# LoRA Fine-tuning Configuration for Sanskrit Translation & Transliteration Enhancement
base_model: Qwen/Qwen2.5-7B-Instruct

# Use our custom chat template
chat_template_jinja: "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a Sanskrit-English bilingual AI assistant created by Divax Shah (diabolic6045). You are specialized in Sanskrit language understanding and translation.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a Sanskrit-English bilingual AI assistant created by Divax Shah (diabolic6045). You are specialized in Sanskrit language understanding and translation.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\\\"name\\\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}"

datasets:
  - path: diabolic6045/Sanskrit-transliteration-chat-dataset
    type: chat_template
    field_messages: messages
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant

val_set_size: 0.1
output_dir: ./outputs/sanskrit-chat-7b-lora

# LoRA configuration
adapter: lora
lora_model_dir:

sequence_len: 512
sample_packing: true
eval_sample_packing: true

# LoRA hyperparameters
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00002

# Precision configuration
bf16: auto
tf32: false

# Memory optimization
gradient_checkpointing: true
flash_attention: true

# Training schedule
warmup_ratio: 0.1
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
logging_steps: 1

# Wandb configuration
wandb_project: sanskrit-qwen
wandb_entity:
wandb_watch:
wandb_name: sanskrit-qwen-7b-lora-chat
wandb_log_model:

# Resume from checkpoint
resume_from_checkpoint:

# Hub model ID (update with your username)
# hub_model_id: your-username/Sanskrit-Qwen2.5-7B-LoRA-chat