Update README.md

README.md

@@ -1,4 +1,33 @@
-
+---
+language:
+- en
+base_model:
+- moonshotai/Kimi-K2-Instruct
+pipeline_tag: text-generation
+tags:
+- kimi-k2
+- MOE
+- neuralmagic
+- redhat
+- llmcompressor
+- quantized
+- INT4
+- GPTQ
+- conversational
+- compressed-tensors
+license: other
+license_name: modified-mit
+name: RedHatAI/Kimi-K2-Instruct-quantized.w4a16
+description: >-
+  This model was obtained by quantizing weights of moonshotai/Kimi-K2-Instruct to INT4 data
+  type.
+readme: >-
+  https://huggingface.co/RedHatAI/Kimi-K2-Instruct-quantized.w4a16/main/README.md
+tasks:
+- text-to-text
+provider: Moonshot AI
+license_link: https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE
+---
 <h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
   Kimi-K2-Instruct-quantized.w4a16
   <img src="https://www.redhat.com/rhdc/managed-files/Catalog-Validated_model_0.png" alt="Model Icon" width="40" style="margin: 0; padding: 0;" />
@@ -153,7 +182,7 @@ spec:
      name: vLLM
  containers:
    - name: kserve-container
-     image: quay.io/modh/vllm:rhoai-2.24-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm
+     image: quay.io/modh/vllm:rhoai-2.24-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.24-rocm
      command:
        - python
        - -m