Templates: Switch to Jinja2

Jinja2 is a lightweight template parser that's used in Transformers
for parsing chat completions. It's much more efficient than Fastchat
and can be imported as part of requirements.

Also allows for unblocking Pydantic's version.

Users now have to provide their own template if needed. A separate
repo may be usable for common prompt template storage.

Signed-off-by: kingbri <bdashore3@proton.me>

templates/README.md

@@ -0,0 +1,7 @@
+# Templates
+
+NOTE: This folder will be replaced by a submodule or something similar in the future
+
+These templates are examples from [Aphrodite Engine](https://github.com/PygmalionAI/aphrodite-engine/tree/main/examples)
+
+Please look at [Huggingface's documentation](https://huggingface.co/docs/transformers/main/chat_templating) for making Jinja2 templates.

templates/alpaca.jinja

@@ -0,0 +1,29 @@
+{{ (messages|selectattr('role', 'equalto', 'system')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'system')|list) else '' }}
+
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+### Instruction:
+{{ message['content']|trim -}}
+{% if not loop.last %}
+
+
+{% endif %}
+{% elif message['role'] == 'assistant' %}
+### Response:
+{{ message['content']|trim -}}
+{% if not loop.last %}
+
+
+{% endif %}
+{% elif message['role'] == 'user_context' %}
+### Input:
+{{ message['content']|trim -}}
+{% if not loop.last %}
+
+
+{% endif %}
+{% endif %}
+{% endfor %}
+{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}
+### Response:
+{% endif %}

templates/chatml.jinja

@@ -0,0 +1,2 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}
+{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}