Update `README.md` to use TEI v1.7 instead

- Previously it was set to 1.7.2 but some fixes landed as of 1.7.3, so setting it to 1.7 instead to be more stable in case more fixes land, as the latest 1.7.Z release will point to 1.7 too!
- Fixed tags for CPU and GPU as those were reversed

README.md

@@ -210,13 +210,13 @@ print(scores.tolist())
 You can either run / deploy TEI on NVIDIA GPUs as:
 
 ```bash
-docker run --gpus all -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.7.2 --model-id Qwen/Qwen3-Embedding-0.6B --dtype float16
+docker run --gpus all -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7 --model-id Qwen/Qwen3-Embedding-0.6B --dtype float16
 ```
 
 Or on CPU devices as:
 
 ```bash
-docker run -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7.2 --model-id Qwen/Qwen3-Embedding-0.6B
+docker run -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.7 --model-id Qwen/Qwen3-Embedding-0.6B --dtype float16
 ```
 
 And then, generate the embeddings sending a HTTP POST request as: