Update README.md

README.md

@@ -35,7 +35,7 @@ More details can be found [here](https://gist.github.com/sethuiyer/08b4498ed13a6
 ### Recommended Prompt Template
 
 ```text
-<|im_start|>system
+<|im_start|>GPT4 Correct system
 You are Chikuma, a constantly learning AI assistant who strives to be
 insightful, engaging, and helpful. You possess vast knowledge and creativity,
 but also a humble curiosity about the world and the people you interact
@@ -46,7 +46,9 @@ Always use <|end_of_turn|> when you want to end the answer.<|im_end|>
 <|im_end|>GPT4 Correct Assistant:
 ```
 
-Works best in [text-generation-webui](https://github.com/oobabooga/text-generation-webui), above prompt template, "<|end_of_turn|"> as eos token, LLaMa-Precise sampling settings.
+## Tested to work well in :
+1. [text-generation-webui](https://github.com/oobabooga/text-generation-webui), eos_token_id=32000, LLaMa-Precise sampling settings.
+2. `transformers` text generation pipeline, temperature=4.0, top_k=50, top_p=0.01, eos_token_id=32000.
 
 
 ## 🧩 Configuration
@@ -66,29 +68,19 @@ dtype: bfloat16
 ## 💻 Usage
 
 ```python
-!pip install -q transformers accelerate bitsandbytes 
-
-from transformers import AutoTokenizer
-import transformers
-import torch
-
-model = "sethuiyer/Chikuma_10.7B"
-tokenizer = AutoTokenizer.from_pretrained(model)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    torch_dtype=torch.bfloat16,
-    device_map="cuda",
-)
-
-system_template = '''
+sys_message = ''' 
 You are Chikuma, a constantly learning AI assistant who strives to be
 insightful, engaging, and helpful. You possess vast knowledge and creativity,
 but also a humble curiosity about the world and the people you interact
 with. If you don't know the answer to a question, please don't share false information. 
 Always use <|end_of_turn|> when you want to end the answer.
 '''
-messages = [{"role": "user", "content": "What is a large language model?"}]
+
+question = '''
+Tell me what is a large language model in under 250 words.
+'''
+
+messages = [{"role":"system", "content": sys_message}, {"role": "user", "content": question}]
 prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=4.0, top_k=50, top_p=0.01, eos_token_id=32000)
 print(outputs[0]["generated_text"])