Fine-Tuning Mistral-7b for Real-World Chatbot Applications Using Axolotl (Lora used) (#1155)

* Mistral-7b finetune example using axolotl with code,config,data

* Corrected the path for huggingface dataset

* Update data.jsonl

* chore: lint

---------

Co-authored-by: twenty8th <twenty8th@users.noreply.github.com>
Co-authored-by: Wing Lian <wing.lian@gmail.com>

README.md

@@ -1,3 +1,6 @@
+## What's New
+- Added `Mistral-7b-example`: A comprehensive example for fine-tuning Mistral-7b model. [Check it out here](https://github.com/Tilemachoc/axolotl/tree/mistral-7b-example/examples/mistral/Mistral-7b-example).
+
 # Axolotl
 
 Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.

examples/mistral/Mistral-7b-example/README.md

@@ -0,0 +1,12 @@
+# Description
+This repository presents an in-depth guide for fine-tuning Mistral-7b or any other compatible model using Axolotl, tailored specifically for chatbot development. It streamlines the process of fine-tuning and uploading the enhanced model to HuggingFace 🤗, thereby serving as an invaluable tool for developers in the AI and chatbot domain.
+
+**What’s Inside:**
+
+Beginner-Friendly Instructions: Comprehensive steps to guide you through fine-tuning your chosen model, including details on the data structure (jsonl), configuration, and the code itself.
+
+Hardware Utilized: For reference, the fine-tuning in this guide was performed using 4x NVIDIA GeForce RTX 3090 (rented 2.1.2-cuda12.1-cudnn8-devel).
+
+**Uploading to HuggingFace 🤗:**
+To upload your fine-tuned model to Hugging Face, include the following files:
+![Screenshot 2024-01-19 213932](https://github.com/OpenAccess-AI-Collective/axolotl/assets/138583191/d660eb84-2d76-46a1-9846-cf0aeb3006d9)

examples/mistral/Mistral-7b-example/config.yml

@@ -0,0 +1,75 @@
+#Mistral-7b
+base_model: mistralai/Mistral-7B-v0.1
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: tilemachos/Demo-Dataset #Path to json dataset file in huggingface
+    #for type,conversation arguments read axolotl readme and pick what is suited for your project, I wanted a chatbot and put sharegpt and chatml
+    type: sharegpt
+    conversation: chatml
+dataset_prepared_path: tilemachos/Demo-Dataset #Path to json dataset file in huggingface
+val_set_size: 0.05
+output_dir: ./out
+
+#using lora for lower cost
+adapter: lora
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+
+sequence_len: 512
+sample_packing: false
+pad_to_sequence_len: true
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+#only 2 epochs because of small dataset
+gradient_accumulation_steps: 3
+micro_batch_size: 2
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+#default deepspeed, can use more aggresive if needed like zero2, zero3
+deepspeed: deepspeed/zero1.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"

examples/mistral/Mistral-7b-example/data.jsonl

@@ -0,0 +1,10 @@
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: Who is the Founder of Apple\""}, {"from": "gpt", "value": "\"<Chatbot>: The founder of Apple is Steve Jobs\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the capital of France?\""}, {"from": "gpt", "value": "\"<Chatbot>: The capital of France is Paris.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: How far is the Moon from Earth?\""}, {"from": "gpt", "value": "\"<Chatbot>: The Moon is approximately 384,400 kilometers from Earth.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the tallest mountain in the world?\""}, {"from": "gpt", "value": "\"<Chatbot>: The tallest mountain in the world is Mount Everest.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: Who wrote Romeo and Juliet?\""}, {"from": "gpt", "value": "\"<Chatbot>: Romeo and Juliet was written by William Shakespeare.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the boiling point of water?\""}, {"from": "gpt", "value": "\"<Chatbot>: The boiling point of water is 100 degrees Celsius.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: When was the first man on the moon?\""}, {"from": "gpt", "value": "\"<Chatbot>: The first man landed on the moon in 1969.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the largest ocean?\""}, {"from": "gpt", "value": "\"<Chatbot>: The largest ocean is the Pacific Ocean.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: Who invented the telephone?\""}, {"from": "gpt", "value": "\"<Chatbot>: The telephone was invented by Alexander Graham Bell.\""}]}
+{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the formula for water?\""}, {"from": "gpt", "value": "\"<Chatbot>: The chemical formula for water is H2O.\""}]}