Update README.md

README.md

@@ -1,7 +1,4 @@
 ---
-tags:
-- int4
-- vllm
 language:
 - en
 - de
@@ -11,9 +8,32 @@ language:
 - hi
 - es
 - th
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
 pipeline_tag: text-generation
-license: llama3.1
-base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+tags:
+- llama
+- facebook
+- meta
+- llama-3
+- int4
+- vllm
+- chat
+- neuralmagic
+- llmcompressor
+- conversational
+- 4-bit precision
+- gptq
+- compressed-tensors
+license: other
+license_name: llama3.1
+name: RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16
+description: This model was obtained by quantizing the weights of Meta-Llama-3.1-8B-Instruct to INT4 data type.
+readme: https://huggingface.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16/main/README.md
+tasks:
+- text-to-text
+provider: Meta
+license_link: https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE
 ---
 <h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
   Meta-Llama-3.1-8B-Instruct-quantized.w4a16