Update README.md

README.md

@@ -1,3 +1,21 @@
+---
+tags:
+- fp4
+- vllm
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+pipeline_tag: text-generation
+license: apache-2.0
+base_model: mistral/Mistral-7B-Instruct-v0.3
+---
+
 # Mistral-7B-Instruct-v0.3-NVFP4
 
 NVFP4-quantized version of `mistralai/Mistral-7B-Instruct-v0.3` produced with [llmcompressor](https://github.com/vllm-project/llm-compressor).
@@ -18,7 +36,7 @@ from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
 
 model_id = "llmat/Mistral-7B-Instruct-v0.3-NVFP4"
-number_gpus = 2
+number_gpus = 1
 
 sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)
 
@@ -39,4 +57,4 @@ generated_text = outputs[0].outputs[0].text
 print(generated_text)
 ```
 
-vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.