From e0e5d9b1d672ce5650b2fb4f9779d0f01cf17abc Mon Sep 17 00:00:00 2001 From: NanoCode012 Date: Mon, 7 Apr 2025 21:49:29 +0700 Subject: [PATCH] feat: add llama4 multimodal (#2499) * feat: add llama4 multimodal * feat: add torchvision to base docker * just use latest torchvision --------- Co-authored-by: Wing Lian --- docker/Dockerfile-base | 2 +- docs/multimodal.qmd | 9 +++++++++ src/axolotl/processing_strategies.py | 1 + src/axolotl/utils/chat_templates.py | 1 + src/axolotl/utils/models.py | 2 ++ src/axolotl/utils/schemas/enums.py | 1 + 6 files changed, 15 insertions(+), 1 deletion(-) diff --git a/docker/Dockerfile-base b/docker/Dockerfile-base index e989152ec..52201f276 100644 --- a/docker/Dockerfile-base +++ b/docker/Dockerfile-base @@ -29,7 +29,7 @@ ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}" WORKDIR /workspace RUN python3 -m pip install --upgrade pip && pip3 install -U packaging==23.2 setuptools==75.8.0 wheel && \ - python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --extra-index-url https://download.pytorch.org/whl/cu$CUDA && \ + python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} torchvision --extra-index-url https://download.pytorch.org/whl/cu$CUDA && \ python3 -m pip install --no-cache-dir "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@main" && \ python3 -m pip install --no-cache-dir "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main" diff --git a/docs/multimodal.qmd b/docs/multimodal.qmd index e8e793482..5ddd91f60 100644 --- a/docs/multimodal.qmd +++ b/docs/multimodal.qmd @@ -9,6 +9,7 @@ format: ## Supported Models - [Mllama](#sec-mllama) +- [Llama4](#sec-llama4) - [Pixtral](#sec-pixtral) - [Llava-1.5](#sec-llava-15) - [Mistral-Small-3.1](#sec-mistral-small-31) @@ -63,6 +64,14 @@ base_model: meta-llama/Llama-3.2-11B-Vision-Instruct chat_template: llama3_2_vision ``` +### Llama4 {#sec-llama4} + +```yaml +base_model: meta-llama/Llama-4-Scout-17B-16E-Instruct + +chat_template: llama4 +``` + ### Pixtral {#sec-pixtral} ```yaml diff --git a/src/axolotl/processing_strategies.py b/src/axolotl/processing_strategies.py index 0b854af8d..4dee4f8a2 100644 --- a/src/axolotl/processing_strategies.py +++ b/src/axolotl/processing_strategies.py @@ -268,6 +268,7 @@ def get_processing_strategy( ) if chat_template_type in [ "llama3_2_vision", + "llama4", "llava", "mistral_v7_tekken", "pixtral", diff --git a/src/axolotl/utils/chat_templates.py b/src/axolotl/utils/chat_templates.py index 234b42d8d..f0cead09b 100644 --- a/src/axolotl/utils/chat_templates.py +++ b/src/axolotl/utils/chat_templates.py @@ -28,6 +28,7 @@ _CHAT_TEMPLATES = { "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 %}", "llama4": "{{- 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 {%- if messages[0]['content'] is string %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- else %}\n {#- FIXME: The processor requires an array, always. #}\n {%- set system_message = messages[0]['content'][0]['text']|trim %}\n {%- endif %}\n {%- set messages = messages[1:] %}\n {%- set user_supplied_system_message = true %}\n{%- else %}\n {%- set system_message = \"\" %}\n {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- System message if the user supplied one #}\n{%- if user_supplied_system_message %}\n {{- \"<|header_start|>system<|header_end|>\\n\\n\" }}\n {%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n {%- endif %}\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|>\" }}\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 {{- '<|header_start|>user<|header_end|>\\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|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|header_start|>' + message['role'] + '<|header_end|>\\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|>\" }}\n {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}\n {{- '<|header_start|>assistant<|header_end|>\\n\\n' -}}\n {{- '<|python_start|>' }}\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 {{- '<|python_end|>' }}\n {%- for tool_call in message.tool_calls %}\n {{- '{\"name\": \"' + tool_call.function.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.function.arguments | tojson }}\n {{- \"}\" }}\n {%- endfor %}\n {{- \"<|eot|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|header_start|>ipython<|header_end|>\\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|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|header_start|>assistant<|header_end|>\\n\\n' }}\n{%- endif %}\n", "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', + "llama4": "{{- 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 {%- if messages[0]['content'] is string %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- else %}\n {#- FIXME: The processor requires an array, always. #}\n {%- set system_message = messages[0]['content'][0]['text']|trim %}\n {%- endif %}\n {%- set messages = messages[1:] %}\n {%- set user_supplied_system_message = true %}\n{%- else %}\n {%- set system_message = \"\" %}\n {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- System message if the user supplied one #}\n{%- if user_supplied_system_message %}\n {{- \"<|header_start|>system<|header_end|>\\n\\n\" }}\n {%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n {%- endif %}\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|>\" }}\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 {{- '<|header_start|>user<|header_end|>\\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|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|header_start|>' + message['role'] + '<|header_end|>\\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|>\" }}\n {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}\n {{- '<|header_start|>assistant<|header_end|>\\n\\n' -}}\n {{- '<|python_start|>' }}\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 {{- '<|python_end|>' }}\n {%- for tool_call in message.tool_calls %}\n {{- '{\"name\": \"' + tool_call.function.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.function.arguments | tojson }}\n {{- \"}\" }}\n {%- endfor %}\n {{- \"<|eot|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|header_start|>ipython<|header_end|>\\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|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|header_start|>assistant<|header_end|>\\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' }}{% endif %}", diff --git a/src/axolotl/utils/models.py b/src/axolotl/utils/models.py index 367e69850..024673b8e 100644 --- a/src/axolotl/utils/models.py +++ b/src/axolotl/utils/models.py @@ -36,6 +36,7 @@ from transformers import ( BitsAndBytesConfig, Gemma3ForConditionalGeneration, GPTQConfig, + Llama4ForConditionalGeneration, LlavaForConditionalGeneration, Mistral3ForConditionalGeneration, MllamaForConditionalGeneration, @@ -76,6 +77,7 @@ LOG = logging.getLogger(__name__) MULTIMODAL_AUTO_MODEL_MAPPING = { "mllama": MllamaForConditionalGeneration, + "llama4": Llama4ForConditionalGeneration, "llava": LlavaForConditionalGeneration, "qwen2_vl": Qwen2VLForConditionalGeneration, "qwen2_5_vl": Qwen2_5_VLForConditionalGeneration, diff --git a/src/axolotl/utils/schemas/enums.py b/src/axolotl/utils/schemas/enums.py index 16b91ec41..d56d7534a 100644 --- a/src/axolotl/utils/schemas/enums.py +++ b/src/axolotl/utils/schemas/enums.py @@ -28,6 +28,7 @@ class ChatTemplate(str, Enum): llama3 = "llama3" # pylint: disable=invalid-name llama4 = "llama4" # pylint: disable=invalid-name llama3_2_vision = "llama3_2_vision" # pylint: disable=invalid-name + llama4 = "llama4" # pylint: disable=invalid-name phi_3 = "phi_3" # pylint: disable=invalid-name phi_35 = "phi_35" # pylint: disable=invalid-name deepseek_v2 = "deepseek_v2" # pylint: disable=invalid-name