Update README.md

README.md

@@ -24,7 +24,7 @@ This metaphorically represents the model's depth, fluidity, and adaptability in
 
 It also perfectly fits the approach taken here - Depth Upscaling, inspired by SOLAR 10.7B.
 
-## Nous LLM Evaluation (Version 1 - with ChatML Prompt Template)
+## Nous LLM Evaluation (with ChatML Prompt Template)
 |                             Model                             |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
 |---------------------------------------------------------------|------:|------:|---------:|-------:|------:|
 |[Chikuma_10.7B](https://huggingface.co/sethuiyer/Chikuma_10.7B)|  42.41|  73.41|     56.69|    43.5|     54|
@@ -32,7 +32,7 @@ It also perfectly fits the approach taken here - Depth Upscaling, inspired by SO
 More details can be found [here](https://gist.github.com/sethuiyer/08b4498ed13a6dead38ad3a6f12e349a)
 
 
-### Recommended Prompt Template
+### Recommended Prompt Template (Experimental)
 
 ```text
 <|im_start|>GPT4 Correct system
@@ -45,11 +45,12 @@ Always use <|end_of_turn|> when you want to end the answer.<|im_end|>
 {{Input}}
 <|im_end|>GPT4 Correct Assistant:
 ```
-ChatML format also works well.
+
+ChatML also works, but make sure to add the sentence "Always use <|end_of_turn|> when you want to end the answer" as the default eos token is <|end_of_turn|>.
 
 ## 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.
+1. [text-generation-webui](https://github.com/oobabooga/text-generation-webui), LLaMa-Precise sampling settings.
+2. `transformers` text generation pipeline, temperature=4.0, top_k=50, top_p=0.01.
 
 
 ## 🧩 Configuration
@@ -83,6 +84,6 @@ 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)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=4.0, top_k=50, top_p=0.01)
 print(outputs[0]["generated_text"])
 ```