Update README.md

README.md

@@ -233,7 +233,7 @@ except Exception as e:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "openthaigpt/openthaigpt1.5-72b-instruct"
+model_name = "openthaigpt/openthaigpt1.5-7b-instruct"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -271,13 +271,13 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    
 2. Run server
 ```bash
-vllm serve openthaigpt/openthaigpt1.5-72b-instruct --tensor-parallel-size 4 
+vllm serve openthaigpt/openthaigpt1.5-7b-instruct --tensor-parallel-size 4 
 ```
 * Note, change ``--tensor-parallel-size 4`` to the amount of available GPU cards.
 
 If you wish to enable tool calling feature, add ``--enable-auto-tool-choice --tool-call-parser hermes`` into command. e.g.,
 ```bash
-vllm serve openthaigpt/openthaigpt1.5-72b-instruct --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser hermes
+vllm serve openthaigpt/openthaigpt1.5-7b-instruct --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser hermes
 ```
 
 3. Run inference (CURL example)