diff --git a/examples/llava/lora-7b.yaml b/examples/llava/lora-7b.yaml new file mode 100644 index 000000000..97e1662b0 --- /dev/null +++ b/examples/llava/lora-7b.yaml @@ -0,0 +1,63 @@ +base_model: llava-hf/llava-1.5-7b-hf +processor_type: AutoProcessor +strict: false + +# these 3 lines are needed for now to handle vision chat templates w images +skip_prepare_dataset: true +remove_unused_columns: false +sample_packing: false + +chat_template: llama3_2_vision +datasets: + - path: HuggingFaceH4/llava-instruct-mix-vsft + type: chat_template + split: train[:1%] + field_messages: messages +dataset_prepared_path: last_run_prepared +val_set_size: 0.0 +output_dir: ./outputs/out + +adapter: lora +lora_model_dir: + +sequence_len: 8192 +pad_to_sequence_len: false + +lora_r: 32 +lora_alpha: 16 +lora_dropout: 0.05 +lora_target_modules: 'language_model.model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj' + +wandb_project: +wandb_entity: +wandb_watch: +wandb_name: +wandb_log_model: + +gradient_accumulation_steps: 4 +micro_batch_size: 1 +num_epochs: 1 +optimizer: adamw_bnb_8bit +lr_scheduler: cosine +learning_rate: 0.0002 + +train_on_inputs: false +group_by_length: false +bf16: true +fp16: +tf32: true + +gradient_checkpointing: true +local_rank: +logging_steps: 1 +flash_attention: true +eager_attention: + +warmup_ratio: 0.1 +evals_per_epoch: 1 +saves_per_epoch: 1 +debug: +deepspeed: +weight_decay: 0.0 +fsdp: +fsdp_config: diff --git a/src/axolotl/utils/chat_templates.py b/src/axolotl/utils/chat_templates.py index c11f62152..211a29d71 100644 --- a/src/axolotl/utils/chat_templates.py +++ b/src/axolotl/utils/chat_templates.py @@ -24,6 +24,7 @@ _CHAT_TEMPLATES = { "cohere": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% 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 %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}", "llama3": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", "llama3_2_vision": '{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now("%d %b %Y") %}\n {%- else %}\n {%- set date_string = "26 Jul 2024" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0][\'role\'] == \'system\' %}\n {%- set system_message = messages[0][\'content\']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = "" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %} \n{%- for message in messages %}\n {%- for content in message[\'content\'] %}\n {%- if content[\'type\'] == \'image\' %}\n {%- set image_ns.has_images = true %}\n {%- endif %}\n {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == "" %}\n {{- raise_exception("Prompting with images is incompatible with system messages.") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n {{- "<|start_header_id|>system<|end_header_id|>\\n\\n" }}\n {%- if tools is not none %}\n {{- "Environment: ipython\\n" }}\n {%- endif %}\n {{- "Cutting Knowledge Date: December 2023\\n" }}\n {{- "Today Date: " + date_string + "\\n\\n" }}\n {%- if tools is not none and not tools_in_user_message %}\n {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}\n {{- \'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.\' }}\n {{- "Do not use variables.\\n\\n" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- "\\n\\n" }}\n {%- endfor %}\n {%- endif %}\n {{- system_message }}\n {{- "<|eot_id|>" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0][\'content\']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception("Cannot put tools in the first user message when there\'s no first user message!") }}\n{%- endif %}\n {{- \'<|start_header_id|>user<|end_header_id|>\\n\\n\' -}}\n {{- "Given the following functions, please respond with a JSON for a function call " }}\n {{- "with its proper arguments that best answers the given prompt.\\n\\n" }}\n {{- \'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.\' }}\n {{- "Do not use variables.\\n\\n" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- "\\n\\n" }}\n {%- endfor %}\n {{- first_user_message + "<|eot_id|>"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == \'ipython\' or message.role == \'tool\' or \'tool_calls\' in message) %}\n {{- \'<|start_header_id|>\' + message[\'role\'] + \'<|end_header_id|>\\n\\n\' }}\n {%- if message[\'content\'] is string %}\n {{- message[\'content\'] }}\n {%- else %}\n {%- for content in message[\'content\'] %}\n {%- if content[\'type\'] == \'image\' %}\n {{- \'<|image|>\' }}\n {%- elif content[\'type\'] == \'text\' %}\n {{- content[\'text\'] }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- \'<|eot_id|>\' }}\n {%- elif \'tool_calls\' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception("This model only supports single tool-calls at once!") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- \'<|start_header_id|>assistant<|end_header_id|>\\n\\n\' -}}\n {{- \'{"name": "\' + tool_call.name + \'", \' }}\n {{- \'"parameters": \' }}\n {{- tool_call.arguments | tojson }}\n {{- "}" }}\n {{- "<|eot_id|>" }}\n {%- elif message.role == "tool" or message.role == "ipython" %}\n {{- "<|start_header_id|>ipython<|end_header_id|>\\n\\n" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- "<|eot_id|>" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- \'<|start_header_id|>assistant<|end_header_id|>\\n\\n\' }}\n{%- endif %}\n', + "llava": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}", "phi_3": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}", "phi_35": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}", "deepseek_v2": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|User|>' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '<|Assistant|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|Assistant|>' }}{% endif %}",