Update llama-7b-chat

Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>

README.md

@@ -25,7 +25,7 @@ Use the default model to continue the conversation from given messages.
 ```python
 from towhee import ops
 
-chat = ops.LLM.Llama_2('path/to/model_file.bin', max_tokens=2048)
+chat = ops.LLM.Llama_2('llama-2-13b-chat', max_tokens=2048)
 
 message = [{"question": "Building a website can be done in 10 simple steps:"}]
 answer = chat(message)
@@ -100,8 +100,8 @@ A dictionary of supported models with model name as key and huggingface hub id &
 
     {
         'llama-2-7b-chat': {
-            'hf_id': 'TheBloke/Llama-2-7B-GGML',
-            'filename': 'llama-2-7b.ggmlv3.q4_0.bin'
+            'hf_id': 'TheBloke/Llama-2-7B-Chat-GGML',
+            'filename': 'llama-2-7b-chat.ggmlv3.q4_0.bin'
             },
         'llama-2-13b-chat': {
             'hf_id': 'TheBloke/Llama-2-13B-chat-GGML',

llama2.py

@@ -77,8 +77,8 @@ class LlamaCpp(PyOperator):
     def supported_model_names():
         models = {
             'llama-2-7b-chat': {
-                'hf_id': 'TheBloke/Llama-2-7B-GGML',
-                'filename': 'llama-2-7b.ggmlv3.q4_0.bin'
+                'hf_id': 'TheBloke/Llama-2-7B-Chat-GGML',
+                'filename': 'llama-2-7b-chat.ggmlv3.q4_0.bin'
                 },
             'llama-2-13b-chat': {
                 'hf_id': 'TheBloke/Llama-2-13B-chat-GGML',