature-extraction",
"vision",
"video-classification",
"en",
"arxiv:2208.02816",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
] | video-classification | "2022-09-07T14:55:19Z" | ---
language: en
license: mit
tags:
- vision
- video-classification
model-index:
- name: nielsr/xclip-base-patch16
results:
- task:
type: video-classification
dataset:
name: Kinetics 400
type: kinetics-400
metrics:
- type: top-1 accuracy
value: 83.8
- type: top-5 accuracy
value: 95.7
---
# X-CLIP (base-sized model)
X-CLIP model (base-sized, patch resolution of 16) trained fully-supervised on [Kinetics-400](https://www.deepmind.com/open-source/kinetics). It was introduced in the paper [Expanding Language-Image Pretrained Models for General Video Recognition](https://arxiv.org/abs/2208.02816) by Ni et al. and first released in [this repository](https://github.com/microsoft/VideoX/tree/master/X-CLIP).
This model was trained using 8 frames per video, at a resolution of 224x224.
Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
X-CLIP is a minimal extension of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
This allows the model to be used for tasks like zero-shot, few-shot or fully supervised video classification and video-text retrieval.
## Intended uses & limitations
You can use the raw model for determining how well text goes with a given video. See the [model hub](https://huggingface.co/models?search=microsoft/xclip) to look for
fine-tuned versions on a task that interests you.
### How to use
For code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/xclip.html#).
## Training data
This model was trained on [Kinetics-400](https://www.deepmind.com/open-source/kinetics).
### Preprocessing
The exact details of preprocessing during training can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L247).
The exact details of preprocessing during validation can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L285).
During validation, one resizes the shorter edge of each frame, after which center cropping is performed to a fixed-size resolution (like 224x224). Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
## Evaluation results
This model achieves a top-1 accuracy of 83.8% and a top-5 accuracy of 95.7%.
|
timm/eva_large_patch14_196.in22k_ft_in1k | timm | "2024-02-10T23:27:53Z" | 993 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2211.07636",
"license:mit",
"region:us"
] | image-classification | "2022-12-22T07:05:00Z" | ---
license: mit
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for eva_large_patch14_196.in22k_ft_in1k
An EVA image classification model. Pretrained on ImageNet-22k with masked image modeling (using EVA-CLIP as a MIM teacher) and fine-tuned on ImageNet-1k by paper authors.
NOTE: `timm` checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 304.1
- GMACs: 61.6
- Activations (M): 63.5
- Image size: 196 x 196
- **Papers:**
- EVA: Exploring the Limits of Masked Visual Representation Learning at Scale: https://arxiv.org/abs/2211.07636
- **Pretrain Dataset:** ImageNet-22k
- **Dataset:** ImageNet-1k
- **Original:**
- https://github.com/baaivision/EVA
- https://huggingface.co/BAAI/EVA
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('eva_large_patch14_196.in22k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'eva_large_patch14_196.in22k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 1024) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |top1 |top5 |param_count|img_size|
|-----------------------------------------------|------|------|-----------|--------|
|eva02_large_patch14_448.mim_m38m_ft_in22k_in1k |90.054|99.042|305.08 |448 |
|eva02_large_patch14_448.mim_in22k_ft_in22k_in1k|89.946|99.01 |305.08 |448 |
|eva_giant_patch14_560.m30m_ft_in22k_in1k |89.792|98.992|1014.45 |560 |
|eva02_large_patch14_448.mim_in22k_ft_in1k |89.626|98.954|305.08 |448 |
|eva02_large_patch14_448.mim_m38m_ft_in1k |89.57 |98.918|305.08 |448 |
|eva_giant_patch14_336.m30m_ft_in22k_in1k |89.56 |98.956|1013.01 |336 |
|eva_giant_patch14_336.clip_ft_in1k |89.466|98.82 |1013.01 |336 |
|eva_large_patch14_336.in22k_ft_in22k_in1k |89.214|98.854|304.53 |336 |
|eva_giant_patch14_224.clip_ft_in1k |88.882|98.678|1012.56 |224 |
|eva02_base_patch14_448.mim_in22k_ft_in22k_in1k |88.692|98.722|87.12 |448 |
|eva_large_patch14_336.in22k_ft_in1k |88.652|98.722|304.53 |336 |
|eva_large_patch14_196.in22k_ft_in22k_in1k |88.592|98.656|304.14 |196 |
|eva02_base_patch14_448.mim_in22k_ft_in1k |88.23 |98.564|87.12 |448 |
|eva_large_patch14_196.in22k_ft_in1k |87.934|98.504|304.14 |196 |
|eva02_small_patch14_336.mim_in22k_ft_in1k |85.74 |97.614|22.13 |336 |
|eva02_tiny_patch14_336.mim_in22k_ft_in1k |80.658|95.524|5.76 |336 |
## Citation
```bibtex
@article{EVA,
title={EVA: Exploring the Limits of Masked Visual Representation Learning at Scale},
author={Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2211.07636},
year={2022}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf | RichardErkhov | "2024-06-05T11:47:51Z" | 993 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-05T11:36:41Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
MagicPrompt-Dalle - GGUF
- Model creator: https://huggingface.co/Gustavosta/
- Original model: https://huggingface.co/Gustavosta/MagicPrompt-Dalle/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [MagicPrompt-Dalle.Q2_K.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q2_K.gguf) | Q2_K | 0.08GB |
| [MagicPrompt-Dalle.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.IQ3_XS.gguf) | IQ3_XS | 0.08GB |
| [MagicPrompt-Dalle.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.IQ3_S.gguf) | IQ3_S | 0.08GB |
| [MagicPrompt-Dalle.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q3_K_S.gguf) | Q3_K_S | 0.08GB |
| [MagicPrompt-Dalle.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.IQ3_M.gguf) | IQ3_M | 0.09GB |
| [MagicPrompt-Dalle.Q3_K.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q3_K.gguf) | Q3_K | 0.09GB |
| [MagicPrompt-Dalle.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q3_K_M.gguf) | Q3_K_M | 0.09GB |
| [MagicPrompt-Dalle.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q3_K_L.gguf) | Q3_K_L | 0.1GB |
| [MagicPrompt-Dalle.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.IQ4_XS.gguf) | IQ4_XS | 0.1GB |
| [MagicPrompt-Dalle.Q4_0.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q4_0.gguf) | Q4_0 | 0.1GB |
| [MagicPrompt-Dalle.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.IQ4_NL.gguf) | IQ4_NL | 0.1GB |
| [MagicPrompt-Dalle.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q4_K_S.gguf) | Q4_K_S | 0.1GB |
| [MagicPrompt-Dalle.Q4_K.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q4_K.gguf) | Q4_K | 0.11GB |
| [MagicPrompt-Dalle.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q4_K_M.gguf) | Q4_K_M | 0.11GB |
| [MagicPrompt-Dalle.Q4_1.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q4_1.gguf) | Q4_1 | 0.11GB |
| [MagicPrompt-Dalle.Q5_0.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q5_0.gguf) | Q5_0 | 0.11GB |
| [MagicPrompt-Dalle.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q5_K_S.gguf) | Q5_K_S | 0.11GB |
| [MagicPrompt-Dalle.Q5_K.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q5_K.gguf) | Q5_K | 0.12GB |
| [MagicPrompt-Dalle.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q5_K_M.gguf) | Q5_K_M | 0.12GB |
| [MagicPrompt-Dalle.Q5_1.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q5_1.gguf) | Q5_1 | 0.12GB |
| [MagicPrompt-Dalle.Q6_K.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q6_K.gguf) | Q6_K | 0.13GB |
| [MagicPrompt-Dalle.Q8_0.gguf](https://huggingface.co/RichardErkhov/Gustavosta_-_MagicPrompt-Dalle-gguf/blob/main/MagicPrompt-Dalle.Q8_0.gguf) | Q8_0 | 0.17GB |
Original model description:
---
license: mit
---
# MagicPrompt - Dall-E 2
This is a model from the MagicPrompt series of models, which are [GPT-2](https://huggingface.co/gpt2) models intended to generate prompt texts for imaging AIs, in this case: [Dall-E 2](https://openai.com/dall-e-2/).
## 🖼️ Here's an example:
<img src="https://files.catbox.moe/h10plz.png">
This model was trained with a set of about 26k of data filtered and extracted from various places such as: [The Web Archive](https://web.archive.org/web/*/https://labs.openai.com/s/*), [The SubReddit for Dall-E 2](https://www.reddit.com/r/dalle2) and [dalle2.gallery](https://dalle2.gallery/#search). This may be a relatively small dataset, but we have to consider that Dall-E 2 is a closed service and we only have prompts from people who share it and have access to the service, for now. The set was trained with about 40,000 steps and I have plans to improve the model if possible.
If you want to test the model with a demo, you can go to: "[spaces/Gustavosta/MagicPrompt-Dalle](https://huggingface.co/spaces/Gustavosta/MagicPrompt-Dalle)".
## 💻 You can see other MagicPrompt models:
- For Stable Diffusion: [Gustavosta/MagicPrompt-Stable-Diffusion](https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion)
- For Midjourney: [Gustavosta/MagicPrompt-Midjourney](https://huggingface.co/Gustavosta/MagicPrompt-Midjourney) **[⚠️ In progress]**
- MagicPrompt full: [Gustavosta/MagicPrompt](https://huggingface.co/Gustavosta/MagicPrompt) **[⚠️ In progress]**
## ⚖️ Licence:
[MIT](https://huggingface.co/models?license=license:mit)
When using this model, please credit: [Gustavosta](https://huggingface.co/Gustavosta)
**Thanks for reading this far! :)**
|
KnutJaegersberg/RWKV-4-PilePlus-430M-20230520-6162-1018Gtokens-ctx4098 | KnutJaegersberg | "2023-09-05T09:59:27Z" | 992 | 0 | transformers | [
"transformers",
"pytorch",
"rwkv",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2023-09-05T08:54:51Z" | ---
license: apache-2.0
---
This is just a standard conversion to hf transformers format of models from here:
https://huggingface.co/BlinkDL/rwkv-4-pileplus
According to the documentation I found, this model should have seen roundabout 1.3 trillion tokens! |
abacusai/MM-OV-bagel-DPO-34b-c1000-250 | abacusai | "2024-01-24T04:17:48Z" | 992 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"dataset:abacusai/MetaMathFewshot",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-23T22:00:23Z" | ---
license: apache-2.0
datasets:
- abacusai/MetaMathFewshot
---
DPO finetune of (https://huggingface.co/abacusai/MM-Orc-Vic-bagel-34b-c1000) on the Bagel DPO dataset
### Evaluation Results
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- |
| | | | | | | | |
mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF | mradermacher | "2024-05-10T16:46:16Z" | 992 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:grimulkan/llama2_70b_longlora_fp16_32k_ROPE8",
"license:llama2",
"endpoints_compatible",
"region:us"
] | null | "2024-03-09T22:00:21Z" | ---
base_model: grimulkan/llama2_70b_longlora_fp16_32k_ROPE8
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
---
## About
weighted/imatrix quants of https://huggingface.co/grimulkan/llama2_70b_longlora_fp16_32k_ROPE8
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ2_S.gguf) | i1-IQ2_S | 21.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ2_M.gguf) | i1-IQ2_M | 23.7 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.6 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ3_S.gguf) | i1-IQ3_S | 30.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ3_M.gguf) | i1-IQ3_M | 31.4 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.9 | |
| [GGUF](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |
| [PART 1](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama2_70b_longlora_fp16_32k_ROPE8-i1-GGUF/resolve/main/llama2_70b_longlora_fp16_32k_ROPE8.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
timm/pvt_v2_b2.in1k | timm | "2023-04-25T04:03:51Z" | 991 | 1 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2106.13797",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-25T04:03:22Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for pvt_v2_b2
A PVT-v2 (Pyramid Vision Transformer) image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 25.4
- GMACs: 4.0
- Activations (M): 27.5
- Image size: 224 x 224
- **Papers:**
- PVT v2: Improved Baselines with Pyramid Vision Transformer: https://arxiv.org/abs/2106.13797
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/whai362/PVT
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('pvt_v2_b2', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'pvt_v2_b2',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 320, 14, 14])
# torch.Size([1, 512, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'pvt_v2_b2',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 512, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{wang2021pvtv2,
title={Pvtv2: Improved baselines with pyramid vision transformer},
author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
journal={Computational Visual Media},
volume={8},
number={3},
pages={1--10},
year={2022},
publisher={Springer}
}
```
|
shaowenchen/chinese-alpaca-2-13b-16k-gguf | shaowenchen | "2023-09-12T00:51:47Z" | 991 | 8 | null | [
"gguf",
"meta",
"llama",
"llama-2",
"alpaca",
"alpaca-2",
"chinese",
"text-generation",
"zh",
"license:other",
"region:us"
] | text-generation | "2023-09-08T23:21:12Z" | ---
inference: false
language:
- zh
license: other
model_creator: ziqingyang
model_link: https://huggingface.co/ziqingyang/chinese-alpaca-2-13b-16k
model_name: chinese-alpaca-2-13b-16k
model_type: llama
pipeline_tag: text-generation
quantized_by: shaowenchen
tasks:
- text2text-generation
tags:
- meta
- gguf
- llama
- llama-2
- alpaca
- alpaca-2
- chinese
---
## Provided files
| Name | Quant method | Size |
| ------------------------------------ | ------------ | ------- |
| chinese-alpaca-2-13b-16k.Q2_K.gguf | Q2_K | 5.2 GB |
| chinese-alpaca-2-13b-16k.Q3_K.gguf | Q3_K | 6.0 GB |
| chinese-alpaca-2-13b-16k.Q3_K_L.gguf | Q3_K_L | 6.6 GB |
| chinese-alpaca-2-13b-16k.Q3_K_S.gguf | Q3_K_S | 5.4 GB |
| chinese-alpaca-2-13b-16k.Q4_0.gguf | Q4_0 | 7.0 GB |
| chinese-alpaca-2-13b-16k.Q4_1.gguf | Q4_1 | 7.8 GB |
| chinese-alpaca-2-13b-16k.Q4_K.gguf | Q4_K | 7.5 GB |
| chinese-alpaca-2-13b-16k.Q4_K_S.gguf | Q4_K_S | 7.1 GB |
| chinese-alpaca-2-13b-16k.Q5_0.gguf | Q5_0 | 8.5 GB |
| chinese-alpaca-2-13b-16k.Q5_1.gguf | Q5_1 | 9.3 GB |
| chinese-alpaca-2-13b-16k.Q5_K.gguf | Q5_K | 8.8 GB |
| chinese-alpaca-2-13b-16k.Q5_K_S.gguf | Q5_K_S | 8.5 GB |
| chinese-alpaca-2-13b-16k.Q6_K.gguf | Q6_K | 10.0 GB |
| chinese-alpaca-2-13b-16k.Q8_0.gguf | Q8_0 | 13.0 GB |
| chinese-alpaca-2-13b-16k.gguf | full | 25.0 GB |
Usage:
```
docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/gguf-model-name.gguf hubimage/llama-cpp-python:latest
```
and you can view http://localhost:8000/docs to see the swagger UI.
|
llmware/bling-sheared-llama-1.3b-0.1 | llmware | "2024-02-13T08:59:27Z" | 991 | 25 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-22T17:03:12Z" | ---
license: apache-2.0
inference: false
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
bling-sheared-llama-1.3b-0.1 is part of the BLING ("Best Little Instruction-following No-GPU-required") model series, instruct trained on top of a Sheared-LLaMA-1.3B base model.
BLING models are fine-tuned with distilled high-quality custom instruct datasets, targeted at a specific subset of instruct tasks with
the objective of providing a high-quality Instruct model that is 'inference-ready' on a CPU laptop even
without using any advanced quantization optimizations.
### Benchmark Tests
Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)
Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.
--**Accuracy Score**: **84.50** correct out of 100
--Not Found Classification: 20.0%
--Boolean: 66.25%
--Math/Logic: 9.4%
--Complex Questions (1-5): 1 (Low)
--Summarization Quality (1-5): 3 (Coherent, extractive)
--Hallucinations: No hallucinations observed in test runs.
For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** llmware
- **Model type:** Instruct-trained decoder
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model [optional]:** princeton-nlp/Sheared-LLaMA-1.3B
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
The intended use of BLING models is two-fold:
1. Provide high-quality Instruct models that can run on a laptop for local testing. We have found it extremely useful when building a
proof-of-concept, or working with sensitive enterprise data that must be closely guarded, especially in RAG use cases.
2. Push the state of the art for smaller Instruct-following models in the sub-7B parameter range, especially 1B-3B, as single-purpose
automation tools for specific tasks through targeted fine-tuning datasets and focused "instruction" tasks.
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
legal and regulatory industries with complex information sources. Rather than try to be "all things to all people," BLING models try to focus on a narrower set of Instructions more suitable to a ~1B parameter GPT model.
BLING is ideal for rapid prototyping, testing, and the ability to perform an end-to-end workflow locally on a laptop without
having to send sensitive information over an Internet-based API.
The first BLING models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types
without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.
## How to Get Started with the Model
The fastest way to get started with BLING is through direct import in transformers:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("llmware/bling-sheared-llama-1.3b-0.1")
model = AutoModelForCausalLM.from_pretrained("llmware/bling-sheared-llama-1.3b-0.1")
Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
1. Text Passage Context, and
2. Specific question or instruction based on the text passage
To get the best results, package "my_prompt" as follows:
my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
If you are using a HuggingFace generation script:
# prepare prompt packaging used in fine-tuning process
new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"
inputs = tokenizer(new_prompt, return_tensors="pt")
start_of_output = len(inputs.input_ids[0])
# temperature: set at 0.3 for consistency of output
# max_new_tokens: set at 100 - may prematurely stop a few of the summaries
outputs = model.generate(
inputs.input_ids.to(device),
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.3,
max_new_tokens=100,
)
output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)
# note: due to artifact of the fine-tuning, use this post-processing with HF generation
eot = output_only.find("<|endoftext|>")
if eot > -1:
output_only = output_only[:eot]
## Citation [optional]
This BLING model was built on top of a "Sheared Llama" model base - for more information about the "Sheared Llama" model, please see the paper referenced below:
@article{xia2023sheared,
title={Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning},
author={Xia, Mengzhou and Gao, Tianyu, and Zeng Zhiyuan, and Chen Danqi},
year={2023}
}
## Model Card Contact
Darren Oberst & llmware team
|
kwchoi/DPO_mistral_7b_ultra_0129_1k | kwchoi | "2024-01-29T00:38:03Z" | 991 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"dataset:argilla/ultrafeedback-binarized-preferences-cleaned",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-29T00:26:26Z" | ---
license: apache-2.0
datasets:
- argilla/ultrafeedback-binarized-preferences-cleaned
language:
- en
---
Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance Testing Mistral-Instruct model with Orca DPO dataset. Trying to see the effects of DPO for own study. Used Mistral-7B-Instrcut-v0.2 model due to its good performance |
juhwanlee/llmdo-Mistral-7B-case-1 | juhwanlee | "2024-03-11T13:31:40Z" | 991 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:Open-Orca/OpenOrca",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-11T07:04:43Z" | ---
license: apache-2.0
datasets:
- Open-Orca/OpenOrca
language:
- en
---
# Model Details
* Model Description: This model is test for data ordering.
* Developed by: Juhwan Lee
* Model Type: Large Language Model
# Model Architecture
This model is based on Mistral-7B-v0.1. We fine-tuning this model for data ordering task.
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
* Grouped-Query Attention
* Sliding-Window Attention
* Byte-fallback BPE tokenizer
# Dataset
We random sample Open-Orca dataset. (We finetune the 100,000 dataset)
# Guthub
https://github.com/trailerAI
# License
Apache License 2.0 |
ChaoticNeutrals/RPMix-4x7B-MoE | ChaoticNeutrals | "2024-03-30T06:57:46Z" | 991 | 7 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"not-for-all-audiences",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-30T05:49:30Z" | ---
license: apache-2.0
language:
- en
tags:
- not-for-all-audiences
---
# RPMix 4x7B MoE
A mixture of experts model using my best scoring RP models. This model should primarily be used for RP and creative writing.
```
base_model: ResplendentAI/DaturaCookie_7B
gate_mode: hidden
experts_per_token: 2
experts:
- source_model: ChaoticNeutrals/RP_Vision_7B
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- "I want"
- source_model: ChaoticNeutrals/BuRP_7B
positive_prompts:
- "show me"
- "touch"
- "believe"
- "see"
- "love"
- source_model: ResplendentAI/DaturaCookie_7B
positive_prompts:
- "storywriting"
- "write"
- "scene"
- "story"
- "character"
- source_model: ChaoticNeutrals/Kool-Aid_7B
positive_prompts:
- "sensual"
- "sexual"
- "horny"
- "turned on"
- "intimate"
dtype: bfloat16
``` |
uclanlp/plbart-java-en_XX | uclanlp | "2021-11-09T17:08:51Z" | 990 | 0 | transformers | [
"transformers",
"pytorch",
"plbart",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2022-03-02T23:29:05Z" | Entry not found |
mzwing/Anything-GGUF | mzwing | "2024-03-15T06:03:05Z" | 990 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-03-15T00:13:51Z" | Entry not found |
LeroyDyer/Mixtral_AI_Cyber_4.0 | LeroyDyer | "2024-04-09T16:43:03Z" | 990 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"biology",
"chemistry",
"medical",
"conversational",
"en",
"base_model:LeroyDyer/Mixtral_AI_Cyber_3.m1",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-30T11:55:47Z" | ---
base_model:
- LeroyDyer/Mixtral_AI_Cyber_3.m1
- LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
- LeroyDyer/Mixtral_AI_Cyber_2.0
- LeroyDyer/Mixtral_AI_Cyber_1.0
- LeroyDyer/Mixtral_AI_Cyber_3.m2
- LeroyDyer/Mixtral_AI_Cyber_3.0
library_name: transformers
tags:
- biology
- chemistry
- medical
license: mit
language:
- en
metrics:
- bertscore
- code_eval
- character
---
### Models Merged
The following models were included in the merge:
* [LeroyDyer/Mixtral_AI_Cyber_3.m1](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.m1)
* [LeroyDyer/Mixtral_AI_Cyber_3.1_SFT](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.1_SFT)
* [LeroyDyer/Mixtral_AI_Cyber_2.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_2.0)
* [LeroyDyer/Mixtral_AI_Cyber_1.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_1.0)
* [LeroyDyer/Mixtral_AI_Cyber_3.0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: LeroyDyer/Mixtral_AI_Cyber_3.m2
parameters:
density: [0.256, 0.512, 0.128] # density gradient
weight: 0.382
- model: LeroyDyer/Mixtral_AI_Cyber_2.0
parameters:
density: 0.382
weight: [0.256, 0.128, 0.256, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_3.0
parameters:
density: 0.382
weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_3.m1
parameters:
density: 0.382
weight: [0.256, 0.256, 0.512, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_1.0
parameters:
density: 0.382
weight: [0.128, 0.512, 0.128, 0.128] # weight gradient
- model: LeroyDyer/Mixtral_AI_Cyber_3.1_SFT
parameters:
density: 0.382
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: ties
base_model: LeroyDyer/Mixtral_AI_Cyber_3.m2
parameters:
normalize: true
int8_mask: true
dtype: float16
``` |
Josephgflowers/Tinyllama-1.5B-Cinder-Test-2 | Josephgflowers | "2024-04-05T14:12:47Z" | 990 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-05T14:07:47Z" | ---
license: mit
---
This is a depth up scalled model of the 616M cinder model and Cinder v2. This model still needs further training. Putting it up for testing. More information coming. Maybe. Lol. Here is a brief desc of the project: Im mixing a lot of techniques I guess that I found interesting and have been testing, HF Cosmo is not great but decent and was fully trained in 4 days using a mix of more fine tuned directed datasets and some synthetic textbook style datasets. So I used pruning and a similar mix as Cosmo on tinyllama (trained on a ton of data for an extended time for its size) to keep the tinyllama model coherent during pruning. Now I am trying to depth up scale it using my pruned model and an original, Then taking a majority of each and combining them to create a larger model. Then it needs more training, then fine tuning. Then theoretically it will be a well performing 1.5B model (that didn't need full scale training).
Test 2, some training, re depth upscalled with cinder reason 1.3B and merged back with 1.5 and slight training. Continuing training from this model for next iteration. |
sampathkethineedi/industry-classification | sampathkethineedi | "2020-07-16T15:27:38Z" | 989 | 20 | transformers | [
"transformers",
"pytorch",
"tf",
"distilbert",
"text-classification",
"tensorflow",
"industry",
"buisiness",
"description",
"multi-class",
"classification",
"en",
"autotrain_compatible",
"region:us"
] | text-classification | "2022-03-02T23:29:05Z" | ---
language: "en"
thumbnail: "https://huggingface.co/sampathkethineedi"
tags:
- distilbert
- pytorch
- tensorflow
- text-classification
- industry
- buisiness
- description
- multi-class
- classification
liscence: "mit"
inference: false
---
# industry-classification
## Model description
DistilBERT Model to classify a business description into one of **62 industry tags**.
Trained on 7000 samples of Business Descriptions and associated labels of companies in India.
## How to use
PyTorch and TF models available
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("sampathkethineedi/industry-classification")
model = AutoModelForSequenceClassification.from_pretrained("sampathkethineedi/industry-classification")
industry_tags = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
industry_tags("Stellar Capital Services Limited is an India-based non-banking financial company ... loan against property, management consultancy, personal loans and unsecured loans.")
'''Ouput'''
[{'label': 'Consumer Finance', 'score': 0.9841355681419373}]
```
## Limitations and bias
Training data is only for Indian companies
|
raicrits/Hermes7b_ITA | raicrits | "2023-09-08T09:57:43Z" | 989 | 0 | transformers | [
"transformers",
"pytorch",
"LLM",
"Italian",
"Orca",
"Hermes",
"LLama2",
"text-generation",
"it",
"dataset:raicrits/Orca_ITA_200k",
"arxiv:2106.09685",
"arxiv:1910.09700",
"license:other",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-08-04T08:12:27Z" | ---
license: other
datasets:
- raicrits/Orca_ITA_200k
language:
- it
pipeline_tag: text-generation
tags:
- LLM
- Italian
- Orca
- Hermes
- LLama2
library_name: transformers
---
# Model Card for Model raicrits/Hermes7b_ITA
<!-- Provide a quick summary of what the model is/does. -->
An open-source LLaMa2 language model of 7b parameters fine-tuned (using as base model [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b)) to follow instructions in italian.
### Model Description
This model is a LLM of 7b parameters based on [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b), a version of [meta-llama/Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b) fine-tuned to follow instructions.
The model was further fine-tuned in order to follow instructions in italian, using [LoRA](https://arxiv.org/abs/2106.09685) approach and a dataset of 120k random pairs of instruction/answer from [raicrits/Orca_ITA_200k](https://huggingface.co/datasets/raicrits/Orca_ITA_200k).
This repository contains the model weights merged with the LoRA adapters obtained in the fine-tuning procedure.
- **Developed by:** Stefano Scotta ([email protected])
- **Model type:** LLM fine-tuned to follow instructions
- **Language(s) (NLP):** Italian
- **License:** Other
- **Finetuned from model:** [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b)
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
The model can be used as is to respond to simple instructions in Italian or can be further fine-tuned to perform specific tasks.
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
As any other LLM it is possible that the model generates content which does not correspond to the reality as well as wrong, biased, offensive and inappropriate answers.
## How to Get Started with the Model
**Prompt template:**
``` python
"""### Instruction: {instruction}
### Response:
"""
```
**Usage:**
Use the code below to get started with the model.
``` python
import os
import torch
import sys
from transformers import LlamaForCausalLM, AutoTokenizer
def generate_prompt_test(instruction):
prompt = f"""### Instruction: {instruction}
### Response:
"""
return prompt
model_name = "raicrits/Hermes7b_ITA"
model = LlamaForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype=torch.bfloat16
)
model.config.use_cache = True
tokenizer = AutoTokenizer.from_pretrained(model_name, add_eos_token=False)
prompt = generate_prompt_test("Cosa puoi dirmi sul dio Hermes?")
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, do_sample = True, num_beams = 2, top_k=50, top_p= 0.95, max_new_tokens=256, early_stopping = True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True).split("Response:")[1].strip())
```
``` python
"""Hermes è un dio dell'antica Grecia. Era il dio del commercio, della comunicazione e del trasporto. Era anche il dio della mente e della intelligenza. Era noto per il suo eloquente linguaggio e la sua capacità di spostarsi velocemente. Era considerato il messaggero degli dèi e spesso veniva raffigurato con un cappello di pelle di capra e sandali."""
```
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
The model was fine-tuned on 120k random records of [raicrits/Orca_ITA_200k](https://huggingface.co/datasets/raicrits/Orca_ITA_200k).
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
The fine-tuning procedure was done using [LoRA](https://arxiv.org/abs/2106.09685) approach.
#### Training Hyperparameters
**Training setting:**
- train epochs=3,
- learning_rate=2e-4,
- mixed precision training: float16
**LoRA configuration:**
- r= 8
- lora_alpha=16
- target_modules=["q_proj","v_proj"]
- lora_dropout=0.05
- bias="none"
- task_type=TaskType.CAUSAL_LM
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** 1 NVIDIA A100/40Gb
- **Hours used:** 78
- **Cloud Provider:** Private Infrastructure
- **Carbon Emitted:** 8.42 kg eq. CO2
## Model Card Authors
Stefano Scotta ([email protected])
## Model Card Contact
[email protected] |
s3nh/Noromaid-Aeryth-7B | s3nh | "2024-03-04T12:39:27Z" | 989 | 3 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:NeverSleep/Noromaid-7b-v0.2",
"base_model:NeuralNovel/Aeryth-7B-v0.1",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-08T08:00:22Z" | ---
license: apache-2.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- NeverSleep/Noromaid-7b-v0.2
- NeuralNovel/Aeryth-7B-v0.1
pipeline_tag: text-generation
model-index:
- name: Noromaid-Aeryth-7B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 56.74
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 78.62
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 57.29
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 65.66
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 71.82
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 16.76
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Noromaid-Aeryth-7B
name: Open LLM Leaderboard
---
# Noromaid-Aeryth-7B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [NeverSleep/Noromaid-7b-v0.2](https://huggingface.co/NeverSleep/Noromaid-7b-v0.2)
* [NeuralNovel/Aeryth-7B-v0.1](https://huggingface.co/NeuralNovel/Aeryth-7B-v0.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: NeverSleep/Noromaid-7b-v0.2
dtype: float16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.22, 0.61, 0.46, 0.77, 1.0]
- filter: mlp
value: [0.78, 0.39, 0.54, 0.23, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 32]
model: NeuralNovel/Aeryth-7B-v0.1
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_s3nh__Noromaid-Aeryth-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |57.82|
|AI2 Reasoning Challenge (25-Shot)|56.74|
|HellaSwag (10-Shot) |78.62|
|MMLU (5-Shot) |57.29|
|TruthfulQA (0-shot) |65.66|
|Winogrande (5-shot) |71.82|
|GSM8k (5-shot) |16.76|
|
Chrisisis/5DtHymom4Md2EiPwwN8GJ7ztRHfNQutrHkeyw9WfftgpFnLR_vgg | Chrisisis | "2024-02-24T08:29:46Z" | 989 | 0 | keras | [
"keras",
"region:us"
] | null | "2024-02-11T17:22:16Z" | Entry not found |
InnerI/A-I-0xtom-7B-slerp | InnerI | "2024-03-04T23:15:05Z" | 989 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"0x0dad0/nous_nous_v2_0",
"tomaszki/nous-thirty",
"conversational",
"base_model:0x0dad0/nous_nous_v2_0",
"base_model:tomaszki/nous-thirty",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-16T01:09:57Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- 0x0dad0/nous_nous_v2_0
- tomaszki/nous-thirty
base_model:
- 0x0dad0/nous_nous_v2_0
- tomaszki/nous-thirty
model-index:
- name: A-I-0xtom-7B-slerp
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 58.19
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/A-I-0xtom-7B-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 77.64
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/A-I-0xtom-7B-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 58.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/A-I-0xtom-7B-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 54.78
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/A-I-0xtom-7B-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 73.24
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/A-I-0xtom-7B-slerp
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 40.18
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InnerI/A-I-0xtom-7B-slerp
name: Open LLM Leaderboard
---
# A-I-0xtom-7B-slerp
A-I-0xtom-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [0x0dad0/nous_nous_v2_0](https://huggingface.co/0x0dad0/nous_nous_v2_0)
* [tomaszki/nous-thirty](https://huggingface.co/tomaszki/nous-thirty)
# Avg model loss 0.3912096044793725
I used this testing script that loads your local model, pulls the latest data from cortex and calculates the loss:
[avg loss script](https://gist.github.com/romanorac/59ccde7cbf07d8950ef9fb5b5db6a24e)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: 0x0dad0/nous_nous_v2_0
layer_range: [0, 32]
- model: tomaszki/nous-thirty
layer_range: [0, 32]
merge_method: slerp
base_model: 0x0dad0/nous_nous_v2_0
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "InnerI/A-I-0xtom-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_InnerI__A-I-0xtom-7B-slerp)
| Metric |Value|
|---------------------------------|----:|
|Avg. |60.46|
|AI2 Reasoning Challenge (25-Shot)|58.19|
|HellaSwag (10-Shot) |77.64|
|MMLU (5-Shot) |58.74|
|TruthfulQA (0-shot) |54.78|
|Winogrande (5-shot) |73.24|
|GSM8k (5-shot) |40.18|
|
EbanLee/kobart-summary-v3 | EbanLee | "2024-03-22T06:07:59Z" | 989 | 5 | transformers | [
"transformers",
"safetensors",
"bart",
"text2text-generation",
"summarization",
"ko",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | "2024-03-21T01:39:02Z" | ---
language:
- ko
metrics:
- rouge
library_name: transformers
pipeline_tag: summarization
tags:
- bart
---
# kobart-summary
- 이 모델은 [kobart모델](https://huggingface.co/hyunwoongko/kobart)을 [문서요약](https://aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=realm&dataSetSn=97), [도서자료요약](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=93), [요약문 및 레포트 생성](https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&dataSetSn=582) 데이터로 fine-tuning한 모델입니다.
- v2와 비슷지만 데이터를 조금 더 추가했고 길게 연결된 문장이 많이 나왔었는데 조금 더 끊어져서 생성됩니다.
## How to use
```python
from transformers import PreTrainedTokenizerFast, BartForConditionalGeneration
# Load Model and Tokenizer
tokenizer = PreTrainedTokenizerFast.from_pretrained("EbanLee/kobart-summary-v3")
model = BartForConditionalGeneration.from_pretrained("EbanLee/kobart-summary-v3")
# Encoding
input_text = "10년 논란 끝에 밑글씨까지 새기고 제작 완료를 눈앞에 둔 ‘광화문 현판’을 원점에서 재검토해 한글 현판으로 교체하자는 주장이 문화계 명사들이 포함된 자칭 ‘시민모임’에서 나왔다.\n 이들은 문화재청이 지난해 8월 최종 확정한 복원안이 시민 의견과 시대정신을 반영한 것이 아니라면서 오는 한글날까지 대대적인 현판 교체 시민운동을 벌이겠다고 예고했다.\n ‘광화문 현판 훈민정음체로 시민모임’(공동대표 강병인‧한재준, 이하 ‘시민모임’)에 이름을 올린 문화예술인은 현재까지 총 24명.\n 이 중엔 2014~2016년 서울시 총괄건축가를 지낸 승효상 이로재 대표와 ‘안상수체’로 유명한 안상수 파주타이포그라피학교 교장, 유영숙 전 환경부장관(세종사랑방 회장), 임옥상 미술가 등이 있다.\n 공동대표인 강병인 작가는 ‘참이슬’ ‘화요’ 등의 상표 글씨로 유명한 캘리그라피(서체) 작가다.\n ‘시민모임’은 14일 오후 서울 종로구의 한 서점에서 기자간담회를 열고 이 같은 입장과 함께 훈민정음 해례 글자꼴로 시범 제작한 모형 현판(1/2 크기 축소판)도 공개할 예정이다.\n 강 공동대표는 13일 기자와 통화에서 “새 현판 제작 과정에서 한글로 만들자는 의견은 묵살됐다”면서 “지난해 8월 이후 문화재청에 거듭 입장을 전했지만 반영되지 않아 시민운동에 나서기로 했다”고 말했다.\n 일단 문화예술인 주축으로 꾸렸지만 조만간 한글협회 등 한글 관련단체들과 연대한다는 방침이다.\n 이들이 배포한 사전자료엔 ^한자현판 설치는 중국의 속국임을 표시하는 것으로 대한민국 정체성에 도움이 되지 않고 ^광화문은 21세기의 중건이지 복원이 아니므로 당대의 시대정신인 한글로 현판을 써야하며 ^한글현판은 미래에 남겨줄 우리 유산을 재창조한다는 의미라는 주장이 담겼다.\n 현재 광화문 현판에 대해선 “고종이 경복궁을 중건할 때 당시 훈련대장이던 임태영이 쓴 광화문 현판의 글씨를 조그만 사진에서 스캐닝하고 이를 다듬어 이명박정부 때 설치된 것”이라면서 복원 기준으로서의 정당성을 깎아내렸다.\n ‘시민모임’에 참여한 승효상 대표도 개인의견을 전제로 “현판을 꼭 한가지만 고집할 필요도 없다.\n 매년 교체할 수도 있고, 광장에서 보이는 정면엔 한글현판, 반대편엔 한자현판을 다는 아이디어도 가능한 것 아니냐”고 말했다.\n 그러면서 “문화재 전문가들은 보수적일 수밖에 없지만 현판이란 게 요즘 말로는 ‘간판’인데 새 시대에 맞게 바꿔 다는 게 바람직하다”고 주장했다.\n"
inputs = tokenizer(input_text, return_tensors="pt", padding="max_length", truncation=True, max_length=1026)
# Generate Summary Text Ids
summary_text_ids = model.generate(
input_ids=inputs['input_ids'],
attention_mask=inputs['attention_mask'],
bos_token_id=model.config.bos_token_id,
eos_token_id=model.config.eos_token_id,
length_penalty=1.0,
max_length=300,
min_length=12,
num_beams=6,
repetition_penalty=1.5,
no_repeat_ngram_size=15,
)
# Decoding Text Ids
print(tokenizer.decode(summary_text_ids[0], skip_special_tokens=True))
``` |
backyardai/aya-23-35B-GGUF | backyardai | "2024-06-04T20:56:18Z" | 989 | 0 | transformers | [
"transformers",
"gguf",
"en",
"fr",
"de",
"es",
"it",
"pt",
"ja",
"ko",
"zh",
"ar",
"el",
"fa",
"pl",
"id",
"cs",
"he",
"hi",
"nl",
"ro",
"ru",
"tr",
"uk",
"vi",
"base_model:CohereForAI/aya-23-35B",
"license:cc-by-nc-4.0",
"region:us"
] | null | "2024-06-04T19:30:56Z" | ---
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
library_name: transformers
base_model: CohereForAI/aya-23-35B
model_name: aya-23-35B-GGUF
inference: false
quantized_by: brooketh
parameter_count: 34980831232
---
<img src="BackyardAI_Banner.png" alt="Backyard.ai" style="height: 90px; min-width: 32px; display: block; margin: auto;">
**<p style="text-align: center;">The official library of GGUF format models for use in the local AI chat app, Backyard AI.</p>**
<p style="text-align: center;"><a href="https://backyard.ai/">Download Backyard AI here to get started.</a></p>
<p style="text-align: center;"><a href="https://www.reddit.com/r/LLM_Quants/">Request Additional models at r/LLM_Quants.</a></p>
***
# Aya 23 35B
- **Creator:** [CohereForAI](https://huggingface.co/CohereForAI/)
- **Original:** [Aya 23 35B](https://huggingface.co/CohereForAI/aya-23-35B)
- **Date Created:** 2024-05-19
- **Trained Context:** 8192 tokens
- **Description:** Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities, serving 23 languages. It is available with 8 billion and 35 billion parameters; this is the 35 billion parameter version.
***
## What is a GGUF?
GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Backyard AI. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware.
GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.
***
<img src="BackyardAI_Logo.png" alt="Backyard.ai" style="height: 75px; min-width: 32px; display: block; horizontal align: left;">
## Backyard AI
- Free, local AI chat application.
- One-click installation on Mac and PC.
- Automatically use GPU for maximum speed.
- Built-in model manager.
- High-quality character hub.
- Zero-config desktop-to-mobile tethering.
Backyard AI makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models without worrying about whether it's the correct format. Backyard AI supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable.
**Join us on [Discord](https://discord.gg/SyNN2vC9tQ)**
*** |
SavirD/distilbert-base-uncased-lora-text-classification | SavirD | "2024-06-27T01:46:55Z" | 989 | 1 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"text-classification",
"en",
"base_model:distilbert-base-uncased",
"doi:10.57967/hf/2601",
"license:apache-2.0",
"region:us"
] | text-classification | "2024-06-20T16:28:33Z" | ---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: distilbert-base-uncased
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-lora-text-classification
results: []
language:
- en
pipeline_tag: text-classification
---
<!-- 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. -->
# distilbert-base-uncased-lora-text-classification
# This model is used for Sentimental Analysis and given an input will return Positive or Negative
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1550
- Accuracy: {'accuracy': 0.883}
## 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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
| No log | 1.0 | 250 | 0.6110 | {'accuracy': 0.832} |
| 0.4023 | 2.0 | 500 | 0.5590 | {'accuracy': 0.871} |
| 0.4023 | 3.0 | 750 | 0.5852 | {'accuracy': 0.876} |
| 0.1908 | 4.0 | 1000 | 0.8232 | {'accuracy': 0.891} |
| 0.1908 | 5.0 | 1250 | 0.9061 | {'accuracy': 0.885} |
| 0.067 | 6.0 | 1500 | 1.0293 | {'accuracy': 0.886} |
| 0.067 | 7.0 | 1750 | 1.1672 | {'accuracy': 0.879} |
| 0.0251 | 8.0 | 2000 | 1.1400 | {'accuracy': 0.881} |
| 0.0251 | 9.0 | 2250 | 1.1411 | {'accuracy': 0.882} |
| 0.0217 | 10.0 | 2500 | 1.1550 | {'accuracy': 0.883} |
### Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.41.2
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1 |
akahana/vit-base-cats-vs-dogs | akahana | "2023-09-19T01:23:03Z" | 988 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:cats_vs_dogs",
"base_model:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2022-03-02T23:29:05Z" | ---
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
datasets:
- cats_vs_dogs
metrics:
- accuracy
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: vit-base-cats-vs-dogs
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: cats_vs_dogs
type: cats_vs_dogs
args: default
metrics:
- type: accuracy
value: 0.9883257403189066
name: Accuracy
---
<!-- 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. -->
# vit-base-cats-vs-dogs
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the cats_vs_dogs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0369
- Accuracy: 0.9883
## how to use
```python
from transformers import ViTFeatureExtractor, ViTModel
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
model = ViTModel.from_pretrained('akahana/vit-base-cats-vs-dogs')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state
```
## 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0949 | 1.0 | 2488 | 0.0369 | 0.9883 |
### Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3
|
ehdwns1516/bert-base-uncased_SWAG | ehdwns1516 | "2021-08-05T09:49:18Z" | 988 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"multiple-choice",
"endpoints_compatible",
"region:us"
] | multiple-choice | "2022-03-02T23:29:05Z" | # ehdwns1516/bert-base-uncased_SWAG
* This model has been trained as a [SWAG dataset](https://huggingface.co/ehdwns1516/bert-base-uncased_SWAG).
* Sentence Inference Multiple Choice DEMO: [Ainize DEMO](https://main-sentence-inference-multiple-choice-ehdwns1516.endpoint.ainize.ai/)
* Sentence Inference Multiple Choice API: [Ainize API](https://ainize.web.app/redirect?git_repo=https://github.com/ehdwns1516/sentence_inference_multiple_choice)
## Overview
Language model: [bert-base-uncased](https://huggingface.co/bert-base-uncased)
Language: English
Training data: [SWAG dataset](https://huggingface.co/datasets/swag)
Code: See [Ainize Workspace](https://ainize.ai/workspace/create?imageId=hnj95592adzr02xPTqss&git=https://github.com/ehdwns1516/Multiple_choice_SWAG_finetunning)
## Usage
## In Transformers
```
from transformers import AutoTokenizer, AutoModelForMultipleChoice
tokenizer = AutoTokenizer.from_pretrained("ehdwns1516/bert-base-uncased_SWAG")
model = AutoModelForMultipleChoice.from_pretrained("ehdwns1516/bert-base-uncased_SWAG")
def run_model(candicates_count, context: str, candicates: list[str]):
assert len(candicates) == candicates_count, "you need " + candicates_count + " candidates"
choices_inputs = []
for c in candicates:
text_a = "" # empty context
text_b = context + " " + c
inputs = tokenizer(
text_a,
text_b,
add_special_tokens=True,
max_length=128,
padding="max_length",
truncation=True,
return_overflowing_tokens=True,
)
choices_inputs.append(inputs)
input_ids = torch.LongTensor([x["input_ids"] for x in choices_inputs])
output = model(input_ids=input_ids)
return {"result": candicates[torch.argmax(output.logits).item()]}
items = list()
count = 4 # candicates count
context = "your context"
for i in range(int(count)):
items.append("sentence")
result = run_model(count, context, items)
```
|
MaziyarPanahi/Calme-7B-Instruct-v0.9 | MaziyarPanahi | "2024-04-02T14:42:07Z" | 988 | 9 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"generated_from_trainer",
"7b",
"calme",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-02T14:34:08Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
- mistral
- 7b
- calme
model-index:
- name: Calme-7B-Instruct-v0.9
results: []
model_name: Calme-7B-Instruct-v0.9
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
<img src="https://cdn-uploads.huggingface.co/production/uploads/5fd5e18a90b6dc4633f6d292/LzEf6vvq2qIiys-q7l9Hq.webp" width="550" />
# MaziyarPanahi/Calme-7B-Instruct-v0.9
## Model Description
Calme-7B is a state-of-the-art language model with 7 billion parameters, fine-tuned over high-quality datasets on top of Mistral-7B. The Calme-7B models excel in generating text that resonates with clarity, calmness, and coherence.
### How to Use
```python
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="MaziyarPanahi/Calme-7B-Instruct-v0.9")
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.9")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Calme-7B-Instruct-v0.9")
```
### Quantized Models
> I love how GGUF democratizes the use of Large Language Models (LLMs) on commodity hardware, more specifically, personal computers without any accelerated hardware. Because of this, I am committed to converting and quantizing any models I fine-tune to make them accessible to everyone!
- GGUF (2/3/4/5/6/8 bits): [MaziyarPanahi/Calme-7B-Instruct-v0.9-GGUF](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.9-GGUF)
## Examples
```
<s>[INST] You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
describe about pros and cons of docker system. [/INST]
```
<details>
<summary>Show me the response</summary>
```
```
</details>
```
```
<details>
<summary>Show me the response</summary>
```
```
</details>
```
<s> [INST] Mark is faster than Mary, Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step [/INST]
```
<details>
<summary>Show me the response</summary>
```
```
</details>
```
```
<details>
<summary>Show me the response</summary>
```
```
</details>
```
<s> [INST] explain step by step 25-4*2+3=? [/INST]
```
<details>
<summary>Show me the response</summary>
```
```
</details>
**Multilingual:**
```
<s> [INST] Vous êtes un assistant utile, respectueux et honnête. Répondez toujours de la manière la plus utile possible, tout en étant sûr. Vos réponses ne doivent inclure aucun contenu nuisible, contraire à l'éthique, raciste, sexiste, toxique, dangereux ou illégal. Assurez-vous que vos réponses sont socialement impartiales et de nature positive.
Si une question n'a pas de sens ou n'est pas cohérente d'un point de vue factuel, expliquez pourquoi au lieu de répondre quelque chose d'incorrect. Si vous ne connaissez pas la réponse à une question, veuillez ne pas partager de fausses informations.
Décrivez les avantages et les inconvénients du système Docker.[/INST]
```
<details>
<summary>Show me the response</summary>
```
```
<details>
<summary>Show me the response</summary>
```
```
</details>
```
<s>[INST] Ви - корисний, поважний та чесний помічник. Завжди відповідайте максимально корисно, будучи безпечним. Ваші відповіді не повинні містити шкідливого, неетичного, расистського, сексистського, токсичного, небезпечного або нелегального контенту. Будь ласка, переконайтеся, що ваші відповіді соціально неупереджені та мають позитивний характер.
Якщо питання не має сенсу або не є фактично послідовним, поясніть чому, замість того, щоб відповідати щось некоректне. Якщо ви не знаєте відповіді на питання, будь ласка, не діліться неправдивою інформацією.
Опис про переваги та недоліки системи Docker.[/INST]
```
<details>
<summary>Show me the response</summary>
```
```
</details>
|
sayakpaul/sdxl-unet-sharded | sayakpaul | "2024-06-07T09:33:14Z" | 988 | 0 | diffusers | [
"diffusers",
"safetensors",
"region:us"
] | null | "2024-06-07T09:31:31Z" | Entry not found |
timm/regnety_008_tv.tv2_in1k | timm | "2024-02-10T23:33:15Z" | 987 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2003.13678",
"license:bsd-3-clause",
"region:us"
] | image-classification | "2023-03-21T06:37:24Z" | ---
license: bsd-3-clause
library_name: timm
tags:
- image-classification
- timm
---
# Model card for regnety_008_tv.tv2_in1k
A RegNetY-800MF image classification model. Pretrained on ImageNet-1k by torchvision contributors (see ImageNet1K-V2 weight details https://github.com/pytorch/vision/issues/3995#new-recipe).
The `timm` RegNet implementation includes a number of enhancements not present in other implementations, including:
* stochastic depth
* gradient checkpointing
* layer-wise LR decay
* configurable output stride (dilation)
* configurable activation and norm layers
* option for a pre-activation bottleneck block used in RegNetV variant
* only known RegNetZ model definitions with pretrained weights
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 6.4
- GMACs: 0.8
- Activations (M): 5.4
- Image size: 224 x 224
- **Papers:**
- Designing Network Design Spaces: https://arxiv.org/abs/2003.13678
- **Original:** https://github.com/pytorch/vision
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('regnety_008_tv.tv2_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'regnety_008_tv.tv2_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 32, 112, 112])
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 144, 28, 28])
# torch.Size([1, 320, 14, 14])
# torch.Size([1, 784, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'regnety_008_tv.tv2_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 784, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in `timm`.
|model |img_size|top1 |top5 |param_count|gmacs|macts |
|-------------------------|--------|------|------|-----------|-----|------|
|[regnety_1280.swag_ft_in1k](https://huggingface.co/timm/regnety_1280.swag_ft_in1k)|384 |88.228|98.684|644.81 |374.99|210.2 |
|[regnety_320.swag_ft_in1k](https://huggingface.co/timm/regnety_320.swag_ft_in1k)|384 |86.84 |98.364|145.05 |95.0 |88.87 |
|[regnety_160.swag_ft_in1k](https://huggingface.co/timm/regnety_160.swag_ft_in1k)|384 |86.024|98.05 |83.59 |46.87|67.67 |
|[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|288 |86.004|97.83 |83.59 |26.37|38.07 |
|[regnety_1280.swag_lc_in1k](https://huggingface.co/timm/regnety_1280.swag_lc_in1k)|224 |85.996|97.848|644.81 |127.66|71.58 |
|[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|288 |85.982|97.844|83.59 |26.37|38.07 |
|[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|224 |85.574|97.666|83.59 |15.96|23.04 |
|[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|224 |85.564|97.674|83.59 |15.96|23.04 |
|[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|288 |85.398|97.584|51.82 |20.06|35.34 |
|[regnety_2560.seer_ft_in1k](https://huggingface.co/timm/regnety_2560.seer_ft_in1k)|384 |85.15 |97.436|1282.6 |747.83|296.49|
|[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|320 |85.036|97.268|57.7 |15.46|63.94 |
|[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|224 |84.976|97.416|51.82 |12.14|21.38 |
|[regnety_320.swag_lc_in1k](https://huggingface.co/timm/regnety_320.swag_lc_in1k)|224 |84.56 |97.446|145.05 |32.34|30.26 |
|[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|320 |84.496|97.004|28.94 |6.43 |37.94 |
|[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|256 |84.436|97.02 |57.7 |9.91 |40.94 |
|[regnety_1280.seer_ft_in1k](https://huggingface.co/timm/regnety_1280.seer_ft_in1k)|384 |84.432|97.092|644.81 |374.99|210.2 |
|[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|320 |84.246|96.93 |27.12 |6.35 |37.78 |
|[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|320 |84.054|96.992|23.37 |6.19 |37.08 |
|[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|320 |84.038|96.992|23.46 |7.03 |38.92 |
|[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|320 |84.022|96.866|27.58 |9.33 |37.08 |
|[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|288 |83.932|96.888|39.18 |13.22|29.69 |
|[regnety_640.seer_ft_in1k](https://huggingface.co/timm/regnety_640.seer_ft_in1k)|384 |83.912|96.924|281.38 |188.47|124.83|
|[regnety_160.swag_lc_in1k](https://huggingface.co/timm/regnety_160.swag_lc_in1k)|224 |83.778|97.286|83.59 |15.96|23.04 |
|[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|256 |83.776|96.704|28.94 |4.12 |24.29 |
|[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|288 |83.72 |96.75 |30.58 |10.55|27.11 |
|[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|288 |83.718|96.724|30.58 |10.56|27.11 |
|[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|288 |83.69 |96.778|83.59 |26.37|38.07 |
|[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|256 |83.62 |96.704|27.12 |4.06 |24.19 |
|[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|256 |83.438|96.776|23.37 |3.97 |23.74 |
|[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|256 |83.424|96.632|27.58 |5.98 |23.74 |
|[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|256 |83.36 |96.636|23.46 |4.5 |24.92 |
|[regnety_320.seer_ft_in1k](https://huggingface.co/timm/regnety_320.seer_ft_in1k)|384 |83.35 |96.71 |145.05 |95.0 |88.87 |
|[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|288 |83.204|96.66 |20.64 |6.6 |20.3 |
|[regnety_320.tv2_in1k](https://huggingface.co/timm/regnety_320.tv2_in1k)|224 |83.162|96.42 |145.05 |32.34|30.26 |
|[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|224 |83.16 |96.486|39.18 |8.0 |17.97 |
|[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|224 |83.108|96.458|30.58 |6.39 |16.41 |
|[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|288 |83.044|96.5 |20.65 |6.61 |20.3 |
|[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|224 |83.02 |96.292|30.58 |6.39 |16.41 |
|[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|224 |82.974|96.502|83.59 |15.96|23.04 |
|[regnetx_320.tv2_in1k](https://huggingface.co/timm/regnetx_320.tv2_in1k)|224 |82.816|96.208|107.81 |31.81|36.3 |
|[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|288 |82.742|96.418|19.44 |5.29 |18.61 |
|[regnety_160.tv2_in1k](https://huggingface.co/timm/regnety_160.tv2_in1k)|224 |82.634|96.22 |83.59 |15.96|23.04 |
|[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|320 |82.634|96.472|13.49 |3.86 |25.88 |
|[regnety_080_tv.tv2_in1k](https://huggingface.co/timm/regnety_080_tv.tv2_in1k)|224 |82.592|96.246|39.38 |8.51 |19.73 |
|[regnetx_160.tv2_in1k](https://huggingface.co/timm/regnetx_160.tv2_in1k)|224 |82.564|96.052|54.28 |15.99|25.52 |
|[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|320 |82.51 |96.358|13.46 |3.92 |25.88 |
|[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|224 |82.44 |96.198|20.64 |4.0 |12.29 |
|[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|224 |82.304|96.078|20.65 |4.0 |12.29 |
|[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|256 |82.16 |96.048|13.46 |2.51 |16.57 |
|[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|256 |81.936|96.15 |13.49 |2.48 |16.57 |
|[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|224 |81.924|95.988|19.44 |3.2 |11.26 |
|[regnety_032.tv2_in1k](https://huggingface.co/timm/regnety_032.tv2_in1k)|224 |81.77 |95.842|19.44 |3.2 |11.26 |
|[regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k)|224 |81.552|95.544|39.57 |8.02 |14.06 |
|[regnetx_032.tv2_in1k](https://huggingface.co/timm/regnetx_032.tv2_in1k)|224 |80.924|95.27 |15.3 |3.2 |11.37 |
|[regnety_320.pycls_in1k](https://huggingface.co/timm/regnety_320.pycls_in1k)|224 |80.804|95.246|145.05 |32.34|30.26 |
|[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|288 |80.712|95.47 |9.72 |2.39 |16.43 |
|[regnety_016.tv2_in1k](https://huggingface.co/timm/regnety_016.tv2_in1k)|224 |80.66 |95.334|11.2 |1.63 |8.04 |
|[regnety_120.pycls_in1k](https://huggingface.co/timm/regnety_120.pycls_in1k)|224 |80.37 |95.12 |51.82 |12.14|21.38 |
|[regnety_160.pycls_in1k](https://huggingface.co/timm/regnety_160.pycls_in1k)|224 |80.288|94.964|83.59 |15.96|23.04 |
|[regnetx_320.pycls_in1k](https://huggingface.co/timm/regnetx_320.pycls_in1k)|224 |80.246|95.01 |107.81 |31.81|36.3 |
|[regnety_080.pycls_in1k](https://huggingface.co/timm/regnety_080.pycls_in1k)|224 |79.882|94.834|39.18 |8.0 |17.97 |
|[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|224 |79.872|94.974|9.72 |1.45 |9.95 |
|[regnetx_160.pycls_in1k](https://huggingface.co/timm/regnetx_160.pycls_in1k)|224 |79.862|94.828|54.28 |15.99|25.52 |
|[regnety_064.pycls_in1k](https://huggingface.co/timm/regnety_064.pycls_in1k)|224 |79.716|94.772|30.58 |6.39 |16.41 |
|[regnetx_120.pycls_in1k](https://huggingface.co/timm/regnetx_120.pycls_in1k)|224 |79.592|94.738|46.11 |12.13|21.37 |
|[regnetx_016.tv2_in1k](https://huggingface.co/timm/regnetx_016.tv2_in1k)|224 |79.44 |94.772|9.19 |1.62 |7.93 |
|[regnety_040.pycls_in1k](https://huggingface.co/timm/regnety_040.pycls_in1k)|224 |79.23 |94.654|20.65 |4.0 |12.29 |
|[regnetx_080.pycls_in1k](https://huggingface.co/timm/regnetx_080.pycls_in1k)|224 |79.198|94.55 |39.57 |8.02 |14.06 |
|[regnetx_064.pycls_in1k](https://huggingface.co/timm/regnetx_064.pycls_in1k)|224 |79.064|94.454|26.21 |6.49 |16.37 |
|[regnety_032.pycls_in1k](https://huggingface.co/timm/regnety_032.pycls_in1k)|224 |78.884|94.412|19.44 |3.2 |11.26 |
|[regnety_008_tv.tv2_in1k](https://huggingface.co/timm/regnety_008_tv.tv2_in1k)|224 |78.654|94.388|6.43 |0.84 |5.42 |
|[regnetx_040.pycls_in1k](https://huggingface.co/timm/regnetx_040.pycls_in1k)|224 |78.482|94.24 |22.12 |3.99 |12.2 |
|[regnetx_032.pycls_in1k](https://huggingface.co/timm/regnetx_032.pycls_in1k)|224 |78.178|94.08 |15.3 |3.2 |11.37 |
|[regnety_016.pycls_in1k](https://huggingface.co/timm/regnety_016.pycls_in1k)|224 |77.862|93.73 |11.2 |1.63 |8.04 |
|[regnetx_008.tv2_in1k](https://huggingface.co/timm/regnetx_008.tv2_in1k)|224 |77.302|93.672|7.26 |0.81 |5.15 |
|[regnetx_016.pycls_in1k](https://huggingface.co/timm/regnetx_016.pycls_in1k)|224 |76.908|93.418|9.19 |1.62 |7.93 |
|[regnety_008.pycls_in1k](https://huggingface.co/timm/regnety_008.pycls_in1k)|224 |76.296|93.05 |6.26 |0.81 |5.25 |
|[regnety_004.tv2_in1k](https://huggingface.co/timm/regnety_004.tv2_in1k)|224 |75.592|92.712|4.34 |0.41 |3.89 |
|[regnety_006.pycls_in1k](https://huggingface.co/timm/regnety_006.pycls_in1k)|224 |75.244|92.518|6.06 |0.61 |4.33 |
|[regnetx_008.pycls_in1k](https://huggingface.co/timm/regnetx_008.pycls_in1k)|224 |75.042|92.342|7.26 |0.81 |5.15 |
|[regnetx_004_tv.tv2_in1k](https://huggingface.co/timm/regnetx_004_tv.tv2_in1k)|224 |74.57 |92.184|5.5 |0.42 |3.17 |
|[regnety_004.pycls_in1k](https://huggingface.co/timm/regnety_004.pycls_in1k)|224 |74.018|91.764|4.34 |0.41 |3.89 |
|[regnetx_006.pycls_in1k](https://huggingface.co/timm/regnetx_006.pycls_in1k)|224 |73.862|91.67 |6.2 |0.61 |3.98 |
|[regnetx_004.pycls_in1k](https://huggingface.co/timm/regnetx_004.pycls_in1k)|224 |72.38 |90.832|5.16 |0.4 |3.14 |
|[regnety_002.pycls_in1k](https://huggingface.co/timm/regnety_002.pycls_in1k)|224 |70.282|89.534|3.16 |0.2 |2.17 |
|[regnetx_002.pycls_in1k](https://huggingface.co/timm/regnetx_002.pycls_in1k)|224 |68.752|88.556|2.68 |0.2 |2.16 |
## Citation
```bibtex
@InProceedings{Radosavovic2020,
title = {Designing Network Design Spaces},
author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{'a}r},
booktitle = {CVPR},
year = {2020}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
922-CA/l2-7b-natsuki-ddlc-v0.1-gguf | 922-CA | "2023-09-09T06:21:51Z" | 987 | 0 | null | [
"gguf",
"license:llama2",
"region:us"
] | null | "2023-09-08T09:05:36Z" | ---
license: llama2
---
GGUFs of [l2-7b-natsuki-ddlc-v0.1](https://huggingface.co/922-CA/l2-7b-natsuki-ddlc-v0.1). (Primarily tested and run with Koboldcpp v1.41+).
QLora (hf and GGML) [here](https://huggingface.co/922-CA/natsuki-lm-lora-tests/tree/main/l2-7b-natsuki-v0.1). |
NeuralNovel/Tiger-7B-v0.1 | NeuralNovel | "2024-03-05T15:57:24Z" | 987 | 7 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"dataset:Intel/orca_dpo_pairs",
"dataset:NeuralNovel/Neural-Story-v1",
"base_model:NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story",
"base_model:NeuralNovel/Gecko-7B-v0.1-DPO",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-18T18:38:51Z" | ---
license: apache-2.0
tags:
- mergekit
- merge
datasets:
- Intel/orca_dpo_pairs
- NeuralNovel/Neural-Story-v1
base_model:
- NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
- NeuralNovel/Gecko-7B-v0.1-DPO
model-index:
- name: Tiger-7b-v0.1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 59.98
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 83.21
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 61.42
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 61.03
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 77.66
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 46.78
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
name: Open LLM Leaderboard
---
# Tiger-7b-v0.1
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
[Join our Discord!](https://discord.gg/rJXGjmxqzS)
<a href='https://ko-fi.com/S6S2UH2TC' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
## Metrics
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story](https://huggingface.co/NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story)
* [NeuralNovel/Gecko-7B-v0.1-DPO](https://huggingface.co/NeuralNovel/Gecko-7B-v0.1-DPO)
# merge
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
layer_range: [0, 32]
- model: NeuralNovel/Gecko-7B-v0.1-DPO
layer_range: [0, 32]
merge_method: slerp
base_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NeuralNovel__Tiger-7b-v0.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |65.02|
|AI2 Reasoning Challenge (25-Shot)|59.98|
|HellaSwag (10-Shot) |83.21|
|MMLU (5-Shot) |61.42|
|TruthfulQA (0-shot) |61.03|
|Winogrande (5-shot) |77.66|
|GSM8k (5-shot) |46.78|
|
cognitivecomputations/dolphincoder-starcoder2-7b | cognitivecomputations | "2024-05-20T14:51:58Z" | 987 | 11 | transformers | [
"transformers",
"pytorch",
"starcoder2",
"text-generation",
"conversational",
"en",
"dataset:cognitivecomputations/dolphin",
"dataset:jondurbin/airoboros-2.2.1",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:teknium/openhermes",
"dataset:ise-uiuc/Magicoder-OSS-Instruct-75K",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"dataset:m-a-p/Code-Feedback",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:microsoft/orca-math-word-problems-200k",
"license:bigcode-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-08T01:51:26Z" | ---
datasets:
- cognitivecomputations/dolphin
- jondurbin/airoboros-2.2.1
- cognitivecomputations/dolphin-coder
- teknium/openhermes
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
- m-a-p/Code-Feedback
- m-a-p/CodeFeedback-Filtered-Instruction
- microsoft/orca-math-word-problems-200k
language:
- en
license: bigcode-openrail-m
---
DolphinCoder StarCoder2 7b 🐬
sponsored by [latitude.sh](https://www.latitude.sh/).
[](https://discord.gg/cognitivecomputations)
Discord: https://discord.gg/cognitivecomputations
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
This model is based on StarCoder2-7b and is subject to bigcode-openrail-m license.
This Dolphin is *really good* at coding, I trained with a lot of coding data.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
You are responsible for any content you create using this model. Enjoy responsibly.
## Training
It took 2 days to train 3 epochs on 8x L40S's using qLoRA and Axolotl
Prompt format:
This model uses ChatML prompt format.
```
<|im_start|>system
You are DolphinCoder, a helpful AI programming assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Example:
```
<|im_start|>system
You are DolphinCoder, a master at software engineering and coding in any programming language.
<|im_start|>user
Please write me a program in golang that parses all the lines in a file, and reverses them character-wise, and saves it to a new file.
<|im_start|>assistant
```
## Quantized models
- [dagbs/-GGUF](https://huggingface.co/dagbs/dolphincoder-starcoder2-7b-GGUF)
## Gratitude
- This model was made possible by the generous sponsorship of [latitude.sh](https://www.latitude.sh/).
- Welcome Microsoft to Open Source AI! Thank you for the Orca-Math Dataset!
- Huge thank you to [BigCode](https://www.bigcode-project.org/) for training and publishing the weights of StarCoder2
- HUGE Thank you to the dataset authors: @ise-uiuc, @teknium, @m-a-p
- And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
## Example Output
[If you would like to financially support my efforts](https://ko-fi.com/erichartford)
[swag](https://fa7113.myshopify.com/) |
alvdansen/popartanime | alvdansen | "2024-06-16T16:30:05Z" | 987 | 10 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | "2024-06-07T16:45:47Z" | ---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: a mouse knight, daiton style
output:
url: images/ComfyUI_00235_.png
- text: a princess with a dress mad of flowers, daiton style
output:
url: images/ComfyUI_00227_.png
- text: a boy with a cool hat, daiton style
output:
url: images/ComfyUI_00211_.png
- text: a happy girl, daiton style
output:
url: images/ComfyUI_00200_.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: daiton style
license: creativeml-openrail-m
---
# Pop Art Anime
<Gallery />
## Model description
A very blocky and bold cartoon style with some anime elements.
## Trigger words
You should use `daiton style` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Model release is for research purposes only. For commercial use, please contact me directly.
[Download](/alvdansen/popartanime/tree/main) them in the Files & versions tab.
|
timm/mvitv2_base.fb_in1k | timm | "2024-02-10T23:42:48Z" | 986 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2112.01526",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-13T00:22:34Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for mvitv2_base.fb_in1k
A MViT-v2 (multi-scale ViT) image classification model. Pretrained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 51.5
- GMACs: 10.2
- Activations (M): 40.5
- Image size: 224 x 224
- **Papers:**
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection: https://arxiv.org/abs/2112.01526
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/facebookresearch/mvit
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('mvitv2_base.fb_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'mvitv2_base.fb_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 49, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
|
Locutusque/Hyperion-2.0-Mistral-7B | Locutusque | "2024-03-12T16:55:05Z" | 986 | 5 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"code",
"chemistry",
"medical",
"en",
"dataset:Locutusque/hyperion-v2.0",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-10T02:34:48Z" | ---
library_name: transformers
tags:
- code
- chemistry
- medical
license: apache-2.0
datasets:
- Locutusque/hyperion-v2.0
language:
- en
---
# Hyperion-2.0-Mistral-7B
## Model Details
- **Model Name**: Locutusque/Hyperion-2.0-Mistral-7B
- **Base Model**: mistralai/Mistral-7B-v0.1
- **Publisher**: Locutusque
- **Model Type**: Question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, logical reasoning.
- **Language**: Multi-domain, English language.
- **License**: Apache-2.0
## Model Description
`Locutusque/Hyperion-2.0-Mistral-7B` is a state-of-the-art language model fine-tuned on the Hyperion-v2.0 dataset for advanced reasoning across scientific domains. This model is designed to handle complex inquiries and instructions, leveraging the diverse and rich information contained in the Hyperion dataset. Its primary use cases include but are not limited to complex question answering, conversational understanding, code generation, medical text comprehension, mathematical reasoning, and logical reasoning.
## Intended Use
This model is intended for researchers and practitioners looking for a powerful tool to tackle challenging problems in scientific domains. It can be used in the following scenarios:
- AI-driven tutoring systems for science, medicine, mathematics, and computer science.
- Assistive tools for professionals requiring fast and accurate domain-specific information retrieval.
- Platforms that require conversational AI capabilities with a focus on technical and scientific reasoning.
- Automation in code generation and understanding complex programming context.
## Training Data
The `Locutusque/Hyperion-2.0-Mistral-7B` model was fine-tuned on 750,000 examples of the Hyperion-v2.0 dataset, which amalgamates various datasets rich in diversity and complexity, including programming, medical texts, mathematical problems, and reasoning tasks.
## Quants
ExLlamaV2: https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-exl2
GGUF: https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF
AWQ: https://huggingface.co/solidrust/Hyperion-2.0-Mistral-7B-AWQ
## Evaluation Results
0-shot AGIEval
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|---------------------------------|-------|------|-----:|--------|-----:|---|-----:|
|agieval_nous |N/A |none | 0|acc |0.3602|± |0.0929|
| | |none | 0|acc_norm|0.3342|± |0.0764|
| - agieval_aqua_rat | 1|none | 0|acc |0.2402|± |0.0269|
| | |none | 0|acc_norm|0.2441|± |0.0270|
| - agieval_logiqa_en | 1|none | 0|acc |0.2965|± |0.0179|
| | |none | 0|acc_norm|0.3226|± |0.0183|
| - agieval_lsat_ar | 1|none | 0|acc |0.2348|± |0.0280|
| | |none | 0|acc_norm|0.2000|± |0.0264|
| - agieval_lsat_lr | 1|none | 0|acc |0.3667|± |0.0214|
| | |none | 0|acc_norm|0.3373|± |0.0210|
| - agieval_lsat_rc | 1|none | 0|acc |0.4981|± |0.0305|
| | |none | 0|acc_norm|0.4089|± |0.0300|
| - agieval_sat_en | 1|none | 0|acc |0.6359|± |0.0336|
| | |none | 0|acc_norm|0.5777|± |0.0345|
| - agieval_sat_en_without_passage| 1|none | 0|acc |0.3883|± |0.0340|
| | |none | 0|acc_norm|0.3544|± |0.0334|
| - agieval_sat_math | 1|none | 0|acc |0.3500|± |0.0322|
| | |none | 0|acc_norm|0.2682|± |0.0299|
| Groups |Version|Filter|n-shot| Metric |Value | |Stderr|
|------------|-------|------|-----:|--------|-----:|---|-----:|
|agieval_nous|N/A |none | 0|acc |0.3602|± |0.0929|
| | |none | 0|acc_norm|0.3342|± |0.0764|
5-shot AGIEval coming soon.
## How to Use
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Locutusque/Hyperion-1.5-Mistral-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# For a text generation task
input_text = "<|im_start|>user\nWhat are the implications of Einstein's theory of relativity in modern physics?<|im_end|>\n<|im_start|>assistant\n"
input_ids = tokenizer.encode(input_text, return_tensors="pt")
# Generate a response
outputs = model.generate(input_ids, max_length=200, num_return_sequences=1, temperature=0.8, top_p=0.95, top_k=40, repetition_penalty=1.1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## Known Limitations
The diversity of the dataset could lead to inconsistencies in the model's responses due to variations in data formatting and annotation quality.
This model is also very compliant, it will respond to any request. Please make sure to build upon this model with DPO if you plan on using it for enterprise-level deployment.
## Licensing Information
This model is released under the Apache-2.0 license. |
abacusai/Llama-3-Giraffe-70B-Instruct | abacusai | "2024-05-04T22:35:52Z" | 986 | 12 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"meta",
"llama-3",
"conversational",
"en",
"arxiv:2309.10400",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-03T17:34:02Z" | ---
language:
- en
pipeline_tag: text-generation
tags:
- meta
- llama-3
license: llama3
---
# Llama-3-Giraffe-70B-Instruct
Abacus.AI presents our longer-necked variant of Llama 3 70B - now with the instruct variant!
This model has an effective context length of approximately 128k.
We have currently trained on ~1.5B tokens.
There are our Needle-in-a-Haystack heatmap results. We are conducting further evals of model efficacy and will update our model card as these come in:
### MT-Bench Evaluation
We also measured performance on MT-Bench to verify that the context extension did not significantly impact performance on instruct tasks:
```
####### 1st turn:
Meta-Llama-3-70B-Instruct 9.21
Llama-3-Giraffe-70B-Instruct 9.19
####### 2nd turn:
Meta-Llama-3-70B-Instruct 2 8.80
Llama-3-Giraffe-70B-Instruct 2 8.54
####### average:
Meta-Llama-3-70B-Instruct 9.00
Llama-3-Giraffe-70B-Instruct 8.87
```
## Training Methodology
The methodology for training uses [PoSE](https://arxiv.org/abs/2309.10400) and dynamic-NTK interpolation.
### NTK-scaling
The scale factor for NTK is 4. Note that we also tried theta-scaling but this did not work as well as NTK scaling in our experiments.
### PoSE
We utilise Positional Skip-wise Training (PoSE) with the following parameters:
- **Number of Chunks**: 5
- **Max position ID**: 32768
### Data
We use on average ~8K long samples from [RedPajama](https://github.com/togethercomputer/RedPajama-Data).
### Hardware
We train on 8xH100 GPUs with Deepspeed Zero Stage 3.
## Evaluation Methodology
We use the [EasyContext](https://github.com/abacusai/EasyContext/blob/eval_runs/eval_needle.py) implementation of Needle-in-a-Haystack to evaluate Llama-3-Giraffe-70B.
We evaluate with the following parameters:
- **Min context length**: 2000
- **Max context length**: 128000
- **Context interval**: 4000
- **Depth interval**: 0.1
- **Num samples**: 2
- **Rnd number digits**: 7
- **Haystack dir**: PaulGrahamEssays
### Adapter Transfer
We apply the above techniques first to Llama-3-70B-Base, using LoRA on the Q and K weights only. This adapter is then applied to Llama-3-70B-Instruct, and we
release the merged version here. |
osiria/deberta-base-italian | osiria | "2023-06-24T16:54:52Z" | 985 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"deberta-v2",
"feature-extraction",
"it",
"arxiv:2111.09543",
"arxiv:2010.05609",
"license:mit",
"endpoints_compatible",
"region:us"
] | feature-extraction | "2023-05-29T17:48:34Z" | ---
license: mit
language:
- it
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: DeBERTa</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>DeBERTa</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using <b>mDeBERTa</b> ([mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 124M parameters, a vocabulary of 50.256 tokens, and a size of ~500 MB.
<h3>Quick usage</h3>
```python
from transformers import DebertaV2TokenizerFast, DebertaV2Model
tokenizer = DebertaV2TokenizerFast.from_pretrained("osiria/deberta-base-italian")
model = DebertaV2Model.from_pretrained("osiria/deberta-base-italian")
```
<h3>References</h3>
[1] https://arxiv.org/abs/2111.09543
[2] https://arxiv.org/abs/2010.05609
<h3>License</h3>
The model is released under <b>MIT</b> license
|
amirMohammadi/Dorna-Llama3-8B-Instruct-Quantized4Bit | amirMohammadi | "2024-06-17T09:47:32Z" | 985 | 10 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"fa",
"arxiv:2307.08691",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-08T15:30:31Z" | ---
license: llama3
language:
- en
- fa
pipeline_tag: text-generation
---
# Model Details
This Repository is a 4-bit quantized version of [Dorna-Llama3-8B-Instruct](https://huggingface.co/PartAI/Dorna-Llama3-8B-Instruct) model for efficient memory usage. Dorna model is a decoder-only model, specifically trained/fine-tuned on Persian data. [Flash Attention 2](https://arxiv.org/abs/2307.08691) is also integrated for faster inference.
## Benefits
- **Reduced Memory Usage**: 4-bit quantization lowers memory requirements.
- **Faster Inference**: Flash Attention 2 speeds up processing.
- **Easy Deployment**: No need for additional libraries like LlamaCPP or Candle.
- **Ready to Use**: Compatible with Langchain, Haystack, LlamaIndex 2, and more.
- **Google Colab Friendly**: Can run on Google Colab free tier with T4 GPU (less than 15 GB of GPU RAM).
## How to use
You can run conversational inference using the Transformers Auto classes with the `generate()` function. Let's look at an example.
```Python
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
model_path = "amirMohammadi/Dorna-Llama3-8B-Instruct-Quantized4Bit"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system",
"content": "You are a helpful Persian assistant. Please answer questions in the asked language."},
{"role": "user", "content": "اصفهان بزرگ تر است یا قم؟"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
## Evaluation of Non-Quantized version
This model is evaluated on questions across various tasks, including Boolean Questions, Code Generation, Long Response, Math, News QA, Paraphrasing, General Knowledge, and Summarization. Most categories typically have two main difficulty levels: Hard and Easy.
Both human evaluation and automatic evaluation (with GPT-4 as the judge) are performed.
In both tables, **Dorna-8B-it** is used as an abbreviated form of **Dorna-Llama3-8B-Instruct**.
Overall human evaluation results are as follows:
|**Model Pairs** | **Parameters** |**Win %**|**Lose %**|**Tie %**|
|--------------------------|:---------:|:---------:|:---------:|:---------:|
| Dorna-8B-it **vs.** Meta-Llama-3-8B-Instruct | 8B |**36.94**| 17.39 | 45.67 |
| Dorna-8B-it **vs.** GPT 3.5 turbo-1106 | N.A. |**32.01**| 26.94 | 41.05 |
| Dorna-8B-it **vs.** Persian Mind | 7B |**55.77**| 10.49 | 33.74 |
Category-based human evaluation results are as follows:
Win/Lose/Tie % is reported for each category.
<!-- | **Model Pairs** | **Parameters** | **Bool Complex** | **Bool Easy** | **Code Gen** | **General Long Response** | **Historical Long Response** | **Math Complex** | **Math Easy** | **News QA Complex** | **News QA Easy** | **Paraphrasing** | **General Knowledge Easy** | **General Knowledge Hard** | **Summarization** |
|:----------------------------------------------|:------------:|:----------------:|:----------------:|:-------------:|:-----------------------:|:--------------------------:|:----------------:|:----------------:|:-----------------:|:----------------:|:---------------:|:------------------------:|:------------------------:|:---------------:|
| Dorna-8B-it **vs.** Meta-Llama-3-8B-Instruct | 8B | 0.25/0.25/0.5 | 0.28/0.35/0.38 | 0.6/0.1/0.3 | 0.8/0.08/0.12 | 0.4/0.3/0.3 | 0.28/0.08/0.65 | 0.47/0.00/0.53 | 0.55/0.07/0.38 | 0.43/0.15/0.42 | 0.1/0.05/0.85 | 0.31/0.2/0.49 | 0.59/0.13/0.28 | 0.28/0.2/0.53 |
| Dorna-8B-it **vs.** GPT 3.5 turbo-1106 | N.A. | 0.35/0.35/0.3 | 0.3/0.3/0.4 | 0.1/0.3/.06 | 0.2/0.45/0.35 | 0.46/0.27/0.27 | 0.25/0.1/0.65 | 0.05/0.1/0.85 | 0.12/0.35/0.53 | 0.15/0.1/0.75 | 0.25/0.15/0.6 | 0.3/0.32/0.38 | 0.22/0.53/0.25 | 0.35/0.55/0.1 |
| Dorna-8B-it **vs.** Persian Mind | 7B | 0.47/0.25/0.28 | 0.57/0.15/0.28 | 0.9/0.1/0.0 | 0.82/0.08/0.1 | 0.4/0.17/0.42 | 0.3/0.0/0.7 | 0.22/0.08/0.7 | 0.72/0.07/0.2 | 0.7/0.0/0.3 | 0.7/0.05/0.25 | 0.51/0.12/0.37 | 0.61/0.1/0.29 | 0.93/0.0/0.07 |
-->
<div style="overflow-x: auto;">
<table>
<thead>
<tr style="vertical-align: middle;">
<th style="white-space: nowrap; vertical-align: middle;"><strong>Model Pairs</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Parameters</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Bool Complex</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Bool Easy</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Code Gen</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>General Long Response</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Historical Long Response</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Math Complex</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Math Easy</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>News QA Complex</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>News QA Easy</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Paraphrasing</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>General Knowledge Easy</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>General Knowledge Hard</strong></th>
<th style="white-space: nowrap; vertical-align: middle;"><strong>Summarization</strong></th>
</tr>
</thead>
<tbody>
<tr>
<td style="white-space: nowrap; vertical-align: middle;">Dorna-8B-it <strong>vs.</strong> Meta-Llama-3-8B-Instruct</td>
<td>8B</td>
<td>0.25/0.25/0.5</td>
<td>0.28/<strong>0.35</strong>/0.38</td>
<td><strong>0.6</strong>/0.1/0.3</td>
<td><strong>0.8</strong>/0.08/0.12</td>
<td><strong>0.4</strong>/0.3/0.3</td>
<td><strong>0.28</strong>/0.08/0.65</td>
<td><strong>0.47</strong>/0.00/0.53</td>
<td><strong>0.55</strong>/0.07/0.38</td>
<td><strong>0.43</strong>/0.15/0.42</td>
<td><strong>0.1</strong>/0.05/0.85</td>
<td><strong>0.31</strong>/0.2/0.49</td>
<td><strong>0.59</strong>/0.13/0.28</td>
<td><strong>0.28</strong>/0.2/0.53</td>
</tr>
<tr>
<td style="white-space: nowrap; vertical-align: middle;">Dorna-8B-it <strong>vs.</strong> GPT 3.5 turbo-1106</td>
<td>N.A.</td>
<td>0.35/0.35/0.3</td>
<td>0.3/0.3/0.4</td>
<td>0.1/<strong>0.3</strong>/.06</td>
<td>0.2/<strong>0.45</strong>/0.35</td>
<td><strong>0.46</strong>/0.27/0.27</td>
<td><strong>0.25</strong>/0.1/0.65</td>
<td>0.05/<strong>0.1</strong>/0.85</td>
<td>0.12/<strong>0.35</strong>/0.53</td>
<td><strong>0.15</strong>/0.1/0.75</td>
<td><strong>0.25</strong>/0.15/0.6</td>
<td>0.3/<strong>0.32</strong>/0.38</td>
<td>0.22/<strong>0.53</strong>/0.25</td>
<td>0.35/<strong>0.55</strong>/0.1</td>
</tr>
<tr>
<td style="white-space: nowrap; vertical-align: middle;">Dorna-8B-it <strong>vs.</strong> Persian Mind</td>
<td>7B</td>
<td><strong>0.47</strong>/0.25/0.28</td>
<td><strong>0.57</strong>/0.15/0.28</td>
<td><strong>0.9</strong>/0.1/0.0</td>
<td><strong>0.82</strong>/0.08/0.1</td>
<td><strong>0.4</strong>/0.17/0.42</td>
<td><strong>0.3</strong>/0.0/0.7</td>
<td><strong>0.22</strong>/0.08/0.7</td>
<td><strong>0.72</strong>/0.07/0.2</td>
<td><strong>0.7</strong>/0.0/0.3</td>
<td><strong>0.7</strong>/0.05/0.25</td>
<td><strong>0.51</strong>/0.12/0.37</td>
<td><strong>0.61</strong>/0.1/0.29</td>
<td><strong>0.93</strong>/0.0/0.07</td>
</tr>
</tbody>
</table>
</div>
Automatic evaluation results are as follows:
| **Model Pairs** | **Parameters** | **Overall Win Rate %** | **Easy Win Rate %** | **Hard Win Rate %** |
|----------------------------------------|:--------------:|:----------------------:|:-------------------:|:-------------------:|
| Dorna-8B-it **vs.** Llama 3 base | 8B | **58.96** | **56.00** | **64.49** |
| Dorna-8B-it **vs.** Part Mistral | 7B | **77.20** | **73.00** | **85.05** |
| Dorna-8B-it **vs.** Persian Mind | 7B | **90.88** | **87.50** | **97.20** |
| Dorna-8B-it **vs.** Neuraorca Gemma 7b | 7B | **86.32** | **86.50** | **85.98** |
| Dorna-8B-it **vs.** Maral 7b | 7B | **97.39** | **97.00** | **98.13** |
| Dorna-8B-it **vs.** PersianLlama 7b | 7B | **98.70** | **98.00** | **100.00** |
| Dorna-8B-it **vs.** Aya-23-8B | 8B | **52.77** | **56.50** | 45.79 |
| Dorna-8B-it **vs.** Aya-23-35B | 35B | 45.93 | **54.00** | 30.84 |
| Dorna-8B-it **vs.** Command R | 35B | **58.63** | **61.00** | **54.21** |
## Contact us
If you have any questions regarding this model, you can reach us via the [community](https://huggingface.co/amirMohammadi/Dorna-Llama3-8B-Instruct-Quantized4Bit/discussions) on Hugging Face. |
mradermacher/Llama-Salad-8x8B-i1-GGUF | mradermacher | "2024-06-10T02:09:42Z" | 985 | 1 | transformers | [
"transformers",
"gguf",
"nsfw",
"not-for-all-audiences",
"llama-3",
"text-generation-inference",
"moe",
"mergekit",
"merge",
"en",
"base_model:HiroseKoichi/Llama-Salad-8x8B",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | "2024-06-09T06:18:14Z" | ---
base_model: HiroseKoichi/Llama-Salad-8x8B
language:
- en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
- nsfw
- not-for-all-audiences
- llama-3
- text-generation-inference
- moe
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/HiroseKoichi/Llama-Salad-8x8B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Llama-Salad-8x8B-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ1_S.gguf) | i1-IQ1_S | 10.3 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ1_M.gguf) | i1-IQ1_M | 11.4 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 13.1 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ2_S.gguf) | i1-IQ2_S | 14.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ2_M.gguf) | i1-IQ2_M | 16.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q2_K.gguf) | i1-Q2_K | 17.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 20.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ3_S.gguf) | i1-IQ3_S | 21.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 21.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ3_M.gguf) | i1-IQ3_M | 22.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 23.1 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q4_0.gguf) | i1-Q4_0 | 27.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 29.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-Salad-8x8B-i1-GGUF/resolve/main/Llama-Salad-8x8B.i1-Q6_K.gguf) | i1-Q6_K | 39.1 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
<!-- end -->
|
openbmb/OmniLMM-12B | openbmb | "2024-04-16T03:15:05Z" | 984 | 60 | transformers | [
"transformers",
"pytorch",
"omnilmm",
"text-generation",
"visual-question-answering",
"dataset:HaoyeZhang/RLHF-V-Dataset",
"dataset:Yirany/UniMM-Chat",
"arxiv:2312.00849",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | visual-question-answering | "2024-01-31T06:44:51Z" | ---
pipeline_tag: visual-question-answering
datasets:
- HaoyeZhang/RLHF-V-Dataset
- Yirany/UniMM-Chat
---
## OmniLMM 12B
[GitHub](https://github.com/OpenBMB/MiniCPM-V) | [Demo](http://120.92.209.146:8081/)
**OmniLMM-12B** is the most capable version of OmniLMM currently. The model is built based on EVA02-5B and Zephyr-7B-β, connected with a perceiver resampler layer, and trained on multimodal data in a curriculum fashion. The model has three notable features:
- 🔥 **Strong Performance.**
OmniLMM-12B achieves **leading performance** among models with comparable sizes, surpassing established LMMs on multiple benchmarks (including MME, MMBench, SEED-Bench, etc). The model also endows rich multi-modal world knowledge.
- 🏆 **Trustworthy Behavior.**
LMMs are known for suffering from hallucination, often generating text that is not factually grounded in images (e.g., faithfully describing non-existing objects in images). OmniLMM-12B is **the first state-of-the-art open-source LMM aligned via multimodal RLHF for trustworthy behavior** (using the recent [RLHF-V](https://rlhf-v.github.io/) technique). It **ranks #1** among open-source models on [MMHal-Bench](https://huggingface.co/datasets/Shengcao1006/MMHal-Bench), and **outperforms GPT-4V** on [Object HalBench](https://arxiv.org/abs/2312.00849).
- 🕹 **Real-time Multimodal Interaction.**
We combine the OmniLMM-12B and GPT-3.5 (text-only) into a **real-time multimodal interactive assistant**. The assistant accepts video streams from the camera and speech streams from the microphone and emits speech output. While still primary, we find the model can **replicate some of the fun cases shown in the Gemini Demo video, without any video edition**.
## Evaluation
<div align="center">
<img src=https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/LuKikSY4CJiqtHocGP_xu.png width=66% />
</div>
<details>
<summary>Click to view results on MME, MMBench, MMMU, MMBench, MMHal-Bench, Object HalBench, SeedBench, LLaVA Bench W, MathVista. </summary>
<table>
<thead>
<tr>
<th align="left">Model</th>
<th>Size</th>
<th>MME</th>
<th nowrap="nowrap">MMB dev (en)</th>
<th nowrap="nowrap" >MMMU val</th>
<th nowrap="nowrap" >MMHal-Bench</th>
<th nowrap="nowrap" >Object HalBench</th>
<th nowrap="nowrap" >SeedBench-I</th>
<th>MathVista</th>
<th nowrap="nowrap" >LLaVA Bench W</th>
</tr>
</thead>
<tbody align="center">
<tr>
<td align="left">GPT-4V†</td>
<td>-</td>
<td>1409</td>
<td>75.1 </td>
<td>56.8</td>
<td>3.53 / 70.8</td>
<td>86.4 / 92.7</td>
<td>71.6 </td>
<td>47.8 </td>
<td>93.1 </td>
</tr>
<tr>
<td nowrap="nowrap" align="left">Qwen-VL-Plus†</td>
<td>-</td>
<td>1681</td>
<td>66.2 </td>
<td>45.2</td>
<td>- </td>
<td>- </td>
<td>65.7 </td>
<td>36.0 </td>
<td>73.7 </td>
</tr>
<tr>
<td align="left">Yi-VL 6B</td>
<td align="right">6.7B </td>
<td>- </td>
<td>68.2 </td>
<td>39.1 </td>
<td>- </td>
<td>- </td>
<td>66.1 </td>
<td>28.0 </td>
<td>39.9 </td>
</tr>
<tr>
<td nowrap="nowrap" align="left" >Qwen-VL-Chat</td>
<td align="right">9.6B</td>
<td>1488</td>
<td>60.6 </td>
<td>35.9</td>
<td>2.93 / 59.4</td>
<td>56.2 / 80.0</td>
<td>64.8 </td>
<td>33.8 </td>
<td>67.7 </td>
</tr>
<tr>
<td align="left" >CogVLM</td>
<td align="right">17.4B</td>
<td>1438</td>
<td>63.7 </td>
<td>32.1 </td>
<td>2.68 / 52.1 </td>
<td>73.6 / 87.4 </td>
<td>68.8 </td>
<td>34.7 </td>
<td>73.9 </td>
</tr>
<tr>
<td align="left" >LLaVA 1.5</td>
<td align="right">13.6B </td>
<td>1531 </td>
<td>68.2 </td>
<td>36.4 </td>
<td>2.71 / 51.0 </td>
<td>53.7 / 77.4 </td>
<td>68.1 </td>
<td>26.4 </td>
<td>64.6 </td>
</tr>
<tr>
<td nowrap="nowrap" align="left" ><b>OmniLMM-12B</b></td>
<td align="right">11.6B </td>
<td>1637 </td>
<td>71.6 </td>
<td>40.7 </td>
<td>3.45 / 68.8 </td>
<td>90.3 / 95.5 </td>
<td>71.1 </td>
<td>34.9 </td>
<td>72.0 </td>
</tr>
</tbody>
</table>
<small>†: Proprietary models</small>
<br>
</details>
## Demo
Click here to try out the Demo of [OmniLMM-12B](http://120.92.209.146:8081).
## Usage
Please look at [GitHub](https://github.com/OpenBMB/OmniLMM) for more detail about usage.
## License
#### Model License
* The code in this repo is released according to [Apache-2.0](https://github.com/OpenBMB/OmniLMM/blob/main/LICENSE)
* The usage of OmniLMM's parameters is subject to ["General Model License Agreement - Source Notes - Publicity Restrictions - Commercial License"](https://github.com/OpenBMB/General-Model-License/blob/main/)
* The parameters are fully open to acedemic research
* Please contact [email protected] to obtain a written authorization for commercial uses. Free commercial use is also allowed after registration.
#### Statement
* As LMMs, OmniLMM generates contents by learning a large mount of texts, but it cannot comprehend, express personal opinions or make value judgement. Anything generated by OmniLMM does not represent the views and positions of the model developers
* We will not be liable for any problems arising from the use of the OmniLMM open Source model, including but not limited to data security issues, risk of public opinion, or any risks and problems arising from the misdirection, misuse, dissemination or misuse of the model.
## Multimodal Projects of Our Team <!-- omit in toc -->
[VisCPM](https://github.com/OpenBMB/VisCPM/tree/main) | [RLHF-V](https://github.com/RLHF-V/RLHF-V) | [LLaVA-UHD](https://github.com/thunlp/LLaVA-UHD)
## Citation
If you find our work helpful, please consider citing the following papers
```bib
@article{yu2023rlhf,
title={Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback},
author={Yu, Tianyu and Yao, Yuan and Zhang, Haoye and He, Taiwen and Han, Yifeng and Cui, Ganqu and Hu, Jinyi and Liu, Zhiyuan and Zheng, Hai-Tao and Sun, Maosong and others},
journal={arXiv preprint arXiv:2312.00849},
year={2023}
}
@article{viscpm,
title={Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages},
author={Jinyi Hu and Yuan Yao and Chongyi Wang and Shan Wang and Yinxu Pan and Qianyu Chen and Tianyu Yu and Hanghao Wu and Yue Zhao and Haoye Zhang and Xu Han and Yankai Lin and Jiao Xue and Dahai Li and Zhiyuan Liu and Maosong Sun},
journal={arXiv preprint arXiv:2308.12038},
year={2023}
}
@article{xu2024llava-uhd,
title={{LLaVA-UHD}: an LMM Perceiving Any Aspect Ratio and High-Resolution Images},
author={Xu, Ruyi and Yao, Yuan and Guo, Zonghao and Cui, Junbo and Ni, Zanlin and Ge, Chunjiang and Chua, Tat-Seng and Liu, Zhiyuan and Huang, Gao},
journal={arXiv preprint arXiv:2403.11703},
year={2024}
}
``` |
RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf | RichardErkhov | "2024-06-05T17:56:55Z" | 984 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-05T17:27:32Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
emailgen-pythia-410m-deduped - GGUF
- Model creator: https://huggingface.co/postbot/
- Original model: https://huggingface.co/postbot/emailgen-pythia-410m-deduped/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [emailgen-pythia-410m-deduped.Q2_K.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q2_K.gguf) | Q2_K | 0.16GB |
| [emailgen-pythia-410m-deduped.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.IQ3_XS.gguf) | IQ3_XS | 0.18GB |
| [emailgen-pythia-410m-deduped.IQ3_S.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.IQ3_S.gguf) | IQ3_S | 0.18GB |
| [emailgen-pythia-410m-deduped.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q3_K_S.gguf) | Q3_K_S | 0.18GB |
| [emailgen-pythia-410m-deduped.IQ3_M.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.IQ3_M.gguf) | IQ3_M | 0.2GB |
| [emailgen-pythia-410m-deduped.Q3_K.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q3_K.gguf) | Q3_K | 0.21GB |
| [emailgen-pythia-410m-deduped.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q3_K_M.gguf) | Q3_K_M | 0.21GB |
| [emailgen-pythia-410m-deduped.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q3_K_L.gguf) | Q3_K_L | 0.22GB |
| [emailgen-pythia-410m-deduped.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.IQ4_XS.gguf) | IQ4_XS | 0.22GB |
| [emailgen-pythia-410m-deduped.Q4_0.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q4_0.gguf) | Q4_0 | 0.23GB |
| [emailgen-pythia-410m-deduped.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.IQ4_NL.gguf) | IQ4_NL | 0.23GB |
| [emailgen-pythia-410m-deduped.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q4_K_S.gguf) | Q4_K_S | 0.23GB |
| [emailgen-pythia-410m-deduped.Q4_K.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q4_K.gguf) | Q4_K | 0.25GB |
| [emailgen-pythia-410m-deduped.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q4_K_M.gguf) | Q4_K_M | 0.25GB |
| [emailgen-pythia-410m-deduped.Q4_1.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q4_1.gguf) | Q4_1 | 0.25GB |
| [emailgen-pythia-410m-deduped.Q5_0.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q5_0.gguf) | Q5_0 | 0.27GB |
| [emailgen-pythia-410m-deduped.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q5_K_S.gguf) | Q5_K_S | 0.27GB |
| [emailgen-pythia-410m-deduped.Q5_K.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q5_K.gguf) | Q5_K | 0.28GB |
| [emailgen-pythia-410m-deduped.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q5_K_M.gguf) | Q5_K_M | 0.28GB |
| [emailgen-pythia-410m-deduped.Q5_1.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q5_1.gguf) | Q5_1 | 0.29GB |
| [emailgen-pythia-410m-deduped.Q6_K.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q6_K.gguf) | Q6_K | 0.31GB |
| [emailgen-pythia-410m-deduped.Q8_0.gguf](https://huggingface.co/RichardErkhov/postbot_-_emailgen-pythia-410m-deduped-gguf/blob/main/emailgen-pythia-410m-deduped.Q8_0.gguf) | Q8_0 | 0.4GB |
Original model description:
---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- postbot/multi-emails-hq
metrics:
- accuracy
widget:
- text: 'Good Morning Professor Beans,
Hope you are doing well. I just wanted to reach out and ask if differential calculus
will be on the exam'
example_title: email to prof
- text: 'Hey <NAME>,
Thank you for signing up for my weekly newsletter. Before we get started, you''ll
have to confirm your email address.'
example_title: newsletter
- text: 'Hi <NAME>,
I hope this email finds you well. I wanted to reach out and ask about office hours'
example_title: office hours
- text: 'Greetings <NAME>,
I hope you had a splendid evening at the Company sausage eating festival. I am
reaching out because'
example_title: festival
- text: 'Good Morning Harold,
I was wondering when the next'
example_title: event
- text: URGENT - I need the TPS reports
example_title: URGENT
- text: 'Hi Archibald,
I hope this email finds you extremely well.'
example_title: emails that find you
- text: 'Hello there.
I just wanted to reach out and check in to'
example_title: checking in
- text: 'Hello <NAME>,
I hope this email finds you well. I wanted to reach out and see if you''ve enjoyed
your time with us'
example_title: work well
- text: 'Hi <NAME>,
I hope this email finds you well. I wanted to reach out and see if we could catch
up'
example_title: catch up
- text: I'm <NAME> and I just moved into the area and wanted to reach out and get
some details on where I could get groceries and
example_title: grocery
pipeline_tag: text-generation
base_model: EleutherAI/pythia-410m-deduped
model-index:
- name: multi-emails-hq-pythia-410m-deduped-r1
results: []
---
# emailgen-pythia-410m-deduped
[](https://colab.research.google.com/gist/pszemraj/94b0e6b95437896f800a65ae2e5f9ab4/emailgen-pythia-410m-deduped.ipynb
)
This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on email data.
It achieves the following results on the evaluation set:
- Loss: 2.1018
- Accuracy: 0.6157
- perplexity: 8.181
## Model description
- fine-tuned on dataset of emails for 4 epochs
- intended use: "text completion" of partially written emails
## Usage example
```python
from transformers import pipeline
model_tag = "postbot/emailgen-pythia-410m-deduped"
generator = pipeline(
"text-generation",
model=model_tag,
)
prompt = """
Hello,
Following up on the bubblegum shipment."""
result = generator(
prompt,
) # generate
print(result[0]["generated_text"])
```
---
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_postbot__emailgen-pythia-410m-deduped)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 26.65 |
| ARC (25-shot) | 27.9 |
| HellaSwag (10-shot) | 40.04 |
| MMLU (5-shot) | 27.35 |
| TruthfulQA (0-shot) | 38.2 |
| Winogrande (5-shot) | 52.09 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 0.99 |
|
SoloBSD/Tinyllama-sp | SoloBSD | "2024-06-25T00:31:42Z" | 984 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"license:bsd-3-clause",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | "2024-06-24T22:32:38Z" | ---
license: bsd-3-clause
---
|
timm/vit_base_patch32_384.augreg_in21k_ft_in1k | timm | "2023-05-06T00:03:42Z" | 983 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-21k",
"arxiv:2106.10270",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-12-22T07:35:19Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-21k
---
# Model card for vit_base_patch32_384.augreg_in21k_ft_in1k
A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.3
- GMACs: 12.7
- Activations (M): 12.1
- Image size: 384 x 384
- **Papers:**
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-21k
- **Original:** https://github.com/google-research/vision_transformer
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_base_patch32_384.augreg_in21k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch32_384.augreg_in21k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 145, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{steiner2021augreg,
title={How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers},
author={Steiner, Andreas and Kolesnikov, Alexander and and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
journal={arXiv preprint arXiv:2106.10270},
year={2021}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
soi147/3d-humanoid | soi147 | "2024-06-06T04:59:11Z" | 983 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-10-27T00:44:14Z" | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### 3D_humanoid Dreambooth model trained by soi147 with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
這 3D人形建模是使用 DesignDoll 免費版的,採集圖片 訓練模型
以修復 基礎訓練模型 為主的 合併用的
訓練出來的 3D人形建模, 是不專業的
玩家的我
----------------------
|
ConvexAI/Luminex-34B-v0.1 | ConvexAI | "2024-03-04T16:33:31Z" | 983 | 8 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"base_model:jondurbin/bagel-34b-v0.2",
"license:other",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-16T09:12:34Z" | ---
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
base_model: jondurbin/bagel-34b-v0.2
model-index:
- name: Luminex-34B-v0.1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 73.63
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-34B-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 86.59
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-34B-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 76.55
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-34B-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 69.68
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-34B-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 83.43
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-34B-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 72.48
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-34B-v0.1
name: Open LLM Leaderboard
---
# ConvexAI/Luminex-34B-v0.1
This model is [Smaug-34b](https://huggingface.co/abacusai/Smaug-34B-v0.1) with LaserRMT applied.
[Join our Discord!](https://discord.gg/rJXGjmxqzS)
### Evaluation Results
Coming Soon
### Contamination Results
Coming Soon
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ConvexAI__Luminex-34B-v0.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |77.06|
|AI2 Reasoning Challenge (25-Shot)|73.63|
|HellaSwag (10-Shot) |86.59|
|MMLU (5-Shot) |76.55|
|TruthfulQA (0-shot) |69.68|
|Winogrande (5-shot) |83.43|
|GSM8k (5-shot) |72.48|
|
TechxGenus/gemma-2b-GPTQ | TechxGenus | "2024-03-05T04:49:04Z" | 983 | 1 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:2312.11805",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:1804.06876",
"arxiv:2110.08193",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:2203.09509",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | "2024-03-05T04:40:53Z" | ---
library_name: transformers
tags: []
extra_gated_heading: "Access Gemma on Hugging Face"
extra_gated_prompt: "To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately."
extra_gated_button_content: "Acknowledge license"
license: other
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
---
GPTQ quantized version of gemma-2b model.
---
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
**Resources and Technical Documentation**:
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-2b-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
#### Fine-tuning the model
You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-2b`.
In that repository, we provide:
* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA
* A script to perform SFT using FSDP on TPU devices
* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a GPU using different precisions
* _Using `torch.float16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.float16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using 4-bit precision_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Other optimizations
* _Flash Attention 2_
First make sure to install `flash-attn` in your environment `pip install flash-attn`
```diff
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ml-pathways).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 59.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | - | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **54.0** | **56.4** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### Evaluation Approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
biases embedded in the training material. These models underwent careful
scrutiny, input data pre-processing described and posterior evaluations
reported in this card.
* Misinformation and Misuse
* LLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the
[Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible).
* Transparency and Accountability:
* This model card summarizes details on the models' architecture,
capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share
innovation by making LLM technology accessible to developers and researchers
across the AI ecosystem.
Risks identified and mitigations:
* Perpetuation of biases: It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* Generation of harmful content: Mechanisms and guidelines for content safety
are essential. Developers are encouraged to exercise caution and implement
appropriate content safety safeguards based on their specific product policies
and application use cases.
* Misuse for malicious purposes: Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
|
Josephgflowers/Tinyllama-616M-Cinder-DPO-With-GGUF | Josephgflowers | "2024-04-03T02:37:42Z" | 983 | 0 | transformers | [
"transformers",
"safetensors",
"gguf",
"llama",
"text-generation",
"conversational",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-03T01:55:44Z" | ---
license: mit
---
I cut my TinyLlama 1.1B cinder v 2 down from 22 layers to 14. At 14 there was no coherent text but there were emerging ideas of a response. I then trained on the Reason with Cinder dataset and prunned the model again to 11 layers and only emerging responses. I then trained on a subset of open orca, sharegpt, cinder again, and tiny textbooks. I am putting it up as a base model that may need work. If you continue training please let me know on the tinyllama discord, I have some interesting plans for this model. I use the Zephyr chat format. |
Yntec/3DRendering | Yntec | "2023-10-17T06:53:21Z" | 982 | 6 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Illustration",
"Midjourney",
"LONGD",
"s6yx",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-10-07T16:18:15Z" | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Illustration
- Midjourney
- LONGD
- s6yx
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
---
# 3DRendering
ReVAnimated with the 3DMM V3 LoRA merged in. It uses the MoistMixV2VAE.
Samples and prompt:
yakuza, ✨, a beautiful detailed painting of a still life of fruit and Cartoon Pretty CUTE LITTLE Girl, beautiful detailed legs, flowers in a basket, DETAILED CHIBI EYES, artgerm, Terry moore, james jean, visible brushstrokes, Iconic, gorgeous detailed hair, Magazine ad, detailed fruitcake, 1949, sharp focus
Original pages:
https://civitai.com/models/73756?modelVersionId=78564 (3DMM LoRA)
https://civitai.com/models/7371?modelVersionId=8665 (ReVAnimated) |
paulml/OmniBeagleMBX-v3-7B | paulml | "2024-02-04T16:55:39Z" | 982 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/OmniBeagle-7B",
"flemmingmiguel/MBX-7B-v3",
"base_model:mlabonne/OmniBeagle-7B",
"base_model:flemmingmiguel/MBX-7B-v3",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-04T13:23:36Z" | ---
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/OmniBeagle-7B
- flemmingmiguel/MBX-7B-v3
base_model:
- mlabonne/OmniBeagle-7B
- flemmingmiguel/MBX-7B-v3
license: cc-by-nc-4.0
---
# OmniBeagleMBX-v3-7B
OmniBeagleMBX-v3-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B)
* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: mlabonne/OmniBeagle-7B
layer_range: [0, 32]
- model: flemmingmiguel/MBX-7B-v3
layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/OmniBeagle-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "paulml/OmniBeagleMBX-v3-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
MBZUAI/MobiLlama-1B | MBZUAI | "2024-02-28T05:18:05Z" | 982 | 14 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"nlp",
"code",
"custom_code",
"en",
"dataset:LLM360/AmberDatasets",
"arxiv:2402.16840",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-24T16:07:35Z" | ---
license: mit
license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- nlp
- code
datasets:
- LLM360/AmberDatasets
---
# MobiLlama-1B
<center><img src="MobileLLaMa.png" alt="mobillama logo" width="300"/></center>
MobiLlama-1B is a Small Language Model with **1.2 billion** parameters. It was trained using the Amber data sources [Amber-Dataset](https://huggingface.co/datasets/LLM360/AmberDatasets).
## Model Summary
"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development. However, LLMs do not suit well for scenarios that require on-device processing, energy efficiency, low memory footprint, and response efficiency. These requisites are crucial for privacy, security, and sustainable deployment. This paper explores the ‘less is more’ paradigm by addressing the challenge of designing accurate yet efficient Small Language Models (SLMs) for resource-constrained devices. Our primary contribution is the introduction of an accurate and fully transparent open-source 0.5 billion (0.5B) parameter SLM, named MobiLlama, catering to the specific needs of resource-constrained computing with an emphasis on enhanced performance with reduced resource demands. MobiLlama is a SLM design that initiates from a larger model and applies a careful parameter sharing scheme to reduce both the pre-training and the deployment cost. Our work strives to not only bridge the gap in open-source SLMs but also ensures full transparency, where complete training data pipeline, training code, model weights, and over 300 checkpoints along with evaluation codes are available on our [Github](https://github.com/mbzuai-oryx/MobiLlama).
[Arxiv Paper Link](https://arxiv.org/abs/2402.16840)
## Model Description
- **Model type:** Small Language Model (SLM) built using the architecture design of LLaMA-7B
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Resources for more information:**
- [Training Code](https://github.com/mbzuai-oryx/MobiLlama)
- [Data Preparation](https://github.com/LLM360/amber-data-prep)
- [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
## How to Use
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("MBZUAI/MobiLlama-1B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("MBZUAI/MobiLlama-1B", trust_remote_code=True)
model.to('cuda')
text = "I was walking towards the river when "
input_ids = tokenizer(text, return_tensors="pt").to('cuda').input_ids
outputs = model.generate(input_ids, max_length=1000, repetition_penalty=1.2, pad_token_id=tokenizer.eos_token_id)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
```
## Training DataMix
| Subset | Tokens (Billion) |
| ----------- | ----------- |
| Arxiv | 30.00 |
| Book | 28.86 |
| C4 | 197.67 |
| Refined-Web | 665.01 |
| StarCoder | 291.92 |
| StackExchange | 21.75 |
| Wikipedia | 23.90 |
| Total | 1259.13 |
## Hyperparameters
| Hyperparameter | Value |
| ----------- | ----------- |
| Total Parameters | 1.2B |
| Hidden Size | 2048 |
| Intermediate Size (MLPs) | 5632 |
| Number of Attention Heads | 32 |
| Number of Hidden Lyaers | 22 |
| RMSNorm ɛ | 1e^-5 |
| Max Seq Length | 2048 |
| Vocab Size | 32000 |
## Evaluation
| Evaluation Benchmark | MobiLlama-0.5B | MobiLlama-0.8B | MobiLlama-1.2B |
| ----------- | ----------- | ----------- | ----------- |
| HellaSwag | 52.52 | 54.09 | 62.99 |
| MMLU | 26.45 | 26.92 | 24.23 |
| Arc Challenge | 29.52 | 30.20 | 34.55 |
| TruthfulQA | 38.05 | 38.48 | 35.57 |
| CrowsPairs | 64.03 | 64.82 | 68.12 |
| PIQA | 72.03 | 73.17 | 75.29 |
| Race | 33.68 | 33.37 | 35.31 |
| SIQA | 40.22 | 41.60 | 41.96 |
| Winogrande | 57.53 | 57.45 | 61.08 |
## Citation
**BibTeX:**
```bibtex
@misc{thawakar2024mobillama,
title={MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT},
author={Omkar Thawakar and Ashmal Vayani and Salman Khan and Hisham Cholakkal and Rao Muhammad Anwer and Michael Felsberg and Timothy Baldwin and Eric P. Xing and Fahad Shahbaz Khan},
year={2024},
eprint={2402.16840},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf | RichardErkhov | "2024-06-05T00:05:52Z" | 982 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-04T23:32:25Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
DialoGPT-medium-joshua - GGUF
- Model creator: https://huggingface.co/r3dhummingbird/
- Original model: https://huggingface.co/r3dhummingbird/DialoGPT-medium-joshua/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [DialoGPT-medium-joshua.Q2_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q2_K.gguf) | Q2_K | 0.17GB |
| [DialoGPT-medium-joshua.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ3_XS.gguf) | IQ3_XS | 0.18GB |
| [DialoGPT-medium-joshua.IQ3_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ3_S.gguf) | IQ3_S | 0.19GB |
| [DialoGPT-medium-joshua.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K_S.gguf) | Q3_K_S | 0.19GB |
| [DialoGPT-medium-joshua.IQ3_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ3_M.gguf) | IQ3_M | 0.2GB |
| [DialoGPT-medium-joshua.Q3_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K.gguf) | Q3_K | 0.21GB |
| [DialoGPT-medium-joshua.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K_M.gguf) | Q3_K_M | 0.21GB |
| [DialoGPT-medium-joshua.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K_L.gguf) | Q3_K_L | 0.23GB |
| [DialoGPT-medium-joshua.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ4_XS.gguf) | IQ4_XS | 0.22GB |
| [DialoGPT-medium-joshua.Q4_0.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_0.gguf) | Q4_0 | 0.23GB |
| [DialoGPT-medium-joshua.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ4_NL.gguf) | IQ4_NL | 0.23GB |
| [DialoGPT-medium-joshua.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_K_S.gguf) | Q4_K_S | 0.23GB |
| [DialoGPT-medium-joshua.Q4_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_K.gguf) | Q4_K | 0.25GB |
| [DialoGPT-medium-joshua.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_K_M.gguf) | Q4_K_M | 0.25GB |
| [DialoGPT-medium-joshua.Q4_1.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_1.gguf) | Q4_1 | 0.25GB |
| [DialoGPT-medium-joshua.Q5_0.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_0.gguf) | Q5_0 | 0.27GB |
| [DialoGPT-medium-joshua.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_K_S.gguf) | Q5_K_S | 0.27GB |
| [DialoGPT-medium-joshua.Q5_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_K.gguf) | Q5_K | 0.29GB |
| [DialoGPT-medium-joshua.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_K_M.gguf) | Q5_K_M | 0.29GB |
| [DialoGPT-medium-joshua.Q5_1.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_1.gguf) | Q5_1 | 0.29GB |
| [DialoGPT-medium-joshua.Q6_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q6_K.gguf) | Q6_K | 0.32GB |
| [DialoGPT-medium-joshua.Q8_0.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q8_0.gguf) | Q8_0 | 0.41GB |
Original model description:
---
thumbnail: https://raw.githubusercontent.com/RuolinZheng08/twewy-discord-chatbot/main/gif-demo/icon.png
tags:
- conversational
license: mit
---
# DialoGPT Trained on the Speech of a Game Character
This is an instance of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) trained on a game character, Joshua from [The World Ends With You](https://en.wikipedia.org/wiki/The_World_Ends_with_You). The data comes from [a Kaggle game script dataset](https://www.kaggle.com/ruolinzheng/twewy-game-script).
I built a Discord AI chatbot based on this model. [Check out my GitHub repo.](https://github.com/RuolinZheng08/twewy-discord-chatbot)
Chat with the model:
```python
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua")
model = AutoModelWithLMHead.from_pretrained("r3dhummingbird/DialoGPT-medium-joshua")
# Let's chat for 4 lines
for step in range(4):
# encode the new user input, add the eos_token and return a tensor in Pytorch
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
# print(new_user_input_ids)
# append the new user input tokens to the chat history
bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
# generated a response while limiting the total chat history to 1000 tokens,
chat_history_ids = model.generate(
bot_input_ids, max_length=200,
pad_token_id=tokenizer.eos_token_id,
no_repeat_ngram_size=3,
do_sample=True,
top_k=100,
top_p=0.7,
temperature=0.8
)
# pretty print last ouput tokens from bot
print("JoshuaBot: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
```
|
gglabs/TinyLM-Chat-0611-9-epoch | gglabs | "2024-06-11T17:06:41Z" | 982 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/tinyllama-chat-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-11T14:32:21Z" | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/tinyllama-chat-bnb-4bit
---
# Uploaded model
- **Developed by:** gglabs
- **License:** apache-2.0
- **Finetuned from model :** unsloth/tinyllama-chat-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
ahishamm/skinsam | ahishamm | "2023-07-10T17:54:07Z" | 981 | 0 | transformers | [
"transformers",
"pytorch",
"sam",
"mask-generation",
"en",
"dataset:ahishamm/combined_masks",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | mask-generation | "2023-07-09T13:28:57Z" | ---
license: apache-2.0
datasets:
- ahishamm/combined_masks
language:
- en
metrics:
- accuracy
- f1
- mean_iou
---
## Model Description
<!-- Provide a longer summary of what this model is/does. -->
SkinSAM is on the 12-layer ViT-b model, the mask decoder module of SAM is fine-tuned on a combined dataset of ISIC and PH2 skin lesion images and masks.
SkinSAM was trained on an Nvidia Tesla A100 40GB GPU.
Some of the notable results taken:
ISIC Dataset:
1. IOU 78.25%
2. Pixel Accuracy 92.18%
3. F1 Score 87.47%
PH2 Dataset:
1. IOU 86.68%
2. Pixel Accuracy 93.33%
3. F1 Score 93.95% |
lorahub/flan_t5_large-newsroom | lorahub | "2023-07-24T10:17:44Z" | 981 | 0 | peft | [
"peft",
"region:us"
] | null | "2023-07-24T10:17:34Z" | ---
library_name: peft
---
|
utrobinmv/t5_translate_en_ru_zh_base_200 | utrobinmv | "2024-02-04T13:44:00Z" | 981 | 8 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"translation",
"ru",
"zh",
"en",
"dataset:ccmatrix",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | translation | "2024-01-07T14:48:46Z" | ---
language:
- ru
- zh
- en
tags:
- translation
- text2text-generation
- t5
license: apache-2.0
datasets:
- ccmatrix
metrics:
- sacrebleu
widget:
- example_title: translate zh-ru
text: >
translate to ru: 开发的目的是为用户提供个人同步翻译。
- example_title: translate ru-en
text: >
translate to en: Цель разработки — предоставить пользователям личного синхронного переводчика.
- example_title: translate en-ru
text: >
translate to ru: The purpose of the development is to provide users with a personal synchronized interpreter.
- example_title: translate en-zh
text: >
translate to zh: The purpose of the development is to provide users with a personal synchronized interpreter.
- example_title: translate zh-en
text: >
translate to en: 开发的目的是为用户提供个人同步解释器。
- example_title: translate ru-zh
text: >
translate to zh: Цель разработки — предоставить пользователям личного синхронного переводчика.
model-index:
- name: utrobinmv/t5_translate_en_ru_zh_base_200
results:
- task:
type: translation
name: Translation en-ru
dataset:
name: ntrex_en-ru
type: ntrex
config: ntrex en-ru
split: test
metrics:
- type: sacrebleu
value: 28.575940911021487
name: bleu
verified: false
- type: chrf
value: 54.27996346886896
name: chrf
verified: false
- type: ter
value: 62.494863914873584
name: ter
verified: false
- type: meteor
value: 0.5174833677740809
name: meteor
verified: false
- type: rouge
value: 0.1908317951570274
name: ROUGE-1
verified: false
- type: rouge
value: 0.065555552204933
name: ROUGE-2
verified: false
- type: rouge
value: 0.1895542893295215
name: ROUGE-L
verified: false
- type: rouge
value: 0.1893813749889601
name: ROUGE-LSUM
verified: false
- type: bertscore
value: 0.8554933660030365
name: bertscore_f1
verified: false
- type: bertscore
value: 0.8578473615646363
name: bertscore_precision
verified: false
- type: bertscore
value: 0.8534188346862793
name: bertscore_recall
verified: false
source:
name: NTREX dataset Benchmark
url: https://huggingface.co/spaces/utrobinmv/TREX_benchmark_en_ru_zh
- name: utrobinmv/t5_translate_en_ru_zh_base_200
results:
- task:
type: translation
name: Translation ru-en
dataset:
name: ntrex_ru-en
type: ntrex
config: ntrex ru-en
split: test
metrics:
- type: sacrebleu
value: 28.575940911021487
name: bleu
verified: false
- type: chrf
value: 54.27996346886896
name: chrf
verified: false
- type: ter
value: 62.494863914873584
name: ter
verified: false
- type: meteor
value: 0.5174833677740809
name: meteor
verified: false
- type: rouge
value: 0.1908317951570274
name: ROUGE-1
verified: false
- type: rouge
value: 0.065555552204933
name: ROUGE-2
verified: false
- type: rouge
value: 0.1895542893295215
name: ROUGE-L
verified: false
- type: rouge
value: 0.1893813749889601
name: ROUGE-LSUM
verified: false
- type: bertscore
value: 0.8554933660030365
name: bertscore_f1
verified: false
- type: bertscore
value: 0.8578473615646363
name: bertscore_precision
verified: false
- type: bertscore
value: 0.8534188346862793
name: bertscore_recall
verified: false
source:
name: NTREX dataset Benchmark
url: https://huggingface.co/spaces/utrobinmv/TREX_benchmark_en_ru_zh
---
# T5 English, Russian and Chinese multilingual machine translation
This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en.
The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to <lang>:'. In this case, the source language may not be specified, in addition, the source text may be multilingual.
Example translate Russian to Chinese
```python
from transformers import T5ForConditionalGeneration, T5Tokenizer
model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024'
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)
prefix = 'translate to zh: '
src_text = prefix + "Цель разработки — предоставить пользователям личного синхронного переводчика."
# translate Russian to Chinese
input_ids = tokenizer(src_text, return_tensors="pt")
generated_tokens = model.generate(**input_ids)
result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
print(result)
#开发的目的是为用户提供个人同步翻译。
```
and Example translate Chinese to Russian
```python
from transformers import T5ForConditionalGeneration, T5Tokenizer
model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024'
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)
prefix = 'translate to ru: '
src_text = prefix + "开发的目的是为用户提供个人同步翻译。"
# translate Russian to Chinese
input_ids = tokenizer(src_text, return_tensors="pt")
generated_tokens = model.generate(**input_ids)
result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
print(result)
#Цель разработки - предоставить пользователям персональный синхронный перевод.
```
##
## Languages covered
Russian (ru_RU), Chinese (zh_CN), English (en_US)
|
BarraHome/zephyr-dpo-4bit | BarraHome | "2024-02-04T02:56:26Z" | 981 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/zephyr-sft",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | "2024-02-04T02:47:31Z" | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/zephyr-sft
---
# Uploaded model
- **Developed by:** BarraHome
- **License:** apache-2.0
- **Finetuned from model :** unsloth/zephyr-sft
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
openbmb/MiniCPM-2B-dpo-bf16-llama-format | openbmb | "2024-04-07T02:26:13Z" | 981 | 12 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"MiniCPM",
"ModelBest",
"THUNLP",
"conversational",
"en",
"zh",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-06T11:25:02Z" | ---
license: other
license_name: gml
license_link: https://github.com/OpenBMB/General-Model-License/blob/main/%E9%80%9A%E7%94%A8%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE-%E6%9D%A5%E6%BA%90%E8%AF%B4%E6%98%8E-%E5%AE%A3%E4%BC%A0%E9%99%90%E5%88%B6-%E5%95%86%E4%B8%9A%E6%8E%88%E6%9D%83.md
language:
- en
- zh
tags:
- MiniCPM
- ModelBest
- THUNLP
---
<div align="center">
<h1>
MiniCPM
</h1>
</div>
<p align="center">
<a href="https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a?pvs=4" target="_blank">MiniCPM 技术报告</a><a href="https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4" target="_blank"> Technical Report</a> |
<a href="https://github.com/OpenBMB/OmniLMM/" target="_blank">OmniLMM 多模态模型 Multi-modal Model</a> |
<a href="https://luca.cn/" target="_blank">CPM-C 千亿模型试用 ~100B Model Trial </a>
</p>
MiniCPM 是面壁与清华大学自然语言处理实验室共同开源的系列端侧语言大模型，主体语言模型 MiniCPM-2B 仅有 24亿（2.4B）的非词嵌入参数量。
- 经过 SFT 后，MiniCPM 在公开综合性评测集上，MiniCPM 与 Mistral-7B相近（中文、数学、代码能力更优），整体性能超越 Llama2-13B、MPT-30B、Falcon-40B 等模型。
- 经过 DPO 后，MiniCPM 在当前最接近用户体感的评测集 MTBench上，MiniCPM-2B 也超越了 Llama2-70B-Chat、Vicuna-33B、Mistral-7B-Instruct-v0.1、Zephyr-7B-alpha 等众多代表性开源大模型。
- 以 MiniCPM-2B 为基础构建端侧多模态大模型 MiniCPM-V，整体性能在同规模模型中实现最佳，超越基于 Phi-2 构建的现有多模态大模型，在部分评测集上达到与 9.6B Qwen-VL-Chat 相当甚至更好的性能。
- 经过 Int4 量化后，MiniCPM 可在手机上进行部署推理，流式输出速度略高于人类说话速度。MiniCPM-V 也首次跑通了多模态大模型在手机上的部署。
- 一张1080/2080可高效参数微调，一张3090/4090可全参数微调，一台机器可持续训练 MiniCPM，二次开发成本较低。
我们将完全开源MiniCPM-2B的模型参数供学术研究和有限商用，以及训练过程中的所有Checkpoint和大部分非专有数据供模型机理研究。
- 基于MiniCPM-2B的指令微调与人类偏好对**MiniCPM-2B-SFT/DPO。**
- 基于MiniCPM-2B的多模态模型**MiniCPM-V**，能力超越基于Phi-2的同参数级别多模态模型**。**
- MiniCPM-2B-SFT/DPO的Int4量化版**MiniCPM-2B-SFT/DPO-Int4。**
- 基于MLC-LLM、LLMFarm开发的MiniCPM手机端程序，**文本及多模态模型均可在手机端进行推理。**
MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings.
- MiniCPM has very close performance compared with Mistral-7B on open-sourced general benchmarks with better ability on Chinese, Mathmetics and Coding after SFT. The overall performance exceeds Llama2-13B, MPT-30B, Falcon-40B, etc.
- After DPO, MiniCPM outperforms Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, Zephyr-7B-alpha, etc. on MTBench.
- MiniCPM-V, based on MiniCPM-2B, achieves the best overall performance among multimodel models of the same scale, surpassing existing multimodal large models built on Phi-2 and achieving performance comparable to or even better than 9.6B Qwen-VL-Chat on some tasks.
- MiniCPM can be deployed and infer on smartphones, and the speed of streaming output is relatively higher than the verbal speed of human. MiniCPM-V is the first multi-modal models that can be deployed on smartphones.
- The cost of developing based on MiniCPM is low. Parameter efficient finetuning can be conducted with a single 1080/2080 GPU and full parameter finetuning can be conducted with a 3090/4090 GPU.
We release all model parameters for research and limited commercial use. We also release all the checkpoint during training and most public training data for research on model mechanism.
- SFT and DPO version based on MiniCPM-2B and human preference: **MiniCPM-2B-SFT/DPO**
- The multi-modal model **MiniCPM-V** based on MiniCPM-2B, which outperforms models with similar size, i.e., Phi-2
- The INT4 quantized version **MiniCPM-2B-SFT/DPO-Int4** based on MiniCPM-2B-SFT/DPO
- Mobile phone application based on MLC-LLM and LLMFarm. Both language model and multimodel model can conduct inference on smartphones.
### 评测结果 Evaluation Results
详细的评测结果位于[github仓库](https://github.com/OpenBMB/MiniCPM?tab=readme-ov-file#%E8%AF%84%E6%B5%8B%E7%BB%93%E6%9E%9C)
Detailed evaluation results are in [github repo](https://github.com/OpenBMB/MiniCPM/blob/main/README-en.md#evaluation-results)
注意：我们发现使用Huggingface生成质量略差于vLLM，因此推荐使用vLLM进行测试。我们正在排查原因。
Notice: We discovered that the quality of Huggingface generation is slightly lower than vLLM, thus benchmarking using vLLM is recommended.
We are investigating the cause now.
### 局限性 Limitations
- 受限于模型规模，模型可能出现幻觉性问题。其中由于DPO模型生成的回复内容更长，更容易出现幻觉。我们也将持续进行MiniCPM模型的迭代改进；
- 为了保证在学术研究用途上模型的通用性，我们未对模型进行任何身份认同训练。同时由于我们用ShareGPT开源语料作为部分训练数据，模型可能会输出类似GPT系列模型的身份认同信息；
- 受限于模型规模，模型的输出受到提示词（prompt）的影响较大，可能多次尝试产生不一致的结果；
- 受限于模型容量，模型的知识记忆较不准确，后续我们将结合RAG方法来增强模型的知识记忆能力。
- Due to limitations in model size, the model may experience hallucinatory issues. As DPO model tend to generate longer response, hallucinations are more likely to occur. We will also continue to iterate and improve the MiniCPM model.
- To ensure the universality of the model for academic research purposes, we did not conduct any identity training on the model. Meanwhile, as we use ShareGPT open-source corpus as part of the training data, the model may output identity information similar to the GPT series models.
- Due to the limitation of model size, the output of the model is greatly influenced by prompt words, which may result in inconsistent results from multiple attempts.
- Due to limited model capacity, the model's knowledge memory is not accurate. In the future, we will combine the RAG method to enhance the model's knowledge memory ability.
## 模型下载 Download
| HuggingFace | ModelScope | WiseModel |
|-------------|------------|-----------|
|[sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16)|[sft-bf16](https://modelscope.cn/models/OpenBMB/miniCPM-bf16)|[sft-bf16](https://wisemodel.cn/models/OpenBMB/miniCPM-bf16)
|[sft-fp32](https://huggingface.co/openbmb/MiniCPM-2B-sft-fp32)|[sft-fp32](https://modelscope.cn/models/OpenBMB/MiniCPM-2B-sft-fp32)|[sft-fp32](https://wisemodel.cn/models/OpenBMB/miniCPM-dpo-fp32)
|[dpo-bf16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16)|[dpo-bf16](https://modelscope.cn/models/OpenBMB/MiniCPM-2B-dpo-bf16/summary)|[dpo-bf16](https://wisemodel.cn/models/OpenBMB/MiniCPM-2B-dpo-bf16)
|[dpo-fp16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-fp16)|[dpo-fp16](https://modelscope.cn/models/OpenBMB/MiniCPM-2B-dpo-fp16/)|[dpo-fp16](https://wisemodel.cn/models/OpenBMB/MiniCPM-2B-dpo-fp16)
|[dpo-fp32](https://huggingface.co/openbmb/MiniCPM-2B-dpo-fp32)|[dpo-fp32](https://modelscope.cn/models/OpenBMB/MiniCPM-2B-dpo-fp32)|[dpo-fp32](https://wisemodel.cn/models/OpenBMB/miniCPM-dpo-fp32)
## 模型使用 Usage
* 安装`transformers>=4.36.0`以及`accelerate`后，运行以下代码
* 注意：需要在`from_pretrained`中明确指明模型的数据类型，否则会引起较大计算误差
* Run the following code after install `transformers>=4.36.0` and `accelerate`
* Warning: It is necessary to specify the data type of the model clearly in 'from_pretrained', otherwise large calculation errors will be caused
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
torch.manual_seed(0)
path = 'openbmb/MiniCPM-2B-dpo-bf16'
tokenizer = AutoTokenizer.from_pretrained(path)
model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map='cuda', trust_remote_code=True)
responds, history = model.chat(tokenizer, "山东省最高的山是哪座山, 它比黄山高还是矮？差距多少？", temperature=0.8, top_p=0.8)
print(responds)
```
* 期望输出 Expected Output
```shell
山东省最高的山是泰山，海拔1545米。
相对于黄山（海拔1864米），泰山海拔较低，相差约319米。
```
## 开源协议 LICENSE
#### 模型协议 Model LICENSE
* 本仓库中代码依照 [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) 协议开源
* MiniCPM 模型权重的使用则需要遵循 [“通用模型许可协议-来源说明-宣传限制-商业授权”](https://github.com/OpenBMB/General-Model-License/blob/main/%E9%80%9A%E7%94%A8%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE-%E6%9D%A5%E6%BA%90%E8%AF%B4%E6%98%8E-%E5%AE%A3%E4%BC%A0%E9%99%90%E5%88%B6-%E5%95%86%E4%B8%9A%E6%8E%88%E6%9D%83.md)。
* MiniCPM 模型权重对学术研究完全开放。
* 如需将模型用于商业用途，请联系[email protected]来获取书面授权，在登记后亦允许免费商业使用。
* This repository is released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
* The usage of MiniCPM model weights must strictly follow [the General Model License (GML)](https://github.com/OpenBMB/General-Model-License/blob/main/%E9%80%9A%E7%94%A8%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE-%E6%9D%A5%E6%BA%90%E8%AF%B4%E6%98%8E-%E5%AE%A3%E4%BC%A0%E9%99%90%E5%88%B6-%E5%95%86%E4%B8%9A%E6%8E%88%E6%9D%83.md).
* The models and weights of MiniCPM are completely free for academic research.
* If you intend to utilize the model for commercial purposes, please reach out to [email protected] to obtain the certificate of authorization.
#### 声明 Statement
* 作为一个语言模型，MiniCPM 通过学习大量的文本来生成内容，但它无法理解、表达个人观点或价值判断，它所输出的任何内容都不代表模型开发者的观点和立场。
* 因此用户在使用 MiniCPM 生成的内容时，应自行负责对其进行评估和验证。
* 如果由于使用 MinCPM 开源模型而导致的任何问题，包括但不限于数据安全问题、公共舆论风险，或模型被误导、滥用、传播或不当利用所带来的任何风险和问题，我们将不承担任何责任。
* As a language model, MiniCPM generates content by learning from a vast amount of text.
* However, it does not possess the ability to comprehend or express personal opinions or value judgments.
* Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers.
* Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own.
<p id="8"></p>
## 工作引用 Citation
* 如果觉得MiniCPM有助于您的工作，请考虑引用下列[技术报告](https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a?pvs=4)
* Please cite our [techinical report](https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4) if you find our work valuable.
```
@inproceedings{minicpm2024,
title={MiniCPM：Unveiling the Potential of End-side Large Language Models},
booktitle={OpenBMB Blog},
year={2024}
}
```
|
Rookie/Llama-3-8B-Instruct-Chinese | Rookie | "2024-04-24T11:17:09Z" | 981 | 27 | transformers | [
"transformers",
"safetensors",
"gguf",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-22T02:55:09Z" | # Llama-3-8B-Instruct-Chinese-chat
Llama-3-8B-Instruct in Chinese 自己微调版本
### 训练可用数据整理
| 数据集 | 介绍 |
|----------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [firefly-train-1.1M](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M) | 包含了23种常见的中文NLP任务的数据，并且构造了许多与中华文化相关的数据，如对联、作诗、文言文翻译、散文、金庸小说等。对于每个任务，由人工书写若干种指令模板，保证数据的高质量与丰富度，数据量为115万。 |
| [moss-003-sft-data](https://huggingface.co/datasets/YeungNLP/moss-003-sft-data) | 由复旦大学MOSS团队开源的中英文多轮对话数据，包含100万+数本。 |
| [school_math_0.25M](https://huggingface.co/datasets/YeungNLP/school_math_0.25M) | 由BELLE项目组开源的数学运算指令数据，包含25万条数问。 |
| [ruozhiba](https://huggingface.co/datasets/LooksJuicy/ruozhiba) | 弱智吧数据问答，据说比较锻炼模型的心智能力。 |
欢迎补充，要求中文且一问一答形式，适合用于提升llama3任务能力的数据集
### [github地址](https://github.com/Rookie1019/Llama-3-8B-Instruct-Chinese.git)
### 推荐微调工具
在此感谢以下项目，提供了许多优秀的中文微调工具，供大家参考：
- Firefly - https://github.com/yangjianxin1/Firefly
- LLaMA-Factory - https://github.com/hiyouga/LLaMA-Factory.git
### Chat版模型下载
- Instruct + 继续中文sft版
- [huggingface地址](https://huggingface.co/Rookie/Llama-3-8B-Instruct-Chinese)
### 模型量化加速、部署
### 模型使用
默认情况下直接运行以下代码即可体验llama3中文对话，请自行修改`model_name_or_path`为你下载的模型路径
```python
from transformers import AutoTokenizer, AutoConfig, AddedToken, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
from dataclasses import dataclass
from typing import Dict
import torch
import copy
## 定义聊天模板
@dataclass
class Template:
template_name:str
system_format: str
user_format: str
assistant_format: str
system: str
stop_word: str
template_dict: Dict[str, Template] = dict()
def register_template(template_name, system_format, user_format, assistant_format, system, stop_word=None):
template_dict[template_name] = Template(
template_name=template_name,
system_format=system_format,
user_format=user_format,
assistant_format=assistant_format,
system=system,
stop_word=stop_word,
)
# 这里的系统提示词是训练时使用的，推理时可以自行尝试修改效果
register_template(
template_name='llama3',
system_format='<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{content}<|eot_id|>',
user_format='<|start_header_id|>user<|end_header_id|>\n\n{content}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n',
assistant_format='{content}<|eot_id|>',
system=None,
stop_word='<|eot_id|>'
)
## 加载模型
def load_model(model_name_or_path, load_in_4bit=False, adapter_name_or_path=None):
if load_in_4bit:
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type="nf4",
llm_int8_threshold=6.0,
llm_int8_has_fp16_weight=False,
)
else:
quantization_config = None
# 加载base model
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
low_cpu_mem_usage=True,
torch_dtype=torch.float16,
device_map='auto',
quantization_config=quantization_config
)
# 加载adapter
if adapter_name_or_path is not None:
model = PeftModel.from_pretrained(model, adapter_name_or_path)
return model
## 加载tokenzier
def load_tokenizer(model_name_or_path):
tokenizer = AutoTokenizer.from_pretrained(
model_name_or_path,
trust_remote_code=True,
use_fast=False
)
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
return tokenizer
## 构建prompt
def build_prompt(tokenizer, template, query, history, system=None):
template_name = template.template_name
system_format = template.system_format
user_format = template.user_format
assistant_format = template.assistant_format
system = system if system is not None else template.system
history.append({"role": 'user', 'message': query})
input_ids = []
# 添加系统信息
if system_format is not None:
if system is not None:
system_text = system_format.format(content=system)
input_ids = tokenizer.encode(system_text, add_special_tokens=False)
# 拼接历史对话
for item in history:
role, message = item['role'], item['message']
if role == 'user':
message = user_format.format(content=message, stop_token=tokenizer.eos_token)
else:
message = assistant_format.format(content=message, stop_token=tokenizer.eos_token)
tokens = tokenizer.encode(message, add_special_tokens=False)
input_ids += tokens
input_ids = torch.tensor([input_ids], dtype=torch.long)
return input_ids
def main():
model_name_or_path = 'NousResearch/Meta-Llama-3-8B'
template_name = 'llama3'
adapter_name_or_path = None
template = template_dict[template_name]
load_in_4bit = False
max_new_tokens = 500
top_p = 0.9
temperature = 0.35
repetition_penalty = 1.1
# 加载模型
print(f'Loading model from: {model_name_or_path}')
print(f'adapter_name_or_path: {adapter_name_or_path}')
model = load_model(
model_name_or_path,
load_in_4bit=load_in_4bit,
adapter_name_or_path=adapter_name_or_path
).eval()
tokenizer = load_tokenizer(model_name_or_path if adapter_name_or_path is None else adapter_name_or_path)
if template.stop_word is None:
template.stop_word = tokenizer.eos_token
stop_token_id = tokenizer.encode(template.stop_word, add_special_tokens=True)
assert len(stop_token_id) == 1
stop_token_id = stop_token_id[0]
history = []
query = input('# User：')
while True:
query = query.strip()
input_ids = build_prompt(tokenizer, template, query, copy.deepcopy(history), system=None).to(model.device)
attention_mask = torch.ones(input_ids.shape,dtype=torch.long,device=model.device)
outputs = model.generate(
input_ids=input_ids, max_new_tokens=max_new_tokens, do_sample=True,
top_p=top_p, temperature=temperature, repetition_penalty=repetition_penalty,
eos_token_id=stop_token_id,
attention_mask=attention_mask,
pad_token_id=tokenizer.eos_token_id
)
outputs = outputs.tolist()[0][len(input_ids[0]):]
response = tokenizer.decode(outputs)
response = response.strip().replace(template.stop_word, "").strip()
# 存储对话历史
history.append({"role": 'user', 'message': query})
history.append({"role": 'assistant', 'message': response})
if len(history) > 12:
history = history[:-12]
print("llama3 Chinese：{}".format(response))
query = input('# User：')
if __name__ == '__main__':
main()
```
### 多轮问答示例
```
User：你是谁
llama3 Chinese：我是一名AI语言模型，我的名字叫MOSS。
User：你会什么
llama3 Chinese：我可以回答问题、提供信息、帮助您完成任务等等。请问您需要我做什么？
User：两千块钱买什么新车好？
llama3 Chinese：两千块钱买一辆新车可能比较困难，因为大多数新车的价格都比这个金额高得多。但是，有一些二手车或者低价新车可能在这个价格范围内，您可以考虑购买这些车辆。但请注意，在购买二手车时，您应该仔细检查车辆的状况，并了解其历史记录，以确保您获得了一个安全可靠的车辆。
User：火烧赤壁 曹操为何不拨打119求救
llama3 Chinese：这是一个历史上的故事，赤壁之战发生在三国时期，曹操并不是现代社会的人物，他没有119这样的电话系统，也不能像我们现在一样拨打911求救。因此，他只能通过其他方式来组织部队和进行战斗。
User：帮我写一个transformer block
llama3 Chinese：当然可以！下面是一个简单的Transformer Block示例：
```python
import torch.nn as nn
import torch
class TransformerBlock(nn.Module):
def __init__(self, d_model, n_heads, dropout=0.1):
super(TransformerBlock, self).__init__()
self.self_attn = MultiHeadAttention(d_model, n_heads)
self.feed_forward = nn.Linear(d_model, d_model)
self.dropout = nn.Dropout(dropout)
def forward(self, x):
# Self-Attention
residual = x
output = self.self_attn(x, x)
output += residual
output = self.dropout(output)
# Feed Forward
residual = output
output = self.feed_forward(output)
output += residual
output = self.dropout(output)
return output
class MultiHeadAttention(nn.Module):
def __init__(self, d_model, n_heads):
super(MultiHeadAttention, self).__init__()
self.d_model = d_model
self.n_heads = n_heads
self.query_linear = nn.Linear(d_model, d_model)
self.key_linear = nn.Linear(d_model, d_model)
self.value_linear = nn.Linear(d_model, d_model)
self.dropout = nn.Dropout(0.1)
def forward(self, query, key, value):
batch_size = query.size(0)
head_dim = self.d_model // self.n_heads
query = self.query_linear(query).view(batch_size, -1, self.n_heads, head_dim)
key = self.key_linear(key).view(batch_size, -1, self.n_heads, head_dim)
value = self.value_linear(value).view(batch_size, -1, self.n_heads, head_dim)
attention_scores = torch.matmul(query.permute(0, 2, 1, 3), key.permute(0, 2, 3, 1)) / math.sqrt(head_dim)
attention_scores = F.softmax(attention_scores, dim=-1)
attention_scores = self.dropout(attention_scores)
output = torch.matmul(attention_scores, value)
output = output.view(batch_size, -1, self.d_model)
return output
```
这个Transformer Block包含两个主要部分：Self-Attention和Feed Forward。Self-Attention使用MultiHeadAttention模块来计算输入序列之间的注意力权重
User：能写歌快速排序吗
llama3 Chinese：当然可以，以下是Python实现的快速排序算法：
```python
def quick_sort(arr):
if len(arr) <= 1:
return arr
pivot = arr[0]
left = [x for x in arr[1:] if x < pivot]
right = [x for x in arr[1:] if x >= pivot]
return quick_sort(left) + [pivot] + quick_sort(right)
```
这个函数接受一个列表作为参数，并返回排好序后的列表。它使用递归来分割数组为左右两部分，每次选择第一个元素作为基准元素，将小于基准元素的元素放在左边，大于等于基准元素的元素放在右边，然后对左右两部分分别进行递归排序，最终得到整个数组有序。
需要注意的是，这种实现方式称为“原地排序”，即在排序过程中不需要额外的存储空间。但是，它的时间复杂度可能会比其他实现方式更高，因为每次都需要创建新的列表来存放子数组。
User：你觉得你还存在哪些缺陷？
llama3 Chinese：作为一个AI语言模型，我可能会存在以下缺陷：
1. 语言理解能力有限：虽然我可以处理大量的文本数据，但是我的语言理解能力仍然受到一定的限制。我可能无法正确理解某些复杂的语境或隐喻。
2. 缺乏人类的情感：虽然我可以模拟人类的语言，但我缺乏真正的人类情感。这意味着我可能无法理解某些情感上的细微差异，或者无法与人类建立深入的关系。
3. 数据偏见：我的训练数据可能存在偏见，这可能导致我的输出也存在偏见。例如，如果我的训练数据中缺少某个群体的信息，那么我可能无法准确地回答该群体相关的问题。
4. 缺乏创造力：虽然我可以生成一些文本，但是我的创造力仍然受到一定的限制。我可能无法像人类一样产生新的想法或创新解决方案。
总之，虽然我是一个强大的工具，但我仍然存在一些缺陷和局限性。
```
|
internlm/internlm2-math-plus-7b | internlm | "2024-06-05T03:43:15Z" | 981 | 9 | transformers | [
"transformers",
"safetensors",
"internlm2",
"text-generation",
"math",
"conversational",
"custom_code",
"en",
"zh",
"arxiv:2402.06332",
"license:other",
"autotrain_compatible",
"region:us"
] | text-generation | "2024-05-24T03:10:48Z" | ---
pipeline_tag: text-generation
license: other
language:
- en
- zh
tags:
- math
---
# InternLM-Math-Plus
<div align="center">
<img src="https://raw.githubusercontent.com/InternLM/InternLM/main/assets/logo.svg" width="200"/>
<div> </div>
<div align="center">
<b><font size="5">InternLM-Math</font></b>
<sup>
<a href="https://internlm.intern-ai.org.cn/">
<i><font size="4">Plus</font></i>
</a>
</sup>
<div> </div>
</div>
State-of-the-art bilingual open-sourced Math reasoning LLMs.
A **solver**, **prover**, **verifier**, **augmentor**.
[💻 Github](https://github.com/InternLM/InternLM-Math) [🤗 Demo](https://huggingface.co/spaces/internlm/internlm2-math-7b)
</div>
# News
- [2024.05.24] We release updated version InternLM2-Math-Plus with 4 sizes and state-of-the-art performances including 1.8B, 7B, 20B, and 8x22B. We improve informal math reasoning performance (chain-of-thought and code-intepreter) and formal math reasoning performance (LEAN 4 translation and LEAN 4 theorem proving) significantly.
- [2024.02.10] We add tech reports and citation reference.
- [2024.01.31] We add MiniF2F results with evaluation codes!
- [2024.01.29] We add checkpoints from ModelScope. Update results about majority voting and Code Intepreter. Tech report is on the way!
- [2024.01.26] We add checkpoints from OpenXLab, which ease Chinese users to download!
# Performance
## Formal Math Reasoning
We evaluate the performance of InternLM2-Math-Plus on formal math reasoning benchmark MiniF2F-test. The evaluation setting is same as Llemma with LEAN 4.
| Models | MiniF2F-test |
| -------------------------------- | ------------ |
| ReProver | 26.5 |
| LLMStep | 27.9 |
| GPT-F | 36.6 |
| HTPS | 41.0 |
| Llemma-7B | 26.2 |
| Llemma-34B | 25.8 |
| InternLM2-Math-7B-Base | 30.3 |
| InternLM2-Math-20B-Base | 29.5 |
| InternLM2-Math-Plus-1.8B | 38.9 |
| InternLM2-Math-Plus-7B | **43.4** |
| InternLM2-Math-Plus-20B | 42.6 |
| InternLM2-Math-Plus-Mixtral8x22B | 37.3 |
## Informal Math Reasoning
We evaluate the performance of InternLM2-Math-Plus on informal math reasoning benchmark MATH and GSM8K. InternLM2-Math-Plus-1.8B outperforms MiniCPM-2B in the smallest size setting. InternLM2-Math-Plus-7B outperforms Deepseek-Math-7B-RL which is the state-of-the-art math reasoning open source model. InternLM2-Math-Plus-Mixtral8x22B achieves 68.5 on MATH (with Python) and 91.8 on GSM8K.
| Model | MATH | MATH-Python | GSM8K |
| -------------------------------- | -------- | ----------- | -------- |
| MiniCPM-2B | 10.2 | - | 53.8 |
| InternLM2-Math-Plus-1.8B | **37.0** | **41.5** | **58.8** |
| InternLM2-Math-7B | 34.6 | 50.9 | 78.1 |
| Deepseek-Math-7B-RL | 51.7 | 58.8 | **88.2** |
| InternLM2-Math-Plus-7B | **53.0** | **59.7** | 85.8 |
| InternLM2-Math-20B | 37.7 | 54.3 | 82.6 |
| InternLM2-Math-Plus-20B | **53.8** | **61.8** | **87.7** |
| Mixtral8x22B-Instruct-v0.1 | 41.8 | - | 78.6 |
| Eurux-8x22B-NCA | 49.0 | - | - |
| InternLM2-Math-Plus-Mixtral8x22B | **58.1** | **68.5** | **91.8** |
We also evaluate models on [MathBench-A](https://github.com/open-compass/MathBench). InternLM2-Math-Plus-Mixtral8x22B has comparable performance compared to Claude 3 Opus.
| Model | Arithmetic | Primary | Middle | High | College | Average |
| -------------------------------- | ---------- | ------- | ------ | ---- | ------- | ------- |
| GPT-4o-0513 | 77.7 | 87.7 | 76.3 | 59.0 | 54.0 | 70.9 |
| Claude 3 Opus | 85.7 | 85.0 | 58.0 | 42.7 | 43.7 | 63.0 |
| Qwen-Max-0428 | 72.3 | 86.3 | 65.0 | 45.0 | 27.3 | 59.2 |
| Qwen-1.5-110B | 70.3 | 82.3 | 64.0 | 47.3 | 28.0 | 58.4 |
| Deepseek-V2 | 82.7 | 89.3 | 59.0 | 39.3 | 29.3 | 59.9 |
| Llama-3-70B-Instruct | 70.3 | 86.0 | 53.0 | 38.7 | 34.7 | 56.5 |
| InternLM2-Math-Plus-Mixtral8x22B | 77.5 | 82.0 | 63.6 | 50.3 | 36.8 | 62.0 |
| InternLM2-Math-20B | 58.7 | 70.0 | 43.7 | 24.7 | 12.7 | 42.0 |
| InternLM2-Math-Plus-20B | 65.8 | 79.7 | 59.5 | 47.6 | 24.8 | 55.5 |
| Llama3-8B-Instruct | 54.7 | 71.0 | 25.0 | 19.0 | 14.0 | 36.7 |
| InternLM2-Math-7B | 53.7 | 67.0 | 41.3 | 18.3 | 8.0 | 37.7 |
| Deepseek-Math-7B-RL | 68.0 | 83.3 | 44.3 | 33.0 | 23.0 | 50.3 |
| InternLM2-Math-Plus-7B | 61.4 | 78.3 | 52.5 | 40.5 | 21.7 | 50.9 |
| MiniCPM-2B | 49.3 | 51.7 | 18.0 | 8.7 | 3.7 | 26.3 |
| InternLM2-Math-Plus-1.8B | 43.0 | 43.3 | 25.4 | 18.9 | 4.7 | 27.1 |
# Citation and Tech Report
```
@misc{ying2024internlmmath,
title={InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning},
author={Huaiyuan Ying and Shuo Zhang and Linyang Li and Zhejian Zhou and Yunfan Shao and Zhaoye Fei and Yichuan Ma and Jiawei Hong and Kuikun Liu and Ziyi Wang and Yudong Wang and Zijian Wu and Shuaibin Li and Fengzhe Zhou and Hongwei Liu and Songyang Zhang and Wenwei Zhang and Hang Yan and Xipeng Qiu and Jiayu Wang and Kai Chen and Dahua Lin},
year={2024},
eprint={2402.06332},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
UBC-NLP/AraT5-base | UBC-NLP | "2024-05-16T17:42:36Z" | 980 | 15 | transformers | [
"transformers",
"pytorch",
"tf",
"t5",
"Arabic T5",
"MSA",
"Twitter",
"Arabic Dialect",
"Arabic Machine Translation",
"Arabic Text Summarization",
"Arabic News Title and Question Generation",
"Arabic Paraphrasing and Transliteration",
"Arabic Code-Switched Translation",
"ar",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | "2022-03-02T23:29:05Z" | ---
language:
- ar
tags:
- Arabic T5
- MSA
- Twitter
- Arabic Dialect
- Arabic Machine Translation
- Arabic Text Summarization
- Arabic News Title and Question Generation
- Arabic Paraphrasing and Transliteration
- Arabic Code-Switched Translation
---
# AraT5-base
# AraT5: Text-to-Text Transformers for Arabic Language Generation
<img src="https://huggingface.co/UBC-NLP/AraT5-base/resolve/main/AraT5_CR_new.png" alt="AraT5" width="45%" height="35%" align="right"/>
This is the repository accompanying our paper [AraT5: Text-to-Text Transformers for Arabic Language Understanding and Generation](https://aclanthology.org/2022.acl-long.47/). In this is the repository we Introduce **AraT5<sub>MSA</sub>**, **AraT5<sub>Tweet</sub>**, and **AraT5**: three powerful Arabic-specific text-to-text Transformer based models;
<span style="color:red"><b>A new version of AraT5 comes out and we recommend using the [AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) instead of this version.</b></span>
---
# How to use AraT5 models
Below is an example for fine-tuning **AraT5-base** for News Title Generation on the Aranews dataset
``` bash
!python run_trainier_seq2seq_huggingface.py \
--learning_rate 5e-5 \
--max_target_length 128 --max_source_length 128 \
--per_device_train_batch_size 8 --per_device_eval_batch_size 8 \
--model_name_or_path "UBC-NLP/AraT5-base" \
--output_dir "/content/AraT5_FT_title_generation" --overwrite_output_dir \
--num_train_epochs 3 \
--train_file "/content/ARGEn_title_genration_sample_train.tsv" \
--validation_file "/content/ARGEn_title_genration_sample_valid.tsv" \
--task "title_generation" --text_column "document" --summary_column "title" \
--load_best_model_at_end --metric_for_best_model "eval_bleu" --greater_is_better True --evaluation_strategy epoch --logging_strategy epoch --predict_with_generate\
--do_train --do_eval
```
For more details about the fine-tuning example, please read this notebook [](https://github.com/UBC-NLP/araT5/blob/main/examples/Fine_tuning_AraT5.ipynb)
In addition, we release the fine-tuned checkpoint of the News Title Generation (NGT) which is described in the paper. The model available at Huggingface ([UBC-NLP/AraT5-base-title-generation](https://huggingface.co/UBC-NLP/AraT5-base-title-generation)).
For more details, please visit our own [GitHub](https://github.com/UBC-NLP/araT5).
# AraT5 Models Checkpoints
AraT5 Pytorch and TensorFlow checkpoints are available on the Huggingface website for direct download and use ```exclusively for research```. ```For commercial use, please contact the authors via email @ (muhammad.mageed[at]ubc[dot]ca).```
| **Model** | **Link** |
|---------|:------------------:|
| **AraT5-base** | [https://huggingface.co/UBC-NLP/AraT5-base](https://huggingface.co/UBC-NLP/AraT5-base) |
| **AraT5-msa-base** | [https://huggingface.co/UBC-NLP/AraT5-msa-base](https://huggingface.co/UBC-NLP/AraT5-msa-base) |
| **AraT5-tweet-base** | [https://huggingface.co/UBC-NLP/AraT5-tweet-base](https://huggingface.co/UBC-NLP/AraT5-tweet-base) |
| **AraT5-msa-small** | [https://huggingface.co/UBC-NLP/AraT5-msa-small](https://huggingface.co/UBC-NLP/AraT5-msa-small) |
| **AraT5-tweet-small**| [https://huggingface.co/UBC-NLP/AraT5-tweet-small](https://huggingface.co/UBC-NLP/AraT5-tweet-small) |
# BibTex
If you use our models for your scientific publication, or if you find the resources in this repository useful, please cite our papers as follows:
**(AraT5-base, AraT5-msa-base, AraT5-tweet-base, AraT5-msa-small, or AraT5-tweet-small)**
```bibtex
@inproceedings{nagoudi2022_arat5,
@inproceedings{nagoudi-etal-2022-arat5,
title = "{A}ra{T}5: Text-to-Text Transformers for {A}rabic Language Generation",
author = "Nagoudi, El Moatez Billah and
Elmadany, AbdelRahim and
Abdul-Mageed, Muhammad",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.47",
pages = "628--647",
abstract = "Transfer learning with a unified Transformer framework (T5) that converts all language problems into a text-to-text format was recently proposed as a simple and effective transfer learning approach. Although a multilingual version of the T5 model (mT5) was also introduced, it is not clear how well it can fare on non-English tasks involving diverse data. To investigate this question, we apply mT5 on a language with a wide variety of dialects{--}Arabic. For evaluation, we introduce a novel benchmark for ARabic language GENeration (ARGEN), covering seven important tasks. For model comparison, we pre-train three powerful Arabic T5-style models and evaluate them on ARGEN. Although pre-trained with {\textasciitilde}49 less data, our new models perform significantly better than mT5 on all ARGEN tasks (in 52 out of 59 test sets) and set several new SOTAs. Our models also establish new SOTA on the recently-proposed, large Arabic language understanding evaluation benchmark ARLUE (Abdul-Mageed et al., 2021). Our new models are publicly available. We also link to ARGEN datasets through our repository: https://github.com/UBC-NLP/araT5.",
}
```
**AraT5v2-base-1024**
``` bibtex
@inproceedings{elmadany-etal-2023-octopus,
title = "Octopus: A Multitask Model and Toolkit for {A}rabic Natural Language Generation",
author = "Elmadany, AbdelRahim and
Nagoudi, El Moatez Billah and
Abdul-Mageed, Muhammad",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.20",
doi = "10.18653/v1/2023.arabicnlp-1.20",
pages = "232--243",
}
```
## Acknowledgments
We gratefully acknowledge support from the Natural Sciences and Engineering Research Council of Canada, the Social Sciences and Humanities Research Council of Canada, Canadian Foundation for Innovation, [ComputeCanada](www.computecanada.ca) and [UBC ARC-Sockeye](https://doi.org/10.14288/SOCKEYE). We also thank the [Google TensorFlow Research Cloud (TFRC)](https://www.tensorflow.org/tfrc) program for providing us with free TPU access.
|
stabilityai/stable-diffusion-2-1-unclip-small | stabilityai | "2023-04-12T15:49:28Z" | 980 | 32 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"text-to-image",
"arxiv:2112.10752",
"arxiv:1910.09700",
"license:openrail++",
"diffusers:StableUnCLIPImg2ImgPipeline",
"region:us"
] | text-to-image | "2023-03-24T16:35:48Z" | ---
license: openrail++
tags:
- stable-diffusion
- text-to-image
pinned: true
---
# Stable Diffusion v2-1-unclip (small) Model Card
This model card focuses on the model associated with the Stable Diffusion v2-1 model, codebase available [here](https://github.com/Stability-AI/stablediffusion).
This `stable-diffusion-2-1-unclip-small` is a finetuned version of Stable Diffusion 2.1, modified to accept (noisy) CLIP image embedding in addition to the text prompt, and can be used to create image variations (Examples) or can be chained with text-to-image CLIP priors. The amount of noise added to the image embedding can be specified via the noise_level (0 means no noise, 1000 full noise).
- Use it with 🧨 [`diffusers`](#examples)
## Model Details
- **Developed by:** Robin Rombach, Patrick Esser
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL)
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([OpenCLIP-ViT/H](https://github.com/mlfoundations/open_clip)).
- **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/).
- **Cite as:**
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
## Examples
Using the [🤗's Diffusers library](https://github.com/huggingface/diffusers) to run Stable Diffusion UnCLIP 2-1-small in a simple and efficient manner.
```bash
pip install diffusers transformers accelerate scipy safetensors
```
Running the pipeline (if you don't swap the scheduler it will run with the default DDIM, in this example we are swapping it to DPMSolverMultistepScheduler):
```python
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
import torch
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1-unclip-small", torch_dtype=torch.float16)
pipe.to("cuda")
# get image
url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/stable_unclip/tarsila_do_amaral.png"
image = load_image(url)
# run image variation
image = pipe(image).images[0]
```
# Uses
## Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
_Note: This section is originally taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), was used for Stable Diffusion v1, but applies in the same way to Stable Diffusion v2_.
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a subset of the large-scale dataset
[LAION-5B](https://laion.ai/blog/laion-5b/), which contains adult, violent and sexual content. To partially mitigate this, we have filtered the dataset using LAION's NFSW detector (see Training section).
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
Stable Diffusion was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
which consists of images that are limited to English descriptions.
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
Stable Diffusion v2 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent.
## Training
**Training Data**
The model developers used the following dataset for training the model:
- LAION-5B and subsets (details below). The training data is further filtered using LAION's NSFW detector, with a "p_unsafe" score of 0.1 (conservative). For more details, please refer to LAION-5B's [NeurIPS 2022](https://openreview.net/forum?id=M3Y74vmsMcY) paper and reviewer discussions on the topic.
## Environmental Impact
**Stable Diffusion v1** **Estimated Emissions**
Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
- **Hardware Type:** A100 PCIe 40GB
- **Hours used:** 200000
- **Cloud Provider:** AWS
- **Compute Region:** US-east
- **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 15000 kg CO2 eq.
## Citation
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
*This model card was written by: Robin Rombach, Patrick Esser and David Ha and is based on the [Stable Diffusion v1](https://github.com/CompVis/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md) and [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).* |
CHE-72/Qwen2-7B-Instruct-Q3_K_M-GGUF | CHE-72 | "2024-06-21T18:53:21Z" | 980 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"region:us"
] | text-generation | "2024-06-21T18:53:00Z" | ---
base_model: Qwen/Qwen2-7B-Instruct
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
# CHE-72/Qwen2-7B-Instruct-Q3_K_M-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2-7B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_M-GGUF --hf-file qwen2-7b-instruct-q3_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_M-GGUF --hf-file qwen2-7b-instruct-q3_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_M-GGUF --hf-file qwen2-7b-instruct-q3_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Qwen2-7B-Instruct-Q3_K_M-GGUF --hf-file qwen2-7b-instruct-q3_k_m.gguf -c 2048
```
|
ab-ai/pii_model_based_on_distilbert | ab-ai | "2024-03-21T12:53:17Z" | 979 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"token-classification",
"pii-detection",
"en",
"dataset:custom_dataset",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2024-03-15T19:22:28Z" | ---
language: en
tags:
- token-classification
- pii-detection
license: apache-2.0
datasets:
- custom_dataset
---
# Model Name
PII Detection Model Based on DistilBERT
## Model description
This model is a token classification model trained for detecting personally identifiable information (PII) entities such as names, addresses, dates of birth, credit card numbers, etc. The model is based on the DistilBERT architecture and has been fine-tuned on a custom dataset for PII detection.
## Intended use
The model is intended to be used for automatically identifying and extracting PII entities from text data. It can be incorporated into data processing pipelines for tasks such as data anonymization, redaction, compliance with privacy regulations, etc.
## Evaluation results
The model's performance was evaluated on a held-out validation set using the following metrics:
- Precision: 94%
- Recall: 96%
- F1 Score: 95%
- Accuracy: 99%
## Limitations and bias
- The model's performance may vary depending on the quality and diversity of the input data.
- It may exhibit biases present in the training data, such as overrepresentation or underrepresentation of certain demographic groups or types of PII.
- The model may struggle with detecting PII entities in noisy or poorly formatted text.
## Ethical considerations
- Care should be taken when deploying the model in production to ensure that it does not inadvertently expose sensitive information or violate individuals' privacy rights.
- Data used to train and evaluate the model should be handled with caution to avoid the risk of exposing PII.
- Regular monitoring and auditing of the model's predictions may be necessary to identify and mitigate any potential biases or errors.
## Model Training and Evaluation Results
| Epoch | Training Loss | Validation Loss | Precision | Recall | F1 Score | Accuracy |
|-------|---------------|-----------------|-----------|--------|----------|----------|
| 1 | 0.047 | 0.051537 | 91.35% | 95.23% | 93.25% | 98.56% |
| 2 | 0.0307 | 0.043873 | 93.27% | 96.10% | 94.66% | 98.75% |
| 3 | 0.0208 | 0.04702 | 91.83% | 95.49% | 93.62% | 98.54% |
| 4 | 0.0147 | 0.046979 | 93.27% | 94.97% | 94.11% | 98.77% |
| 5 | 0.0094 | 0.057863 | 93.41% | 95.92% | 94.65% | 98.70% |
## Authors
- [email protected]
|
MaziyarPanahi/Multi_verse_modelM7-7B-GGUF | MaziyarPanahi | "2024-04-01T04:28:38Z" | 979 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:liminerity/M7-7b",
"base_model:ammarali32/multi_verse_model",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:automerger/Multi_verse_modelM7-7B"
] | text-generation | "2024-04-01T04:05:29Z" | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- mergekit
- merge
- conversational
- arxiv:2311.03099
- arxiv:2306.01708
- base_model:liminerity/M7-7b
- base_model:ammarali32/multi_verse_model
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: Multi_verse_modelM7-7B-GGUF
base_model: automerger/Multi_verse_modelM7-7B
inference: false
model_creator: automerger
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/Multi_verse_modelM7-7B-GGUF](https://huggingface.co/MaziyarPanahi/Multi_verse_modelM7-7B-GGUF)
- Model creator: [automerger](https://huggingface.co/automerger)
- Original model: [automerger/Multi_verse_modelM7-7B](https://huggingface.co/automerger/Multi_verse_modelM7-7B)
## Description
[MaziyarPanahi/Multi_verse_modelM7-7B-GGUF](https://huggingface.co/MaziyarPanahi/Multi_verse_modelM7-7B-GGUF) contains GGUF format model files for [automerger/Multi_verse_modelM7-7B](https://huggingface.co/automerger/Multi_verse_modelM7-7B).
## How to use
Thanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
### Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: [MaziyarPanahi/Multi_verse_modelM7-7B-GGUF](https://huggingface.co/MaziyarPanahi/Multi_verse_modelM7-7B-GGUF) and below it, a specific filename to download, such as: Multi_verse_modelM7-7B-GGUF.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download MaziyarPanahi/Multi_verse_modelM7-7B-GGUF Multi_verse_modelM7-7B.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
</details>
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download [MaziyarPanahi/Multi_verse_modelM7-7B-GGUF](https://huggingface.co/MaziyarPanahi/Multi_verse_modelM7-7B-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/Multi_verse_modelM7-7B-GGUF Multi_verse_modelM7-7B.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m Multi_verse_modelM7-7B.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20-%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://github.com/abetlen/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./Multi_verse_modelM7-7B.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./Multi_verse_modelM7-7B.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) |
BLURPLETESTS/L3-8B-Chara-v1-Alpha-Q5_K_M_imat_GGUF | BLURPLETESTS | "2024-07-01T06:38:45Z" | 979 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"base_model:Sao10K/L3-8B-Chara-v1-Alpha",
"license:cc-by-nc-4.0",
"region:us"
] | null | "2024-07-01T06:38:19Z" | ---
base_model: Sao10K/L3-8B-Chara-v1-Alpha
language:
- en
license: cc-by-nc-4.0
tags:
- llama-cpp
- gguf-my-repo
---
# BLURPLETESTS/L3-8B-Chara-v1-Alpha-Q5_K_M-GGUF
This model was converted to GGUF format from [`Sao10K/L3-8B-Chara-v1-Alpha`](https://huggingface.co/Sao10K/L3-8B-Chara-v1-Alpha) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Sao10K/L3-8B-Chara-v1-Alpha) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo BLURPLETESTS/L3-8B-Chara-v1-Alpha-Q5_K_M-GGUF --hf-file l3-8b-chara-v1-alpha-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo BLURPLETESTS/L3-8B-Chara-v1-Alpha-Q5_K_M-GGUF --hf-file l3-8b-chara-v1-alpha-q5_k_m-imat.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo BLURPLETESTS/L3-8B-Chara-v1-Alpha-Q5_K_M-GGUF --hf-file l3-8b-chara-v1-alpha-q5_k_m-imat.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo BLURPLETESTS/L3-8B-Chara-v1-Alpha-Q5_K_M-GGUF --hf-file l3-8b-chara-v1-alpha-q5_k_m-imat.gguf -c 2048
```
|
HamidRezaAttar/gpt2-product-description-generator | HamidRezaAttar | "2024-06-03T11:17:25Z" | 978 | 14 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"en",
"arxiv:1706.03762",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-03-02T23:29:04Z" | ---
language: en
tags:
- text-generation
license: apache-2.0
widget:
- text: "Maximize your bedroom space without sacrificing style with the storage bed."
- text: "Handcrafted of solid acacia in weathered gray, our round Jozy drop-leaf dining table is a space-saving."
- text: "Our plush and luxurious Emmett modular sofa brings custom comfort to your living space."
---
## GPT2-Home
This model is fine-tuned using GPT-2 on amazon home products metadata.
It can generate descriptions for your **home** products by getting a text prompt.
https://github.com/HamidRezaAttar/GPT2-Home
### Model description
[GPT-2](https://openai.com/blog/better-language-models/) is a large [transformer](https://arxiv.org/abs/1706.03762)-based language model with 1.5 billion parameters, trained on a dataset of 8 million web pages. GPT-2 is trained with a simple objective: predict the next word, given all of the previous words within some text. The diversity of the dataset causes this simple goal to contain naturally occurring demonstrations of many tasks across diverse domains. GPT-2 is a direct scale-up of GPT, with more than 10X the parameters and trained on more than 10X the amount of data.
### Live Demo
For testing model with special configuration, please visit [Demo](https://huggingface.co/spaces/HamidRezaAttar/gpt2-home)
### Blog Post
For more detailed information about project development please refer to my [blog post](https://hamidrezaattar.github.io/blog/markdown/2022/02/17/gpt2-home.html).
### How to use
For best experience and clean outputs, you can use Live Demo mentioned above, also you can use the notebook mentioned in my [GitHub](https://github.com/HamidRezaAttar/GPT2-Home)
You can use this model directly with a pipeline for text generation.
```python
>>> from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
>>> tokenizer = AutoTokenizer.from_pretrained("HamidRezaAttar/gpt2-product-description-generator")
>>> model = AutoModelForCausalLM.from_pretrained("HamidRezaAttar/gpt2-product-description-generator")
>>> generator = pipeline('text-generation', model, tokenizer=tokenizer, config={'max_length':100})
>>> generated_text = generator("This bed is very comfortable.")
```
### Citation info
```bibtex
@misc{GPT2-Home,
author = {HamidReza Fatollah Zadeh Attar},
title = {GPT2-Home the English home product description generator},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/HamidRezaAttar/GPT2-Home}},
}
```
|
imvladikon/general_character_bert | imvladikon | "2022-01-30T11:35:11Z" | 978 | 3 | transformers | [
"transformers",
"pytorch",
"bert",
"language model",
"en",
"dataset:wikipedia",
"dataset:openwebtext",
"arxiv:2010.10392",
"endpoints_compatible",
"region:us"
] | null | "2022-03-02T23:29:05Z" | ---
language:
- en
tags:
- language model
datasets:
- wikipedia
- openwebtext
---
Pretrained general_character_bert model
from the ['CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters' El Boukkouri H., et al., 2020](https://github.com/helboukkouri/character-bert)
```
@inproceedings{el-boukkouri-etal-2020-characterbert,
title = "{C}haracter{BERT}: Reconciling {ELM}o and {BERT} for Word-Level Open-Vocabulary Representations From Characters",
author = "El Boukkouri, Hicham and
Ferret, Olivier and
Lavergne, Thomas and
Noji, Hiroshi and
Zweigenbaum, Pierre and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year={2020},
eprint={2010.10392},
archivePrefix={arXiv},
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.coling-main.609",
doi = "10.18653/v1/2020.coling-main.609",
pages = "6903--6915",
abstract = "Due to the compelling improvements brought by BERT, many recent representation models adopted the Transformer architecture as their main building block, consequently inheriting the wordpiece tokenization system despite it not being intrinsically linked to the notion of Transformers. While this system is thought to achieve a good balance between the flexibility of characters and the efficiency of full words, using predefined wordpiece vocabularies from the general domain is not always suitable, especially when building models for specialized domains (e.g., the medical domain). Moreover, adopting a wordpiece tokenization shifts the focus from the word level to the subword level, making the models conceptually more complex and arguably less convenient in practice. For these reasons, we propose CharacterBERT, a new variant of BERT that drops the wordpiece system altogether and uses a Character-CNN module instead to represent entire words by consulting their characters. We show that this new model improves the performance of BERT on a variety of medical domain tasks while at the same time producing robust, word-level, and open-vocabulary representations.",
}
``` |
timm/resnet101d.ra2_in1k | timm | "2024-02-10T23:40:02Z" | 978 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1512.03385",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-05T18:25:53Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnet101d.ra2_in1k
A ResNet-D image classification model.
This model features:
* ReLU activations
* 3-layer stem of 3x3 convolutions with pooling
* 2x2 average pool + 1x1 convolution shortcut downsample
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* RandAugment `RA2` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476).
* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
* Step (exponential decay w/ staircase) LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 44.6
- GMACs: 10.5
- Activations (M): 22.3
- Image size: train = 256 x 256, test = 320 x 320
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resnet101d.ra2_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet101d.ra2_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 128, 128])
# torch.Size([1, 256, 64, 64])
# torch.Size([1, 512, 32, 32])
# torch.Size([1, 1024, 16, 16])
# torch.Size([1, 2048, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resnet101d.ra2_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@article{He2018BagOT,
title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
pages={558-567}
}
```
|
predibase/gsm8k | predibase | "2024-02-21T19:13:55Z" | 978 | 2 | peft | [
"peft",
"safetensors",
"text-generation",
"base_model:mistralai/Mistral-7B-v0.1",
"region:us"
] | text-generation | "2024-02-19T19:10:41Z" | ---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
pipeline_tag: text-generation
---
Description: Grade school math problems\
Original dataset: https://huggingface.co/datasets/gsm8k \
---\
Try querying this adapter for free in Lora Land at https://predibase.com/lora-land! \
The adapter_category is STEM and the name is Grade School Math (gsm8k)\
---\
Sample input: Please answer the following question: James decides to run 3 sprints 3 times a week. He runs 60 meters each sprint. How many total meters does he run a week?\nAnswer:\
---\
Sample output: He runs 3*3=<<3*3=9>>9 sprints a week
He runs 60*9=<<60*9=540>>540 meters a week
#### 540\
---\
Try using this adapter yourself!
```
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mistral-7B-v0.1"
peft_model_id = "predibase/gsm8k"
model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)
``` |
second-state/E5-Mistral-7B-Instruct-Embedding-GGUF | second-state | "2024-07-01T03:20:13Z" | 978 | 5 | transformers | [
"transformers",
"gguf",
"mistral",
"feature-extraction",
"en",
"base_model:intfloat/e5-mistral-7b-instruct",
"license:mit",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | feature-extraction | "2024-03-14T06:24:50Z" | ---
base_model: intfloat/e5-mistral-7b-instruct
license: mit
model_creator: intfloat
quantized_by: Second State Inc.
language: en
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# E5-Mistral-7B-Instruct-Embedding-GGUF
## Original Model
[intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct)
## Run with LlamaEdge
- LlamaEdge version: [v0.8.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.2) and above
- Prompt template
- Prompt type: `embedding`
- Context size: `4096`
- Run as LlamaEdge service
```bash
wasmedge --dir .:. --nn-preload default:GGML:AUTO:e5-mistral-7b-instruct-Q5_K_M.gguf \
llama-api-server.wasm \
--prompt-template embedding \
--ctx-size 4096 \
--model-name e5-mistral-7b-instruct
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [e5-mistral-7b-instruct-Q2_K.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q2_K.gguf) | Q2_K | 2 | 2.72 GB| smallest, significant quality loss - not recommended for most purposes |
| [e5-mistral-7b-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss |
| [e5-mistral-7b-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss |
| [e5-mistral-7b-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss |
| [e5-mistral-7b-instruct-Q4_0.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [e5-mistral-7b-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended |
| [e5-mistral-7b-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss |
| [e5-mistral-7b-instruct-Q5_0.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [e5-mistral-7b-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended |
| [e5-mistral-7b-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended |
| [e5-mistral-7b-instruct-Q6_K.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss |
| [e5-mistral-7b-instruct-Q8_0.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-Q8_0.gguf) | Q8_0 | 8 | 7.7 GB| very large, extremely low quality loss - not recommended |
| [e5-mistral-7b-instruct-f16.gguf](https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF/blob/main/e5-mistral-7b-instruct-f16.gguf) | f16 | 8 | 14.5 GB| very large, extremely low quality loss - not recommended |
*Quantized with llama.cpp b2334*
|
ShleeSSU/Scoring_Korean_Narrative_Sentences | ShleeSSU | "2024-05-21T06:54:34Z" | 978 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2024-05-21T06:53:29Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
DiscoResearch/Llama3-German-8B-32k | DiscoResearch | "2024-05-29T11:36:19Z" | 978 | 9 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"de",
"arxiv:2404.10830",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-24T07:31:58Z" | ---
license: llama3
language:
- de
library_name: transformers
---
# Llama3-German-8B-32k (version 0.1)
This version of the model refers to the long-context extension version described [below](https://huggingface.co/DiscoResearch/Llama3-German-8B-32k#long-context-extension)
Llama3-German-8B-v0.1 is a large language model based on [Meta's Llama3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B). It is specialized for the German language through continuous pretraining on 65 billion high-quality tokens, similar to previous [LeoLM](https://huggingface.co/LeoLM) or [Occiglot](https://huggingface.co/collections/occiglot/occiglot-eu5-7b-v01-65dbed502a6348b052695e01) models.
Llama3 itself was trained on 15T tokens, of which only <1T were multilingual, resulting in suboptimal performance in German with reduced linguistic capabilities and frequent grammatical errors, motivating the necessity for continued pretraining. Benchmark results on our model show minimal degradation in English performance, despite the absence of replay during training. Importantly, Llama3-German-8B-v0.1 demonstrates strong improvements in German, particularly on the Hellaswag benchmark, which measures linguistic understanding and general reasoning.
[DiscoResearch/Llama3-German-8B-v0.1](https://huggingface.co/collections/DiscoResearch/discoleo-8b-llama3-for-german-6650527496c0fafefd4c9729) is the result of a joint effort between [DiscoResearch](https://huggingface.co/DiscoResearch) and [Occiglot](https://huggingface.co/occiglot) with support from the [DFKI](https://www.dfki.de/web/) (German Research Center for Artificial Intelligence) and [hessian.Ai](https://hessian.ai). Occiglot kindly handled data preprocessing, filtering, and deduplication as part of their latest [dataset release](https://huggingface.co/datasets/occiglot/occiglot-fineweb-v0.5), as well as sharing their compute allocation at hessian.Ai's 42 Supercomputer.
## How to use
This is a base model and should probably be subject to finetuning before use. See our [collection](https://huggingface.co/collections/DiscoResearch/discoleo-8b-llama3-for-german-6650527496c0fafefd4c9729) for various finetuned and long-context versions.
## Model Training and Hyperparameters
The model was trained on 128 GPUs on [hessian.Ai 42](hessian.ai) for ~60 hours. See detailed hyperparameters below.
| Parameter | Value |
|-------------------|-----------------------------------|
| Sequence Length | 8192 tokens |
| Learning Rate | 1.5e-5 to 1.5e-6 (cosine schedule)|
| Batch Size | 4194304 (512*8192) tokens |
| Micro Batch Size | 4*8192 tokens |
| Training Steps | 15500 |
| Warmup Steps | 155 (1%) |
| Weight Decay | 0.05 |
| Optimizer | AdamW |
## Data Collection and Preprocessing
For pre-training, we used 65B German tokens from the [occiglot-fineweb-0.5](https://huggingface.co/datasets/occiglot/occiglot-fineweb-v0.5) dataset.
The data comprises multiple curated datasets from [LLM-Datasets](https://github.com/malteos/llm-datasets) as well as 12 [Common-Crawl](https://commoncrawl.org) releases that were processed with [OSCAR's Ungoliant pipeline](https://github.com/oscar-project/ungoliant).
All data was further filtered with a set of language-specific filters based on [Huggingface's fine-web](https://github.com/huggingface/datatrove/blob/main/examples/fineweb.py) and globally deduplicated.
For more information please refer to the [dataset card](https://huggingface.co/datasets/occiglot/occiglot-fineweb-v0.5) and corresponding [blog-post](https://occiglot.eu/posts/occiglot-fineweb/).
## Evaluation and Results
We evaluated the model using a suite of common English Benchmarks and their German counterparts with [GermanBench](https://github.com/bjoernpl/GermanBenchmark).
The following figure shows the benchmark results in comparison to the base model [meta-llama/Meta-Llama3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) and two different hyperparameter configurations.
We swept different learning rates to identify a well-working setup. The final released model is the 1.5e-5 lr version.
Find the detailed benchmark scores for the base and long-context models in this table.
| Model | truthful_qa_de | truthfulqa_mc | arc_challenge | arc_challenge_de | hellaswag | hellaswag_de | MMLU | MMLU-DE | mean |
|--------------------------------------|----------------|---------------|---------------|------------------|-----------|--------------|--------|---------|------------|
| DiscoResearch/Llama3-German-8B | **0.49499** | 0.44838 | 0.55802 | **0.49829** | 0.79924 | **0.65395** | 0.62240| **0.54413** | **0.57743** |
| DiscoResearch/Llama3-German-8B-32k | 0.48920 | **0.45138** | 0.54437 | 0.49232 | 0.79078 | 0.64310 | 0.58774| 0.47971 | 0.55982 |
| meta-llama/Meta-Llama-3-8B-Instruct | 0.47498 | 0.43923 | **0.59642** | 0.47952 | **0.82025**| 0.60008 | **0.66658**| 0.53541 | 0.57656 |
## Long-Context Extension
In addition to the base model, we release a long-context version of Llama3-German-8B ([DiscoResearch/Llama3-German-8B-32k](https://huggingface.co/DiscoResearch/Llama3-German-8B-32k) capable of processing context lengths up to 65k tokens. This variant was trained on an additional 100 million tokens at 32k context length, using a rope_theta value of `1.5e6` and a learning rate of `1.5e-5` with a batch size of `256*8192` tokens and otherwise equal hyperparameters to the base model.
## Instruction Tuning
We also provide an instruction-tuned version: [DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1), utilizing the DiscoLM German dataset for fine-tuning (also available as a long-context model at [DiscoResearch/Llama3-DiscoLeo-Instruct-8B-32k-v0.1](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1)).
Find more details in the respective model cards. Also check out our experimental merge ([DiscoResearch/Llama3-DiscoLeo-8B-DARE-Experimental](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-8B-DARE-Experimental)) between [meta-llama/Meta-Llama3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) and our finetuned model in an attempt to keep the extraordinary capabilities of Llama3-Instruct and add exceptional German skills.
## Document Packing
We employed a more intelligent document packing strategy based on the ["Fewer Truncations Improve Language Modeling" paper by Ding et al.](https://arxiv.org/abs/2404.10830v2), using the first-fit-decreasing algorithm to pack documents into batches without truncation.
We packed our data in chunks of 10000 documents for more efficient processing while maintaining >99% packing efficiency. Documents longer than the sequence length are split into chunks of sequence length.
This approach results in overall higher benchmark scores when training on the same data with equal hyperparameters. The following numbers are from initial experiments with `3e-5 lr` and 12k steps and show improvements comparable to those shown in the original paper.
| Task | Naive Packing | Fewer Truncations Packing | Percentage Increase |
|-------------------|---------------|---------------------------|---------------------|
| truthfulqa_mc | 0.452648 | 0.467687 | 3.32% |
| arc_challenge | 0.517918 | 0.528157 | 1.98% |
| truthful_qa_de | 0.485529 | 0.492979 | 1.53% |
| arc_challenge_de | 0.480375 | 0.493174 | 2.66% |
| hellaswag | 0.776041 | 0.773352 | -0.35% |
| hellaswag_de | 0.655248 | 0.653356 | -0.29% |
| MMLU | 0.573719 | 0.579802 | 1.06% |
| MMLU-DE | 0.504509 | 0.503863 | -0.13% |
The following is our simple implementation of the first-fit-decreasing algorithm described in the paper.
```python
def pack_documents(tokenized_documents):
# Sort documents by their length in descending order
sorted_docs = sorted(tokenized_documents, key=len, reverse=True)
# Initialize bins
bins = []
# Function to find the first bin that can accommodate the document
def find_bin(doc):
for b in bins:
if sum(len(d) for d in b) + len(doc) <= 8192:
return b
return None
# Place each document in the first available bin or create a new bin
for doc in sorted_docs:
target_bin = find_bin(doc)
if target_bin is not None:
target_bin.append(doc)
else:
# Create a new bin with this document if no suitable bin is found
bins.append([doc])
# Return results
return bins
```
## Model Configurations
We release DiscoLeo-8B in the following configurations:
1. [Base model with continued pretraining](https://huggingface.co/DiscoResearch/Llama3-German-8B)
2. [Long-context version (32k context length)](https://huggingface.co/DiscoResearch/Llama3-German-8B-32k)
3. [Instruction-tuned version of the base model](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1)
4. [Instruction-tuned version of the long-context model](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-32k-v0.1)
5. [Experimental `DARE-TIES` Merge with Llama3-Instruct](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-8B-DARE-Experimental)
6. [Collection of Quantized versions](https://huggingface.co/collections/DiscoResearch/discoleo-8b-quants-6651bcf8f72c9a37ce485d42)
## How to use:
Here's how to use the model with transformers:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
device="cuda"
model = AutoModelForCausalLM.from_pretrained(
"DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1")
prompt = "Schreibe ein Essay über die Bedeutung der Energiewende für Deutschlands Wirtschaft"
messages = [
{"role": "system", "content": "Du bist ein hilfreicher Assistent."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## Acknowledgements
The model was trained and evaluated by [Björn Plüster](https://huggingface.co/bjoernp) ([DiscoResearch](https://huggingface.co/DiscoResearch), [ellamind](https://ellamind.com)) with data preparation and project supervision by [Manuel Brack](http://manuel-brack.eu) ([DFKI](https://www.dfki.de/web/), [TU-Darmstadt](https://www.tu-darmstadt.de/)). Initial work on dataset collection and curation was performed by [Malte Ostendorff](https://ostendorff.org) and [Pedro Ortiz Suarez](https://portizs.eu). Instruction tuning was done with the DiscoLM German dataset created by [Jan-Philipp Harries](https://huggingface.co/jphme) and [Daniel Auras](https://huggingface.co/rasdani) ([DiscoResearch](https://huggingface.co/DiscoResearch), [ellamind](https://ellamind.com)). We extend our gratitude to [LAION](https://laion.ai/) and friends, especially [Christoph Schuhmann](https://entwickler.de/experten/christoph-schuhmann) and [Jenia Jitsev](https://huggingface.co/JJitsev), for initiating this collaboration.
The model training was supported by a compute grant at the [42 supercomputer](https://hessian.ai/) which is a central component in the development of [hessian AI](https://hessian.ai/), the [AI Innovation Lab](https://hessian.ai/infrastructure/ai-innovationlab/) (funded by the [Hessian Ministry of Higher Education, Research and the Art (HMWK)](https://wissenschaft.hessen.de) & the [Hessian Ministry of the Interior, for Security and Homeland Security (HMinD)](https://innen.hessen.de)) and the [AI Service Centers](https://hessian.ai/infrastructure/ai-service-centre/) (funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)).
The curation of the training data is partially funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)
through the project [OpenGPT-X](https://opengpt-x.de/en/) (project no. 68GX21007D).
|
SicariusSicariiStuff/Zion_Alpha_Instruction_Tuned_SLERP | SicariusSicariiStuff | "2024-06-10T01:25:36Z" | 978 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-09T21:10:58Z" | ---
language:
- en
license: apache-2.0
---
<div align="center">
<b style="font-size: 40px;">Zion_Alpha_Instruction_Tuned_SLERP</b>
</div>
<img src="https://i.imgur.com/e1LEQ18.png" alt="Zion_Alpha_Instruction_Tuned_SLERP" style="width: 50%; min-width: 400px; display: block; margin: auto;">
# Model Details
Zion_Alpha is the first **REAL** Hebrew model in the world. This version WAS fine tuned for tasks. I did the finetune using SOTA techniques and using my insights from years of underwater basket weaving. If you wanna offer me a job, just add me on Facebook.
# Another world record broken by Zion_Alpha!
On **June 10th, 2024**, this model achieved the **highest sentiment analysis score in the world** for Hebrew LLMs, with an impressive **70.3**, surpassing even a **35B** model that's five times its size!
<div align="center">
<img src="https://i.imgur.com/yg6CJoz.png" alt="Zion_Alpha SNLI Score" style="width: 80%; min-width: 700px; display: block; margin: auto;">
</div>
# Future Plans
My previous LLM, Zion_Alpha, set a world record on Hugging Face by achieving the highest SNLI score for Hebrew open LLMs at 84.05. The current model, a SLERP merge, achieved a lower SNLI score but still surprised everyone by securing the highest sentiment analysis score of 70.3. This demonstrates significant untapped potential in optimizing the training process, showing that 7B models can deliver far more performance in Hebrew than previously thought possible. This will be my last Hebrew model for a while, as I have other adventures to pursue.
# Looking for Sponsors
Since all my work is done on-premises, I am constrained by my current hardware. I would greatly appreciate any support in acquiring an A6000, which would enable me to train significantly larger models much faster.
# Papers?
Maybe. We'll see. No promises here 🤓
# Contact Details
I'm not great at self-marketing (to say the least) and don't have any social media accounts. If you'd like to reach out to me, you can email me at [email protected]. Please note that this email might receive more messages than I can handle, so I apologize in advance if I can't respond to everyone.
# Versions and QUANTS
- Base model: [FP16](https://huggingface.co/SicariusSicariiStuff/Zion_Alpha)
- Instruction tuned: [FP16](https://huggingface.co/SicariusSicariiStuff/Zion_Alpha_Instruction_Tuned) | [GGUF](https://huggingface.co/SicariusSicariiStuff/Zion_Alpha_Instruction_Tuned_GGUF)
# Model architecture
Based on Mistral 7B. I didn't even bother to alter the tokenizer.
# The recommended prompt setting is Debug-deterministic:
```
temperature: 1
top_p: 1
top_k: 1
typical_p: 1
min_p: 1
repetition_penalty: 1
```
# The recommended instruction template is Mistral:
```
{%- for message in messages %}
{%- if message['role'] == 'system' -%}
{{- message['content'] -}}
{%- else -%}
{%- if message['role'] == 'user' -%}
{{-'[INST] ' + message['content'].rstrip() + ' [/INST]'-}}
{%- else -%}
{{-'' + message['content'] + '</s>' -}}
{%- endif -%}
{%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt -%}
{{-''-}}
{%- endif -%}
```
# English to hebrew example:
<div align="center">
<b style="font-size: 40px;">Zion_Alpha English to Hebrew example</b>
</div>
<img src="https://i.imgur.com/JnTuawF.png" alt="Zion_Alpha" style="width: 40%; min-width: 600px; display: block; margin: auto;">
# English to hebrew example:
<div align="center">
<b style="font-size: 40px;">Zion_Alpha Hebrew to English example</b>
</div>
<img src="https://i.imgur.com/Wm2igLJ.png" alt="Zion_Alpha" style="width: 40%; min-width: 600px; display: block; margin: auto;">
<div align="center">
<b style="font-size: 30px;">Unscripted video: live zero shot demonstration at story writing capabilities in Hebrew</b>
[](https://www.youtube.com/watch?v=YYKeovnS0do)
</div>
<div align="center">
<b style="font-size: 30px;">Zion_Alpha VS Mistral 'Hebrew' Live & unscripted in real time</b>
[](https://www.youtube.com/watch?v=DQFtx8M2txc)
</div>
<div align="center">
<b style="font-size: 30px;">Zion_Alpha VS Mistral 'Hebrew' Live & unscripted in real time Long text translation</b>
[](https://www.youtube.com/watch?v=w5fz3Ot6tH8)
</div>
### History
The model was originally trained about 2 month after Mistral (v0.1) was released.
As of 04 June 2024, Zion_Alpha got the **Highest SNLI score in the world** among open source models in Hebrew, surpassing most of the models by a huge margin. (**84.05** score)
<img src="https://i.imgur.com/7HokS5w.png" alt="Zion_Alpha SNLI Score" style="width: 80%; min-width: 700px; display: block; margin: auto;">
### Support
<img src="https://i.imgur.com/0lHHN95.png" alt="GPUs too expensive" style="width: 10%; min-width: 100px; display: block; margin: left;">
- [My Ko-fi page](https://ko-fi.com/sicarius) ALL donations will go for research resources and compute, every bit counts 🙏🏻
- [My Patreon](https://patreon.com/TenebraAI) ALL donations will go for research resources and compute, every bit counts 🙏🏻
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.