docs updated

.env.example

@@ -4,8 +4,8 @@ HF_HOME=DUMMY_PATH/huggingface
 HF_HUB_ENABLE_HF_TRANSFER=1
 # HF_TOKEN=TO_BE_FILLED
 # RUNPOD_API_KEY=TO_BE_FILLED
-HF_MODEL_NAME=mistralai/Pixtral-Large-Instruct-2411
-SERVED_MODEL_NAME=Pixtral-Large-Instruct-2411
+HF_MODEL_NAME=alpindale/c4ai-command-r-plus-GPTQ
+SERVED_MODEL_NAME=vLLM-Model
 MAX_CONTEXT_LEN=32000
 ENABLE_HEALTH_CHECK=1
 ENABLE_AUTO_RESTART=0

Makefile

@@ -31,15 +31,12 @@ prepare-env-file:  ## Copy .env.example to .env and correct the paths
 	cp .env.example .env
 	$(MAKE) change-paths-in-env-file
 
-change-model-env: ## Change the model that is specified in the .env file
-	# sed -i 's/HF_MODEL_NAME=alpindale\/WizardLM-2-8x22B/HF_MODEL_NAME=CohereForAI\/c4ai-command-r-v01/g' .env
-	sed -i '/HF_MODEL_NAME=/d' .env
-	echo "HF_MODEL_NAME=${HF_MODEL_NAME}" >> .env
-
-change-max-context-len-env: ## Change the max context length that is specified in the .env file
-	# sed -i 's/MAX_CONTEXT_LEN=32000/MAX_CONTEXT_LEN=40000/g' .env
-	sed -i '/MAX_CONTEXT_LEN=/d' .env
-	echo "MAX_CONTEXT_LEN=${MAX_CONTEXT_LEN}" >> .env
+replace-value-in-env-file: ## Replace a variable in the .env file
+	@if [ -z "${variable_name}" ] || [ -z "${new_value}" ]; then \
+		echo "Usage: make replace-value-in-env-file variable_name=<variable> new_value=<value>"; \
+		exit 1; \
+	fi
+	sed -i "s|${variable_name}=.*|${variable_name}=${new_value}|g" .env
 
 install-uv:
 	! command -v uv &> /dev/null && curl -LsSf https://astral.sh/uv/install.sh | sh

README.md

@@ -39,21 +39,20 @@ make gui
 - Example: Change default model and its context length to CohereForAI/c4ai-command-r-plus-GPTQ
 
 ```bash
-make change-model-env HF_MODEL_NAME=CohereForAI/c4ai-command-r-plus-GPTQ
-make change-max-context-len-env MAX_CONTEXT_LEN=40000
-
+make replace-value-in-env-file variable_name=HF_MODEL_NAME new_value=CohereForAI/c4ai-command-r-plus-GPTQ
+make replace-value-in-env-file variable_name=MAX_CONTEXT_LEN new_value=40000
 ```
 
 ## cURL Examples
 
-- Request with system message
+- Request with system message assuming `SERVED_MODEL_NAME=vLLM-Model`
 
 ```bash
 curl --request POST \
     --url http://0.0.0.0:8000/v1/chat/completions \
     --header "Content-Type: application/json" \
     --data '{
-  "model": "c4ai-command-r-plus-GPTQ",
+  "model": "vLLM-Model",
   "messages": [
   {
       "role": "system",
@@ -69,14 +68,14 @@ curl --request POST \
 }'
 ```
 
-- Request without system message
+- Request without system message assuming `SERVED_MODEL_NAME=vLLM-Model`
 
 ```bash
 curl --request POST \
     --url http://0.0.0.0:8000/v1/chat/completions \
     --header "Content-Type: application/json" \
     --data '{
-  "model": "c4ai-command-r-plus-GPTQ",
+  "model": "vLLM-Model",
   "messages": [
   {
     "role": "user",