Upload README.md

README.md

@@ -7,7 +7,7 @@ license: apache-2.0
 model_creator: YeungNLP
 model_name: Firefly Mixtral 8X7B
 model_type: mixtral
-prompt_template: '{prompt}
+prompt_template: '[INST] {prompt} [/INST]
 
   '
 quantized_by: TheBloke
@@ -76,10 +76,10 @@ AWQ models are supported by (note that not all of these may support Mixtral mode
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
-## Prompt template: None
+## Prompt template: Mistral
 
 ```
-{prompt}
+[INST] {prompt} [/INST]
 
 ```
 
@@ -145,7 +145,7 @@ prompts = [
     "What is 291 - 150?",
     "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
 ]
-prompt_template=f'''{prompt}
+prompt_template=f'''[INST] {prompt} [/INST]
 '''
 
 prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
@@ -187,7 +187,7 @@ from huggingface_hub import InferenceClient
 endpoint_url = "https://your-endpoint-url-here"
 
 prompt = "Tell me about AI"
-prompt_template=f'''{prompt}
+prompt_template=f'''[INST] {prompt} [/INST]
 '''
 
 client = InferenceClient(endpoint_url)
@@ -250,7 +250,7 @@ model = AutoModelForCausalLM.from_pretrained(
 streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
 prompt = "Tell me about AI"
-prompt_template=f'''{prompt}
+prompt_template=f'''[INST] {prompt} [/INST]
 '''
 
 # Convert prompt to tokens