Update README.md

README.md

@@ -1,3 +1,60 @@
 ---
 license: apache-2.0
 ---
+
+# LimaRP-Llama2-7B-v3 (Alpaca, experimental, 4-bit LoRA adapter)
+
+This is an experimental version of LimaRP using a somewhat updated dataset (1800 training samples)
+and a 2-pass training procedure. The first pass includes unsupervised tuning on 2800 stories within
+4k tokens and the second is LimaRP.
+
+For more details about LimaRP, see the model page for the [previously released version](https://huggingface.co/lemonilia/limarp-llama2-v2).
+Most details written there apply for this version as well.
+
+## Prompt used
+Same as before. It uses Alpaca format, with `### Input:` immediately preceding user inputs and `### Response`
+immediately preceding model outputs.
+
+```
+### Instruction:
+Character's Persona: {bot character description}
+
+User's Persona: {user character description}
+
+Scenario: {what happens in the story}
+
+Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User. Character should respond with messages of medium length.
+
+### Input:
+User: {utterance}
+
+### Response:
+Character: {utterance}
+```
+
+### Other notes
+- Replace all the text in curly braces (curly braces included) with your own text.
+- `User` and `Character` should be replaced with appropriate names.
+
+## Training Hyperparameters
+[Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training.
+The model has been trained as a 4-bit LoRA adapter. It's so large because a LoRA rank
+of 256 was used. It's suggested to merge it to the base Llama2-7B model.
+
+- learning_rate: 0.0002
+- lr_scheduler_type: constant
+- lora_r: 256
+- lora_alpha: 16
+- lora_dropout: 0.1
+- lora_target_linear: True
+- num_epochs: 1
+- bf16: True
+- tf32: True
+- load_in_4bit: True
+- adapter: qlora
+- micro_batch_size: 2
+- gradient_accumulation_steps: 1
+- optimizer: adamw_torch
+
+For the multi-stage training, the `lora_model_dir` option was used to load and train the
+previously created adapter.