Update README.md

README.md

@@ -21,76 +21,6 @@ With this fix applied:
 
 GPTQ via Ooba UI may not need this patch.
 
------
-## Model Details:
-
-Converted from the XORs weights from PygmalionAI's release https://huggingface.co/PygmalionAI/metharme-13b
-
-
-Metharme 13b is an instruct model based on Meta's LLaMA-13b.
-
-This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the [prompting](#prompting) section below for examples.
-
-It was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached.
-
-The current Metharme-13b has been trained as a LoRA, then merged down to the base model for distribuition. 
-
-It has also been quantized down to 8Bit using the GPTQ library available here: https://github.com/0cc4m/GPTQ-for-LLaMa
-```
-python llama.py .\TehVenom_Metharme-13b-Merged c4 --wbits 8 --act-order --save_safetensors Metharme-13b-GPTQ-8bit.act-order.safetensors
-```
-
-## Prompting
-
-The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
-
-The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
-
-### Prompting example
-
-Here's a concrete example. Let's say you have the following system prompt:
-
-> This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.
-
-And the user has typed in the following message:
-
-> Start!
-
-To perform inference against the model, the prompt should be formatted like this:
-```
-<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>
-```
-
-The model might generate something like:
-
-> You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!'
->
-> - Go inside the house.
-> - Ignore the call and move away.
-> - Run as fast as you can.
-
-It will automatically emit an end-of-text token (`</s>`) when it judges that the response is complete.
-
-Pretend then that the user has replied with `go inside`. The next prompt should then be:
-
-```
-<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!'
-
-- Go inside the house.
-- Ignore the call and move away.
-- Run as fast as you can.<|user|>go inside<|model|>
-```
-
-Which might generate something like:
-
-> You enter the house, and immediately, a wave of unsettling energy washes over you. Your senses seem heightened, but your mind feels foggy. A figure appears before you - a tall man with piercing eyes. He speaks to you in a language you don't understand.
->
-> - Ask him what he wants.
-> - Attack him.
-> - Run away.
-
-Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window.
-
 ## Eval / Benchmark scores
 
 Current evals out of the Metharme-13b model: <br>
@@ -171,6 +101,76 @@ Current evals out of the Metharme-13b model: <br>
 
 <hr>
 
+-----
+## Model Details:
+
+Converted from the XORs weights from PygmalionAI's release https://huggingface.co/PygmalionAI/metharme-13b
+
+
+Metharme 13b is an instruct model based on Meta's LLaMA-13b.
+
+This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the [prompting](#prompting) section below for examples.
+
+It was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached.
+
+The current Metharme-13b has been trained as a LoRA, then merged down to the base model for distribuition. 
+
+It has also been quantized down to 8Bit using the GPTQ library available here: https://github.com/0cc4m/GPTQ-for-LLaMa
+```
+python llama.py .\TehVenom_Metharme-13b-Merged c4 --wbits 8 --act-order --save_safetensors Metharme-13b-GPTQ-8bit.act-order.safetensors
+```
+
+## Prompting
+
+The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
+
+The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
+
+### Prompting example
+
+Here's a concrete example. Let's say you have the following system prompt:
+
+> This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.
+
+And the user has typed in the following message:
+
+> Start!
+
+To perform inference against the model, the prompt should be formatted like this:
+```
+<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>
+```
+
+The model might generate something like:
+
+> You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!'
+>
+> - Go inside the house.
+> - Ignore the call and move away.
+> - Run as fast as you can.
+
+It will automatically emit an end-of-text token (`</s>`) when it judges that the response is complete.
+
+Pretend then that the user has replied with `go inside`. The next prompt should then be:
+
+```
+<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!'
+
+- Go inside the house.
+- Ignore the call and move away.
+- Run as fast as you can.<|user|>go inside<|model|>
+```
+
+Which might generate something like:
+
+> You enter the house, and immediately, a wave of unsettling energy washes over you. Your senses seem heightened, but your mind feels foggy. A figure appears before you - a tall man with piercing eyes. He speaks to you in a language you don't understand.
+>
+> - Ask him what he wants.
+> - Attack him.
+> - Run away.
+
+Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window.
+
 ## Other notes
 
 - When prompted correctly, the model will always start by generating a BOS token. This behavior is an accidental side-effect which we plan to address in future model versions and should not be relied upon.