sarvamai/sarvam-1 · Fine tuning using Lora

13 days ago

Hi All,

Anyone tried fine tuning this model, what is the template to be used to fine tune this model for instruction following and multi-turn chat?

Thanks in advance!

jarvisvasu changed discussion title from Fine tuned for chatting to Fine tuning using Lora 13 days ago

i-was-here

about 17 hours ago

•

edited about 17 hours ago

Here's a chat template you can use:
"{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}"