Update README.md

README.md

@@ -2,7 +2,9 @@
 license: apache-2.0
 ---
 
-Finetunes Llama-13b+Alaca to solve problems via stepwise reasoning (OpenAI PRM800k dataset). [`Birchlabs/openai-prm800k-solutions-only`](https://huggingface.co/datasets/Birchlabs/openai-prm800k-solutions-only).
+Finetunes Llama-13b+Alaca to solve problems via stepwise reasoning (OpenAI [PRM800k dataset](https://github.com/openai/prm800k), or rather our postprocessed version, [`Birchlabs/openai-prm800k-solutions-only`](https://huggingface.co/datasets/Birchlabs/openai-prm800k-solutions-only)).
+
+## Model description
 
 This is a fork of [`llama-13b`](https://huggingface.co/huggyllama/llama-13b) + [`chansung/alpaca-lora-13b`](https://huggingface.co/chansung/alpaca-lora-13b).
 
@@ -16,6 +18,8 @@ Parts:
 - tokenizer [`Birchlabs/llama-13b-stepwise-tokenizer`](https://huggingface.co/Birchlabs/llama-13b-stepwise-tokenizer)
 - finetuned input/output embedding layers: [`Birchlabs/llama-13b-stepwise-embeddings`](https://huggingface.co/Birchlabs/llama-13b-stepwise-embeddings)
 
+## Usage
+
 You can load using [`evaluate.py`](https://github.com/scottlogic-alex/qlora/blob/stepwise/evaluate.py#L209-L278) from our [`stepwise`](https://github.com/scottlogic-alex/qlora/tree/stepwise) branch of [qlora](https://github.com/artidoro/qlora).
 
 Download `embed_tokens.pt` and `lm_head.pt` from [`Birchlabs/llama-13b-stepwise-embeddings`](https://huggingface.co/Birchlabs/llama-13b-stepwise-embeddings/tree/main), then run evaluator like so:
@@ -33,7 +37,13 @@ python -m evaluate \
 --overrun_countermeasures False
 ```
 
-Example instruction-response conversations:
+## Prompt style
+
+The model is finetuned for instruction-response.
+
+`prompt = '<s>Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nHow do I feed a family of 5 without ingredients?\n\n### Response:\n<|step_start|>'`
+
+## Example output:
 
 `$ How do I drink a matcha latte?`  
 `To drink a matcha latte, I should first remove the matcha from the bag. <|step_end|> <|step_start|> I can do that by opening the bag and shaking out the matcha into a glass or bowl. <|step_end|> <|step_start|> Then, I should add some hot water into the glass or bowl and start stirring the matcha. <|step_end|> <|step_start|> This is to make the matcha easier to mix with the water. <|step_end|> <|step_start|> Next, I should add milk into the glass or bowl and continue stirring. <|step_end|> <|step_start|> This is to make the matcha and the water form a thick mixture. <|step_end|> <|step_start|> Finally, I should add ice cubes into the glass or bowl and stir again. <|step_end|> <|step_start|> This is to make the mixture even thicker and chilled. <|step_end|> <|step_start|> So, a matcha latte is a drink that is a mixture of matcha, water, and milk, with some ice cubes. <|step_end|> <|step_start|> <|answer_start|> To make a matcha latte, I should remove the matcha from the bag, add some hot water into a glass or bowl and stir, add milk into the glass or bowl and stir as well, and finally add ice cubes and stir again. <|step_end|> <|step_start|> <|answer_start|> To drink a matcha latte, I should remove`