Update README.md

README.md

@@ -7,4 +7,84 @@ Abliterated using the following the guide here:
 
 https://huggingface.co/blog/mlabonne/abliteration
 
-Fine tuned on orpo-dpo-mix-40k dataset
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: cowWhySo/Phi-3-mini-4k-instruct-Friendly
+trust_remote_code: true
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+chat_template: phi_3
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+save_safetensors: true
+
+rl: dpo
+datasets:
+  - path: mlabonne/orpo-dpo-mix-40k
+    split: train
+    type: chatml.intel
+
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./out
+
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: false
+
+adapter: qlora
+lora_model_dir:
+
+lora_r: 64
+lora_alpha: 32
+lora_dropout: 0.1
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: axolotl
+wandb_entity:
+wandb_watch:
+wandb_name: phi3-mini-4k-instruct-Friendly
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 4
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: linear
+learning_rate: 5e-6
+train_on_inputs: false
+group_by_length: false
+
+bf16: auto
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: True
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+warmup_steps: 150
+evals_per_epoch: 0
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed: deepspeed_configs/zero3.json
+weight_decay: 0.01
+max_grad_norm: 1.0
+resize_token_embeddings_to_32x: true
+```
+
+## Quants
+
+GGUF: https://huggingface.co/cowWhySo/Phi-3-mini-4k-instruct-Friendly-gguf