Update README.md

README.md

@@ -53,7 +53,7 @@ This version underwent a subset of DPO, but is fairly censored.  For a less cens
 3) Once inside the VM, open the terminal and run `conda activate text-generation-inference`
 4) Then `cd Desktop/text-generation-inference/`
 5) Run `volume=$PWD/data`
-6) Run`model=jondurbin/nontoxic-bagle-34b-v0.2`
+6) Run`model=jondurbin/nontoxicbagel-34b-v0.2`
 7) `sudo docker run --gpus '"device=0,1"' --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model`
 8) The model will take some time to load...
 9) Once loaded the model will be available on port 8080
@@ -62,7 +62,7 @@ Sample command within the VM
 ```
 curl 0.0.0.0:8080/generate \
     -X POST \
-    -d '{"inputs":"<|system|>You are a friendly chatbot.\n<|user|>What type of model are you?\n<|assistant|>","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
+    -d '{"inputs":"[INST] <</SYS>>\nYou are a friendly chatbot.\n<</SYS>>\n\nWhat type of model are you? [/INST]","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
     -H 'Content-Type: application/json'
 ```
 
@@ -70,7 +70,7 @@ You can also access the model from outside the VM
 ```
 curl IP_ADDRESS_PROVIDED_BY_MASSED_COMPUTE_VM:8080/generate \
     -X POST \
-    -d '{"inputs":"<|system|>You are a friendly chatbot.\n<|user|>What type of model are you?\n<|assistant|>","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
+    -d '{"inputs":"[INST] <</SYS>>\nYou are a friendly chatbot.\n<</SYS>>\n\nWhat type of model are you? [/INST]","parameters":{"do_sample": true, "max_new_tokens": 100, "repetition_penalty": 1.15, "temperature": 0.7, "top_k": 20, "top_p": 0.9, "best_of": 1}}'\
     -H 'Content-Type: application/json
 ```