Update README.md

README.md

@@ -9,6 +9,8 @@ tags:
 - llama
 - trl
 base_model: unsloth/llama-3-8b-bnb-4bit
+datasets:
+- cognitivecomputations/samantha-data
 ---
 
 # Uploaded  model
@@ -17,6 +19,22 @@ base_model: unsloth/llama-3-8b-bnb-4bit
 - **License:** apache-2.0
 - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+This model is finetuned on the data of [Samantha](https://erichartford.com/meet-samantha).  
+Prompt format is Alpaca. I used the same system prompt as the original Samantha.
+```
+"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+### Instruction:
+{SYSTEM_PROMPT}
+
+### Input:
+{QUESTION}
+
+### Response:
+"""
+```
+[Training code is here](https://github.com/RuslanPeresy/gptchain)
+
+2 epoch finetuning from llama-3-8b took 1 hour on a single A100 with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)