Determine the default precision and quantization in chat and generate

Nobody has claimed this yet.

If you finetune a model with a certain quantization and precision setting, you still need to specify that in the chat and generate commands today:

```py
litgpt chat \
--checkpoint_dir out/qlora-codellama-13b/final \
--precision bf16-true \
--quantize bnb.nf4-dq
```
Otherwise you may get an OOM or different results that you were getting during training. Since we store the hyperparameters in a yaml file, we could select the two settings automatically if they are not specified:

```py
# uses precision=bf16-true and quantize=bnb.nf4-dq from checkpoint folder
litgpt chat --checkpoint_dir out/qlora-codellama-13b/final
```

We already do this in other parts of LitGPT, so we could just reuse the utility function to read the two settings from the checkpoint.

Start by locating the chat and generate command entry points and the existing utility that reads hyperparameters from a checkpoint, as referenced in the issue. The work is done when omitted precision and quantization values are selected from the checkpoint while explicitly supplied values continue to work.

Written by the indexing model from the issue text.