Upload README.md with huggingface_hub

README.md

@@ -10,15 +10,54 @@ tags:
 - mistral
 - peft
 - lora
-- 3B
 - hmc
 - reasoning
 - mathematical-reasoning
+datasets:
+- piqa
+- ai2_arc
+- gsm8k
 base_model:
 - mistralai/Ministral-3-3B-Base-2512
 library_name: transformers
 pipeline_tag: text-generation
-license: mit
+model-index:
+- name: RubiNet
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      type: piqa
+      name: PIQA
+      split: validation
+    metrics:
+    - type: accuracy
+      name: Accuracy
+      value: 71.55
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      type: ai2_arc
+      name: ARC-Easy
+      config: ARC-Easy
+      split: test
+    metrics:
+    - type: accuracy
+      name: Accuracy
+      value: 79.82
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      type: gsm8k
+      name: GSM8K-100
+      split: test
+    metrics:
+    - type: accuracy
+      name: Accuracy
+      value: 24.0
 ---
 
 # RubiNet
@@ -37,7 +76,7 @@ The goal of RubiNet is to provide sharper dialogue quality, stronger consistency
 - **Inference stack**: Transformers + PEFT
 - **Tuning style**: RubiNet HMC chat adaptation
 
-## Benchmark Snapshot
+## Eval Results
 
 The following benchmark scores were reported for the RubiNet setup:
 
@@ -93,9 +132,9 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 
 ## Chat Example
 
-![RubiNet local chat example](./rubinet_chat_example.png)
+![RubiNet HMC architecture](./RubiNetHMC.png)
 
-Example local RubiNet chat interface screenshot.
+RubiNet HMC architecture overview used in the local serving stack.
 
 ## Training / Adaptation Note
 
@@ -110,4 +149,4 @@ RubiNet is a fine-tuned conversational adaptation derived from `mistralai/Minist
 
 ## Repository Notes
 
-If you publish this repository publicly, keep the model title as **RubiNet** and place extra technical details such as benchmark scores, language coverage, and architecture hints in the tags and description rather than in the title.
+If you publish this repository publicly, keep the model title as **RubiNet** and place extra technical details such as benchmark scores, language coverage, and architecture hints in the tags and description rather than in the title.