v0.47.0

See https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.

README.md

@@ -29,13 +29,7 @@ There are two ways to deploy this model on your device:
 
 ### Option 1: Download Pre-Exported Models
 
-Below are pre-exported model assets ready for deployment.
-
-| Runtime | Precision | Chipset | SDK Versions | Download |
-|---|---|---|---|---|
-| GENIE | w8a16 | qualcomm-qcs8275 | QAIRT 2.37 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/qwen2_5_7b_instruct/releases/v0.46.0/qwen2_5_7b_instruct-genie-w8a16-qualcomm_qcs8275.zip)
-
-For more device-specific assets and performance metrics, visit **[Qwen2.5-7B-Instruct on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/qwen2_5_7b_instruct)**.
+Download pre-exported model assets from **[Qwen2.5-7B-Instruct on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/qwen2_5_7b_instruct)**.
 
 
 ### Option 2: Export with Custom Configurations
@@ -56,7 +50,7 @@ See our repository for [Qwen2.5-7B-Instruct on GitHub](https://github.com/quic/a
 **Model Stats:**
 - Input sequence length for Prompt Processor: 128
 - Context length: 4096
-- Precision: w4a16 + w8a16 (few layers)
+- Quantization Type: w4a16 + w8a16 (few layers)
 - Supported languages: Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
 - TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
 - Response Rate: Rate of response generation after the first response token.