feat: add img overview

src/ml/llm-train-finetune/mod.md

@@ -1,18 +1,31 @@
 # LLM Train and FineTune
 
-- [x] Try [Colab Notebook to Finetuning Mistral-7b-Instruct](https://adithyask.medium.com/a-beginners-guide-to-fine-tuning-mistral-7b-instruct-model-0f39647b20fe): https://github.com/adithya-s-k/CompanionLLM
+## Overview
 
-The notebook needs to add `pad_token_id=2` when calling merged_model.generate() in Test the merged model:
+![](./llm-langchain-flow.png)
 
-```python
-outputs = merged_model.generate(input_ids=input_ids, pad_token_id=2,
-max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.5)
-```
+> ref: https://github.com/chatchat-space/Langchain-Chatchat/blob/master/README_en.md
 
-Fixed notebook is [Mistral_7B_qLora_Finetuning.ipynb](./Mistral_7B_qLora_Finetuning.ipynb). Prompt formatting is still questioned.
+## Brain dump
+
+- [Colab Notebook to Fine-tuning Mistral-7b-Instruct](https://adithyask.medium.com/a-beginners-guide-to-fine-tuning-mistral-7b-instruct-model-0f39647b20fe): https://github.com/adithya-s-k/CompanionLLM
+
+  ⚠️ This notebook needs to add `pad_token_id=2` when calling merged_model.generate() in Test the merged model:
+
+  ```python
+  outputs = merged_model.generate(input_ids=input_ids, pad_token_id=2,
+  max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.5)
+  ```
+
+  Fixed notebook is [Mistral_7B_qLora_Finetuning.ipynb](./Mistral_7B_qLora_Finetuning.ipynb). Prompt formatting is still questioned.
 
 ## TODO
 
+- [ ] Understand pgvector: https://bugbytes.io/posts/vector-databases-pgvector-and-langchain/
+- [ ] Try RAG: https://bugbytes.io/posts/retrieval-augmented-generation-with-langchain-and-pgvector/
+
+## TOREAD
+
 - [ ] Read, try and summary: https://github.com/replit/replitLM#alpaca-style-instruct-tuning-with-hugging-face-transformers
 - [ ] Try fine-tune-mistral: https://github.com/abacaj/fine-tune-mistral
 - [ ] Try fine-tune-mistral: https://github.com/brevdev/notebooks/blob/main/mistral-finetune-own-data.ipynb
@@ -21,3 +34,4 @@ Fixed notebook is [Mistral_7B_qLora_Finetuning.ipynb](./Mistral_7B_qLora_Finetun
 - [ ] Read and summary: https://docs.llamaindex.ai/en/stable/core_modules/data_modules/index/metadata_extraction.html
 - [ ] LLaVA: Visual and language AI with GPT-4, instruction tuning to visual data.
 - [ ] MUFFIN: follow Scaling Tasks per Input paradigm to collect multiple task instructions for a single input. (Keywords: Instruction Brainstorm, Instruction Rematching)
+- [ ] Take a look: https://github.com/chatchat-space/Langchain-Chatchat