ibibrahim commited on
Commit
51ced9b
1 Parent(s): 50ada2f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -241,6 +241,7 @@ model-index:
241
  veriefied: false
242
  base_model:
243
  - ibm-granite/granite-3.0-3b-a800m-base
 
244
  ---
245
 
246
  <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->
@@ -342,6 +343,11 @@ We train Granite 3.0 Language Models using IBM's super computing cluster, Blue V
342
  **Ethical Considerations and Limitations:**
343
  Granite 3.0 Instruct Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering eleven languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks.
344
 
 
 
 
 
 
345
  <!-- ## Citation
346
  ```
347
  @misc{granite-models,
 
241
  veriefied: false
242
  base_model:
243
  - ibm-granite/granite-3.0-3b-a800m-base
244
+ new_version: ibm-granite/granite-3.1-3b-a800m-instruct
245
  ---
246
 
247
  <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->
 
343
  **Ethical Considerations and Limitations:**
344
  Granite 3.0 Instruct Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering eleven languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks.
345
 
346
+ **Resources**
347
+ - ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
348
+ - 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
349
+ - 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
350
+
351
  <!-- ## Citation
352
  ```
353
  @misc{granite-models,