add notes for train_param.yaml

docs/inference.md

@@ -46,10 +46,11 @@ torchrun --nnodes 1 --nproc_per_node 8  llama_finetuning.py --enable_fsdp --mode
 ```
 Then convert your FSDP checkpoint to HuggingFace checkpoints using:
 ```bash
- python checkpoint_converter_fsdp_hf.py --fsdp_checkpoint_path  PATH/to/FSDP/Checkpoints --consolidated_model_path PATH/to/save/checkpoints --HF_model_path PATH/or/HF/model_name
+ python checkpoint_converter_fsdp_hf.py --fsdp_checkpoint_path  PATH/to/FSDP/Checkpoints --consolidated_model_path PATH/to/save/checkpoints --HF_model_path_or_name PATH/or/HF/model_name
 
- # --HF_model_path specifies the HF Llama model name or path where it has config.json and tokenizer.json
+ # --HF_model_path_or_name specifies the HF Llama model name or path where it has config.json and tokenizer.json
  ```
+By default, training parameter are saved in train_params.yaml in the path where FSDP checkpoints are saved, in the converter script we frist try to find the HugingFace model name used in the fine-tuning to load the model with configs from there, if not found user need to provide it.
 
 Then run inference using: