Remove hmp from config and README
#1
by
jwieczorekhabana
- opened
- README.md +3 -6
- gaudi_config.json +1 -46
README.md
CHANGED
@@ -13,16 +13,13 @@ This model only contains the `GaudiConfig` file for running **Stable Diffusion v
|
|
13 |
**This model contains no model weights, only a GaudiConfig.**
|
14 |
|
15 |
This enables to specify:
|
16 |
-
- `
|
17 |
-
- `hmp_opt_level`: optimization level for HMP, see [here](https://docs.habana.ai/en/latest/PyTorch/PyTorch_Mixed_Precision/PT_Mixed_Precision.html#configuration-options) for a detailed explanation
|
18 |
-
- `hmp_bf16_ops`: list of operators that should run in bf16
|
19 |
-
- `hmp_fp32_ops`: list of operators that should run in fp32
|
20 |
-
- `hmp_is_verbose`: verbosity
|
21 |
|
22 |
## Usage
|
23 |
|
24 |
The `GaudiStableDiffusionPipeline` (`GaudiDDIMScheduler`) is instantiated the same way as the `StableDiffusionPipeline` (`DDIMScheduler`) in the 🤗 Diffusers library.
|
25 |
-
The only difference is that there are a few new training arguments specific to HPUs
|
|
|
26 |
|
27 |
Here is an example with one prompt:
|
28 |
```python
|
|
|
13 |
**This model contains no model weights, only a GaudiConfig.**
|
14 |
|
15 |
This enables to specify:
|
16 |
+
- `use_torch_autocast`: whether to use Torch Autocast for managing mixed precision
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Usage
|
19 |
|
20 |
The `GaudiStableDiffusionPipeline` (`GaudiDDIMScheduler`) is instantiated the same way as the `StableDiffusionPipeline` (`DDIMScheduler`) in the 🤗 Diffusers library.
|
21 |
+
The only difference is that there are a few new training arguments specific to HPUs.\
|
22 |
+
It is strongly recommended to train this model doing bf16 mixed-precision training for optimal performance and accuracy.
|
23 |
|
24 |
Here is an example with one prompt:
|
25 |
```python
|
gaudi_config.json
CHANGED
@@ -1,50 +1,5 @@
|
|
1 |
{
|
2 |
-
"use_habana_mixed_precision": true,
|
3 |
-
"hmp_is_verbose": false,
|
4 |
"use_fused_adam": true,
|
5 |
"use_fused_clip_norm": true,
|
6 |
-
"
|
7 |
-
"addmm",
|
8 |
-
"batch_norm",
|
9 |
-
"bmm",
|
10 |
-
"conv1d",
|
11 |
-
"conv2d",
|
12 |
-
"conv3d",
|
13 |
-
"conv_transpose1d",
|
14 |
-
"conv_transpose2d",
|
15 |
-
"conv_transpose3d",
|
16 |
-
"dot",
|
17 |
-
"dropout",
|
18 |
-
"dropout1d",
|
19 |
-
"dropout2d",
|
20 |
-
"dropout3d",
|
21 |
-
"group_norm",
|
22 |
-
"instance_norm",
|
23 |
-
"layer_norm",
|
24 |
-
"leaky_relu",
|
25 |
-
"linear",
|
26 |
-
"matmul",
|
27 |
-
"mean",
|
28 |
-
"mm",
|
29 |
-
"mv",
|
30 |
-
"relu",
|
31 |
-
"t"
|
32 |
-
],
|
33 |
-
"hmp_fp32_ops": [
|
34 |
-
"binary_cross_entropy",
|
35 |
-
"binary_cross_entropy_with_logits",
|
36 |
-
"cross_entropy",
|
37 |
-
"div",
|
38 |
-
"divide",
|
39 |
-
"embedding",
|
40 |
-
"embedding_bag",
|
41 |
-
"log",
|
42 |
-
"log2",
|
43 |
-
"log_softmax",
|
44 |
-
"nll_loss",
|
45 |
-
"smooth_l1_loss",
|
46 |
-
"softmax",
|
47 |
-
"topk",
|
48 |
-
"truediv"
|
49 |
-
]
|
50 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"use_fused_adam": true,
|
3 |
"use_fused_clip_norm": true,
|
4 |
+
"use_torch_autocast": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|