Update README.md

README.md

@@ -31,24 +31,24 @@ _Note: For all samples, your environment must have access to cuda_
 #### Setup
 
 ```bash
-docker pull docker-eu-public.artifactory.swg-devops.com/res-zrl-snap-docker-local/tgis-os:spec.7
+docker pull quay.io/wxpe/text-gen-server:speculative-decoding.ecd73c4
 docker run -d --rm --gpus all \
     --name my-tgis-server \
     -p 8033:8033 \
     -v /path/to/all/models:/models \
     -e MODEL_NAME=/models/model_weights/llama/13B-F \
-    -e SPECULATOR_NAME=/models/speculator_weights/llama/13B-F \
+    -e SPECULATOR_NAME=/models/speculator_weights/llama/llama-13b-accelerator \
     -e FLASH_ATTENTION=true \
     -e PAGED_ATTENTION=true \
     -e DTYPE_STR=float16 \
-    docker-eu-public.artifactory.swg-devops.com/res-zrl-snap-docker-local/tgis-os:spec.7
+    quay.io/wxpe/text-gen-server:speculative-decoding.ecd73c4
 
 # check logs and wait for "gRPC server started on port 8033" and "HTTP server started on port 3000"
 docker logs my-tgis-server -f
 
 # get the client sample (Note: The first prompt will take longer as there is a warmup time)
-conda create -n tgis-env python=3.11
-conda activate tgis-env
+conda create -n tgis-client-env python=3.11
+conda activate tgis-client-env
 git clone --branch speculative-decoding --single-branch https://github.com/tdoublep/text-generation-inference.git
 cd text-generation-inference/integration_tests
 make gen-client