Update README.md

README.md

@@ -229,6 +229,10 @@ This is one of the first models trained on the LosslessMegaCodeTrainingV2_1m_Evo
 
 - This model was made as a colaboration between me and andreaskoepf who is an affiliate of Open Assistant.
 
+This Model score .29 on humaneval+ the same as LLaMA-2 70B Chat Link bellow (in this benchmark the model is called andreaskoepf/llama2-13b-megacode2_min100)
+
+- https://tju01.github.io/FastEval-OpenAssistant/
+
 Prompt template:
 
 - chatml format is used: "<|im_start|>system\n{system message}<|im_end|>\n<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"
@@ -242,6 +246,42 @@ multi-line:
 <|im_start|>assistant
 {Assistant answer}<|im_end|>
 ```
+Gpt4all template:
+
+- System prompt
+```
+<|im_start|>system
+{system message}
+```
+- Prompt template
+```
+<|im_end|>
+<|im_start|>user
+%1<|im_end|>
+<|im_start|>assistant
+```
+
+Oobagooba Text-Generation-Webui Template
+- user:
+```
+  <|im_start|>user
+  {User string}<|im_end|>
+```
+- bot:
+```
+  <|im_start|>assistant
+  {Bot string}<|im_end|>
+```
+- turn_template:
+```
+<|user|>\n<|user-message|>\n\n<|bot|>\n<|bot-message|>\n\n
+```
+- context:
+```
+  <|im_start|>system
+  Below is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>
+```
+
 Training data:
 
 - https://wandb.ai/open-assistant/epfl-mt-sft/runs/run34_megacode2_min100_13b
@@ -256,4 +296,4 @@ Link for the filtered dataset used to make this model are bellow:
 
 The original posting for this model was uploaded at the link bellow.
 
-- https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100
+- https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100