Ink

README.md

@@ -12,8 +12,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: human-exams
-      name: MMLU
+        type: human-exams
+        name: MMLU
     metrics:
     - name: pass@1
       type: pass@1
@@ -22,8 +22,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: human-exams
-      name: MMLU-Pro
+        type: human-exams
+        name: MMLU-Pro
     metrics:
     - name: pass@1
       type: pass@1
@@ -32,8 +32,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: human-exams
-      name: AGI-Eval
+        type: human-exams
+        name: AGI-Eval
     metrics:
     - name: pass@1
       type: pass@1
@@ -42,38 +42,38 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: commonsense
-      name: WinoGrande
+        type: commonsense
+        name: WinoGrande
     metrics:
     - name: pass@1
       type: pass@1
-      value: 80.9
+      value: 80.90
       veriefied: false
   - task:
       type: text-generation
     dataset:
-      type: commonsense
-      name: OBQA
+        type: commonsense
+        name: OBQA 
     metrics:
     - name: pass@1
       type: pass@1
-      value: 46.8
+      value: 46.80
       veriefied: false
   - task:
       type: text-generation
     dataset:
-      type: commonsense
-      name: SIQA
+        type: commonsense
+        name: SIQA
     metrics:
     - name: pass@1
       type: pass@1
-      value: 67.8
+      value: 67.80
       veriefied: false
   - task:
       type: text-generation
     dataset:
-      type: commonsense
-      name: PIQA
+        type: commonsense
+        name: PIQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -82,8 +82,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: commonsense
-      name: Hellaswag
+        type: commonsense
+        name: Hellaswag
     metrics:
     - name: pass@1
       type: pass@1
@@ -92,8 +92,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: commonsense
-      name: TruthfulQA
+        type: commonsense
+        name: TruthfulQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -102,8 +102,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: reading-comprehension
-      name: BoolQ
+        type: reading-comprehension
+        name: BoolQ
     metrics:
     - name: pass@1
       type: pass@1
@@ -112,8 +112,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: reading-comprehension
-      name: SQuAD 2.0
+        type: reading-comprehension
+        name: SQuAD 2.0
     metrics:
     - name: pass@1
       type: pass@1
@@ -122,18 +122,18 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: reasoning
-      name: ARC-C
+        type: reasoning
+        name: ARC-C
     metrics:
     - name: pass@1
       type: pass@1
-      value: 63.4
+      value: 63.40
       veriefied: false
   - task:
       type: text-generation
     dataset:
-      type: reasoning
-      name: GPQA
+        type: reasoning
+        name: GPQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -142,8 +142,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: reasoning
-      name: BBH
+        type: reasoning
+        name: BBH
     metrics:
     - name: pass@1
       type: pass@1
@@ -152,8 +152,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: reasoning
-      name: MUSR
+        type: reasoning
+        name: MUSR
     metrics:
     - name: pass@1
       type: pass@1
@@ -162,8 +162,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: code
-      name: HumanEval
+        type: code
+        name: HumanEval
     metrics:
     - name: pass@1
       type: pass@1
@@ -172,42 +172,39 @@ model-index:
   - task:
       type: text-generation
     dataset:
-      type: code
-      name: MBPP
+        type: code
+        name: MBPP
     metrics:
     - name: pass@1
       type: pass@1
-      value: 41.4
-      veriefied: false
+      value: 41.40
+      veriefied: false     
   - task:
       type: text-generation
     dataset:
-      type: math
-      name: GSM8K
+        type: math
+        name: GSM8K
     metrics:
     - name: pass@1
       type: pass@1
       value: 64.06
-      veriefied: false
+      veriefied: false 
   - task:
       type: text-generation
     dataset:
-      type: math
-      name: MATH
+        type: math
+        name: MATH
     metrics:
     - name: pass@1
       type: pass@1
       value: 29.28
-      veriefied: false
-new_version: ibm-granite/granite-3.1-8b-base
+      veriefied: false   
 ---
 <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->
 <!-- ![image/png](granite-3_0-language-models_Group_1.png) -->
 
 # Granite-3.0-8B-Base
 
-<!-- **Note: We are continuously improving our models and recommend users to checkout our latest [Granite 3.1](https://huggingface.co/collections/ibm-granite/granite-31-language-models-6751dbbf2f3389bec5c6f02d) models.** -->
-
 **Model Summary:** 
 Granite-3.0-8B-Base is a decoder-only language model to support a variety of text-to-text generation tasks. It is trained from scratch following a two-stage training strategy. In the first stage, it is trained on 10 trillion tokens sourced from diverse domains. During the second stage, it is further trained on 2 trillion tokens using a carefully curated mix of high-quality data, aiming to enhance its performance on specific tasks.
 
@@ -291,11 +288,6 @@ We train Granite 3.0 Language Models using IBM's super computing cluster, Blue V
 **Ethical Considerations and Limitations:** 
 The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. Granite-3.0-8B-Base model is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use Granite-3.0-8B-Base model with ethical intentions and in a responsible way. 
 
-**Resources**
-- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
-- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
-- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
-
 <!-- ## Citation
 ```
 @misc{granite-models,
@@ -306,4 +298,4 @@ The use of Large Language Models involves risks and ethical considerations peopl
   year = {2024},
   url = {https://arxiv.org/abs/0000.00000},
 }
-``` -->
+``` -->