v0.58.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.
- README.md +3 -3
- release_assets.json +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: text-generation
|
|
| 16 |
Granite 4.0 is a family of open language models from IBM designed for enterprise AI workloads including code generation, summarization, and retrieval-augmented generation.
|
| 17 |
|
| 18 |
This is based on the implementation of Granite-4.0-Micro found [here](https://huggingface.co/ibm-granite/granite-4.0-h-micro).
|
| 19 |
-
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 20 |
|
| 21 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 22 |
|
|
@@ -40,14 +40,14 @@ For more device-specific assets and performance metrics, visit **[Granite-4.0-Mi
|
|
| 40 |
|
| 41 |
### Option 2: Export with Custom Configurations
|
| 42 |
|
| 43 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 44 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 45 |
- Custom input shapes
|
| 46 |
- Target device and runtime configurations
|
| 47 |
|
| 48 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 49 |
|
| 50 |
-
See our repository for [Granite-4.0-Micro on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
|
|
|
| 16 |
Granite 4.0 is a family of open language models from IBM designed for enterprise AI workloads including code generation, summarization, and retrieval-augmented generation.
|
| 17 |
|
| 18 |
This is based on the implementation of Granite-4.0-Micro found [here](https://huggingface.co/ibm-granite/granite-4.0-h-micro).
|
| 19 |
+
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/granite_4_0_micro) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 20 |
|
| 21 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 22 |
|
|
|
|
| 40 |
|
| 41 |
### Option 2: Export with Custom Configurations
|
| 42 |
|
| 43 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/granite_4_0_micro) Python library to compile and export the model with your own:
|
| 44 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 45 |
- Custom input shapes
|
| 46 |
- Target device and runtime configurations
|
| 47 |
|
| 48 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 49 |
|
| 50 |
+
See our repository for [Granite-4.0-Micro on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/granite_4_0_micro) for usage instructions.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
release_assets.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"q4_0": {
|
| 5 |
"universal_assets": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.58.0",
|
| 3 |
"precisions": {
|
| 4 |
"q4_0": {
|
| 5 |
"universal_assets": {
|