Knowledge: IBM Granite Knowledge

knowledge/technology/large_language_model/granite/attribution.txt

@@ -0,0 +1,5 @@
+Title of work: IBM Granite
+Link to work: https://en.wikipedia.org/wiki/IBM_Granite
+Revision: https://en.wikipedia.org/wiki/IBM_Granite?utm_source=ibm_developer&utm_content=in_content_link&utm_id=tutorials_awb-contributing-llm-granite-instructlab-ui
+License of the work: IBM-AJ-1.0
+Creator names: Wikiepedia Authors

knowledge/technology/large_language_model/granite/qna.yaml

@@ -0,0 +1,82 @@
+created_by: amnajamal-ibm
+version: 3
+domain: large-language-model
+document_outline: Knowledge contribution about the IBM Granite model
+seed_examples:
+  - context: >-
+      IBM Granite is a series of decoder-only AI foundation models created by
+      IBM. It was announced on September 7, 2023, and an initial paper was
+      published 4 days later
+    questions_and_answers:
+      - question: What is IBM Granite
+        answer: >-
+          IBM Granite is a series of decoder-only AI foundation models created
+          by IBM
+      - question: When was IBM Granite announced?
+        answer: September 7, 2023
+      - question: What's a series of IBM decoder-only AI foundation models?
+        answer: IBM Granite
+  - context: >-
+      Granite's first foundation models were Granite.13b.instruct and
+      Granite.13b.chat. The "13b" in their name comes from 13 billion, the
+      amount of parameters they have as models, lesser than most of the larger
+      models of the time. Later models vary from 3 to 34 billion parameters
+    questions_and_answers:
+      - question: What was Granite's first foundation model?
+        answer: ' Granite.13b.instruct and  Granite.13b.chat'
+      - question: What does 13b in the name mean?
+        answer: 13 billion, amount of parameters they have as models
+      - question: What is the range of parameters in the later models?
+        answer: 3 to 34 billion parameters
+  - context: >-
+      On May 6, 2024, IBM released the source code of four variations of Granite
+      Code Models under Apache 2, an open source permissive license that allows
+      completely free use, modification and sharing of the software, and put
+      them on Hugging Face for public use. According to IBM's own report,
+      Granite 8b outperforms Llama 3 on several coding related tasks within
+      similar range of parameters
+    questions_and_answers:
+      - question: >-
+          When did IBM release the source code of four variations of Granite
+          code Models under Apache 2?
+        answer: May 6, 2024
+      - question: What is Apache 2 standard?
+        answer: >-
+          an open source permissive license that allows completely free use,
+          modification and sharing of the software
+      - question: >-
+          Which Granite model outperforms Lllama 3 on several coding related
+          taks?
+        answer: 'Granite 8b '
+  - context: >-
+      A foundation model is an AI model trained on broad data at scale such that
+      it can be adapted to a wide range of downstream tasks
+    questions_and_answers:
+      - question: What is a foundation model?
+        answer: A foundation model is an AI model trained on broad data at scale
+      - question: Can foundation models adapt to a wide range of downstream tasks?
+        answer: 'Yes'
+      - question: What is trained on broad data at scale?
+        answer: Foundation models
+  - context: >-
+      Initially intended for use in the IBM's cloud-based data and generative AI
+      platform Watsonx along with other models, IBM opened the source code of
+      some code models. Granite models are trained on datasets curated from
+      Internet, academic publishings, code datasets, legal and finance
+      documents.
+    questions_and_answers:
+      - question: What data is Granite model trained on?
+        answer: >-
+          Granite models are trained on datasets curated from Internet, academic
+          publishings, code datasets, legal and finance documents.
+      - question: Where was Granite series initially intended for use ?
+        answer: >-
+          Initially intended for use in the IBM's cloud-based data and
+          generative AI platform Watsonx
+      - question: Did IBM open source code of some code models?
+        answer: 'Yes'
+document:
+  repo: https://github.com/amnajamal-ibm/taxonomy-knowledge-docs
+  commit: 2d5313a1a3db04f68a23fe0f6da45466b1b4cf03
+  patterns:
+    - IBM-Granite-20241206T034852310.md