Commit b7374ad4 authored by zhuwenwen's avatar zhuwenwen
Browse files

update v0.6.2

parent 57d61ec2
<#meta#>
- Date: {{ (messages|selectattr('role', 'equalto', 'meta-current_date')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'meta-current_date')|list) else '' }}
- Task: {{ (messages|selectattr('role', 'equalto', 'meta-task_name')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'meta-task_name')|list) else '' }}
<#system#>
{{ (messages|selectattr('role', 'equalto', 'system')|list|last).content|trim if (messages|selectattr('role', 'equalto', 'system')|list) else '' }}
<#chat#>
{% for message in messages %}
{% if message['role'] == 'user' %}
<#user#>
{{ message['content']|trim -}}
{% if not loop.last %}
{% endif %}
{% elif message['role'] == 'assistant' %}
<#bot#>
{{ message['content']|trim -}}
{% if not loop.last %}
{% endif %}
{% elif message['role'] == 'user_context' %}
<#user_context#>
{{ message['content']|trim -}}
{% if not loop.last %}
{% endif %}
{% endif %}
{% endfor %}
{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}
<#bot#>
{% endif %}
\ No newline at end of file
{% if messages[0]['role'] == 'system' %}
{% set system_message = '<<SYS>>\n' + messages[0]['content'] | trim + '\n<</SYS>>\n\n' %}
{% set messages = messages[1:] %}
{% else %}
{% set system_message = '' %}
{% endif %}
{% for message in messages %}
{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
{% endif %}
{% if loop.index0 == 0 %}
{% set content = system_message + message['content'] %}
{% else %}
{% set content = message['content'] %}
{% endif %}
{% if message['role'] == 'user' %}
{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}
{% elif message['role'] == 'assistant' %}
{{ ' ' + content | trim + ' ' + eos_token }}
{% endif %}
{% endfor %}
\ No newline at end of file
{%- if messages[0]['role'] == 'system' -%}
{%- set system_message = messages[0]['content'] -%}
{%- set messages = messages[1:] -%}
{%- else -%}
{% set system_message = '' -%}
{%- endif -%}
{{ bos_token + system_message }}
{%- for message in messages -%}
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
{%- endif -%}
{%- if message['role'] == 'user' -%}
{{ 'USER: ' + message['content'] + '\n' }}
{%- elif message['role'] == 'assistant' -%}
{{ 'ASSISTANT: ' + message['content'] + eos_token + '\n' }}
{%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt -%}
{{ 'ASSISTANT:' }}
{% endif %}
......@@ -2,12 +2,8 @@
{%- for message in messages -%}
{%- if message['role'] == 'user' -%}
{{- '<reserved_106>' + message['content'] -}}
{{- '<_user>' + message['content'] +'<_bot>' -}}
{%- elif message['role'] == 'assistant' -%}
{{- '<reserved_107>' + message['content'] -}}
{{- message['content'] + '<_end>' -}}
{%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt and messages[-1]['role'] != 'assistant' -%}
{{- '<reserved_107>' -}}
{% endif %}
\ No newline at end of file
import argparse
import dataclasses
import json
import os
import uuid
from functools import partial
from tensorizer import stream_io
from vllm import LLM
from vllm.distributed import (init_distributed_environment,
initialize_model_parallel)
from vllm.engine.arg_utils import EngineArgs
from vllm.engine.llm_engine import LLMEngine
from vllm.model_executor.model_loader.tensorizer import (TensorizerArgs,
TensorizerConfig,
serialize_vllm_model)
# yapf conflicts with isort for this docstring
# yapf: disable
"""
tensorize_vllm_model.py is a script that can be used to serialize and
deserialize vLLM models. These models can be loaded using tensorizer
to the GPU extremely quickly over an HTTP/HTTPS endpoint, an S3 endpoint,
or locally. Tensor encryption and decryption is also supported, although
libsodium must be installed to use it. Install vllm with tensorizer support
using `pip install vllm[tensorizer]`. To learn more about tensorizer, visit
https://github.com/coreweave/tensorizer
To serialize a model, install vLLM from source, then run something
like this from the root level of this repository:
python -m examples.tensorize_vllm_model \
--model facebook/opt-125m \
serialize \
--serialized-directory s3://my-bucket \
--suffix v1
Which downloads the model from HuggingFace, loads it into vLLM, serializes it,
and saves it to your S3 bucket. A local directory can also be used. This
assumes your S3 credentials are specified as environment variables
in the form of `S3_ACCESS_KEY_ID`, `S3_SECRET_ACCESS_KEY`, and
`S3_ENDPOINT_URL`. To provide S3 credentials directly, you can provide
`--s3-access-key-id` and `--s3-secret-access-key`, as well as `--s3-endpoint`
as CLI args to this script.
You can also encrypt the model weights with a randomly-generated key by
providing a `--keyfile` argument.
To deserialize a model, you can run something like this from the root
level of this repository:
python -m examples.tensorize_vllm_model \
--model EleutherAI/gpt-j-6B \
--dtype float16 \
deserialize \
--path-to-tensors s3://my-bucket/vllm/EleutherAI/gpt-j-6B/v1/model.tensors
Which downloads the model tensors from your S3 bucket and deserializes them.
You can also provide a `--keyfile` argument to decrypt the model weights if
they were serialized with encryption.
For more information on the available arguments for serializing, run
`python -m examples.tensorize_vllm_model serialize --help`.
Or for deserializing:
`python -m examples.tensorize_vllm_model deserialize --help`.
Once a model is serialized, tensorizer can be invoked with the `LLM` class
directly to load models:
llm = LLM(model="facebook/opt-125m",
load_format="tensorizer",
model_loader_extra_config=TensorizerConfig(
tensorizer_uri = path_to_tensors,
num_readers=3,
)
)
A serialized model can be used during model loading for the vLLM OpenAI
inference server. `model_loader_extra_config` is exposed as the CLI arg
`--model-loader-extra-config`, and accepts a JSON string literal of the
TensorizerConfig arguments desired.
In order to see all of the available arguments usable to configure
loading with tensorizer that are given to `TensorizerConfig`, run:
`python -m examples.tensorize_vllm_model deserialize --help`
under the `tensorizer options` section. These can also be used for
deserialization in this example script, although `--tensorizer-uri` and
`--path-to-tensors` are functionally the same in this case.
"""
def parse_args():
parser = argparse.ArgumentParser(
description="An example script that can be used to serialize and "
"deserialize vLLM models. These models "
"can be loaded using tensorizer directly to the GPU "
"extremely quickly. Tensor encryption and decryption is "
"also supported, although libsodium must be installed to "
"use it.")
parser = EngineArgs.add_cli_args(parser)
subparsers = parser.add_subparsers(dest='command')
serialize_parser = subparsers.add_parser(
'serialize', help="Serialize a model to `--serialized-directory`")
serialize_parser.add_argument(
"--suffix",
type=str,
required=False,
help=(
"The suffix to append to the serialized model directory, which is "
"used to construct the location of the serialized model tensors, "
"e.g. if `--serialized-directory` is `s3://my-bucket/` and "
"`--suffix` is `v1`, the serialized model tensors will be "
"saved to "
"`s3://my-bucket/vllm/EleutherAI/gpt-j-6B/v1/model.tensors`. "
"If none is provided, a random UUID will be used."))
serialize_parser.add_argument(
"--serialized-directory",
type=str,
required=True,
help="The directory to serialize the model to. "
"This can be a local directory or S3 URI. The path to where the "
"tensors are saved is a combination of the supplied `dir` and model "
"reference ID. For instance, if `dir` is the serialized directory, "
"and the model HuggingFace ID is `EleutherAI/gpt-j-6B`, tensors will "
"be saved to `dir/vllm/EleutherAI/gpt-j-6B/suffix/model.tensors`, "
"where `suffix` is given by `--suffix` or a random UUID if not "
"provided.")
serialize_parser.add_argument(
"--keyfile",
type=str,
required=False,
help=("Encrypt the model weights with a randomly-generated binary key,"
" and save the key at this path"))
deserialize_parser = subparsers.add_parser(
'deserialize',
help=("Deserialize a model from `--path-to-tensors`"
" to verify it can be loaded and used."))
deserialize_parser.add_argument(
"--path-to-tensors",
type=str,
required=True,
help="The local path or S3 URI to the model tensors to deserialize. ")
deserialize_parser.add_argument(
"--keyfile",
type=str,
required=False,
help=("Path to a binary key to use to decrypt the model weights,"
" if the model was serialized with encryption"))
TensorizerArgs.add_cli_args(deserialize_parser)
return parser.parse_args()
def deserialize():
llm = LLM(model=args.model,
load_format="tensorizer",
model_loader_extra_config=tensorizer_config
)
return llm
args = parse_args()
s3_access_key_id = (getattr(args, 's3_access_key_id', None)
or os.environ.get("S3_ACCESS_KEY_ID", None))
s3_secret_access_key = (getattr(args, 's3_secret_access_key', None)
or os.environ.get("S3_SECRET_ACCESS_KEY", None))
s3_endpoint = (getattr(args, 's3_endpoint', None)
or os.environ.get("S3_ENDPOINT_URL", None))
credentials = {
"s3_access_key_id": s3_access_key_id,
"s3_secret_access_key": s3_secret_access_key,
"s3_endpoint": s3_endpoint
}
_read_stream, _write_stream = (partial(
stream_io.open_stream,
mode=mode,
s3_access_key_id=s3_access_key_id,
s3_secret_access_key=s3_secret_access_key,
s3_endpoint=s3_endpoint,
) for mode in ("rb", "wb+"))
model_ref = args.model
model_name = model_ref.split("/")[1]
os.environ["MASTER_ADDR"] = "127.0.0.1"
os.environ["MASTER_PORT"] = "8080"
init_distributed_environment(world_size=1, rank=0, local_rank=0)
initialize_model_parallel()
keyfile = args.keyfile if args.keyfile else None
if args.model_loader_extra_config:
config = json.loads(args.model_loader_extra_config)
tensorizer_args = TensorizerConfig(**config)._construct_tensorizer_args()
tensorizer_args.tensorizer_uri = args.path_to_tensors
else:
tensorizer_args = None
if args.command == "serialize":
eng_args_dict = {f.name: getattr(args, f.name) for f in
dataclasses.fields(EngineArgs)}
engine_args = EngineArgs.from_cli_args(argparse.Namespace(**eng_args_dict))
engine = LLMEngine.from_engine_args(engine_args)
input_dir = args.serialized_directory.rstrip('/')
suffix = args.suffix if args.suffix else uuid.uuid4().hex
base_path = f"{input_dir}/vllm/{model_ref}/{suffix}"
model_path = f"{base_path}/model.tensors"
tensorizer_config = TensorizerConfig(
tensorizer_uri=model_path,
**credentials)
serialize_vllm_model(engine, tensorizer_config, keyfile)
elif args.command == "deserialize":
if not tensorizer_args:
tensorizer_config = TensorizerConfig(
tensorizer_uri=args.path_to_tensors,
encryption_keyfile = keyfile,
**credentials
)
deserialize()
else:
raise ValueError("Either serialize or deserialize must be specified.")
{%- macro json_to_python_type(json_spec) %}
{%- set basic_type_map = {
"string": "str",
"number": "float",
"integer": "int",
"boolean": "bool"
} %}
{%- if basic_type_map[json_spec.type] is defined %}
{{- basic_type_map[json_spec.type] }}
{%- elif json_spec.type == "array" %}
{{- "list[" + json_to_python_type(json_spec|items) + "]" }}
{%- elif json_spec.type == "object" %}
{%- if json_spec.additionalProperties is defined %}
{{- "dict[str, " + json_to_python_type(json_spec.additionalProperties) + ']' }}
{%- else %}
{{- "dict" }}
{%- endif %}
{%- elif json_spec.type is iterable %}
{{- "Union[" }}
{%- for t in json_spec.type %}
{{- json_to_python_type({"type": t}) }}
{%- if not loop.last %}
{{- "," }}
{%- endif %}
{%- endfor %}
{{- "]" }}
{%- else %}
{{- "Any" }}
{%- endif %}
{%- endmacro %}
{{- bos_token }}
{{- "<|im_start|>system\nYou are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> " }}
{%- if tools is iterable and tools | length > 0 %}
{%- for tool in tools %}
{%- if tool.function is defined %}
{%- set tool = tool.function %}
{%- endif %}
{{- '{"type": "function", "function": ' }}
{{- '{"name": "' + tool.name + '", ' }}
{{- '"description": "' + tool.name + '(' }}
{%- for param_name, param_fields in tool.parameters.properties|items %}
{{- param_name + ": " + json_to_python_type(param_fields) }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- if tool.return is defined %}
{{- " -> " + json_to_python_type(tool.return) }}
{%- endif %}
{{- " - " + tool.description + "\n\n" }}
{%- for param_name, param_fields in tool.parameters.properties|items %}
{%- if loop.first %}
{{- " Args:\n" }}
{%- endif %}
{{- " " + param_name + "(" + json_to_python_type(param_fields) + "): " + param_fields.description|trim }}
{%- endfor %}
{%- if tool.return is defined and tool.return.description is defined %}
{{- "\n Returns:\n " + tool.return.description }}
{%- endif %}
{{- '"' }}
{{- ', "parameters": ' }}
{%- if tool.parameters.properties | length == 0 %}
{{- "{}" }}
{%- else %}
{{- tool.parameters|tojson }}
{%- endif %}
{{- "}" }}
{%- if not loop.last %}
{{- "\n" }}
{%- endif %}
{%- endfor %}
{%- endif %}
{{- " </tools>" }}
{{- 'Use the following pydantic model json schema for each tool call you will make: {"properties": {"name": {"title": "Name", "type": "string"}, "arguments": {"title": "Arguments", "type": "object"}}, "required": ["name", "arguments"], "title": "FunctionCall", "type": "object"}}
' }}
{{- "For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
" }}
{{- "<tool_call>
" }}
{{- '{"name": <function-name>, "arguments": <args-dict>}
' }}
{{- '</tool_call><|im_end|>' }}
{%- for message in messages %}
{%- if message.role == "user" or message.role == "system" or (message.role == "assistant" and message.tool_calls is not defined) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" and message.tool_calls is defined %}
{{- '<|im_start|>' + message.role }}
{%- for tool_call in message.tool_calls %}
{{- '\n<tool_call>\n' }}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '{' }}
{{- '"name": "' }}
{{- tool_call.name }}
{{- '"' }}
{%- if tool_call.arguments is defined %}
{{- ', ' }}
{{- '"arguments": ' }}
{{- tool_call.arguments|tojson }}
{%- endif %}
{{- '}' }}
{{- '\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>tool\n' }}
{%- endif %}
{{- '<tool_response>\n' }}
{{- message.content }}
{%- if not loop.last %}
{{- '\n</tool_response>\n' }}
{%- else %}
{{- '\n</tool_response>' }}
{%- endif %}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>' }}
{%- elif loop.last %}
{{- '<|im_end|>' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}
{%- if messages[0]["role"] == "system" %}
{%- set system_message = messages[0]["content"] %}
{%- set loop_messages = messages[1:] %}
{%- else %}
{%- set loop_messages = messages %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
{%- for message in loop_messages | rejectattr("role", "equalto", "tool") | rejectattr("role", "equalto", "tool_results") | selectattr("tool_calls", "undefined") %}
{%- if (message["role"] == "user") != (loop.index0 % 2 == 0) %}
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
{%- endif %}
{%- endfor %}
{{- bos_token }}
{%- for message in loop_messages %}
{%- if message["role"] == "user" %}
{%- if tools is not none and (message == user_messages[-1]) %}
{{- "[AVAILABLE_TOOLS] [" }}
{%- for tool in tools %}
{%- set tool = tool.function %}
{{- '{"type": "function", "function": {' }}
{%- for key, val in tool.items() if key != "return" %}
{%- if val is string %}
{{- '"' + key + '": "' + val + '"' }}
{%- else %}
{{- '"' + key + '": ' + val|tojson }}
{%- endif %}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- "}}" }}
{%- if not loop.last %}
{{- ", " }}
{%- else %}
{{- "]" }}
{%- endif %}
{%- endfor %}
{{- "[/AVAILABLE_TOOLS]" }}
{%- endif %}
{%- if loop.last and system_message is defined %}
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
{%- else %}
{{- "[INST] " + message["content"] + "[/INST]" }}
{%- endif %}
{%- elif message["role"] == "tool_calls" or message.tool_calls is defined %}
{%- if message.tool_calls is defined %}
{%- set tool_calls = message.tool_calls %}
{%- else %}
{%- set tool_calls = message.content %}
{%- endif %}
{{- "[TOOL_CALLS] [" }}
{%- for tool_call in tool_calls %}
{%- set out = tool_call.function|tojson %}
{{- out[:-1] }}
{%- if not tool_call.id is defined or tool_call.id|length < 9 %}
{{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (1)" + tool_call.id) }}
{%- endif %}
{{- ', "id": "' + tool_call.id[-9:] + '"}' }}
{%- if not loop.last %}
{{- ", " }}
{%- else %}
{{- "]" + eos_token }}
{%- endif %}
{%- endfor %}
{%- elif message["role"] == "assistant" %}
{{- " " + message["content"] + eos_token }}
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
{%- if message.content is defined and message.content.content is defined %}
{%- set content = message.content.content %}
{%- else %}
{%- set content = message.content %}
{%- endif %}
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
{%- if not message.tool_call_id is defined or message.tool_call_id|length < 9 %}
{{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (2)" + message.tool_call_id) }}
{%- endif %}
{{- '"call_id": "' + message.tool_call_id[-9:] + '"}[/TOOL_RESULTS]' }}
{%- else %}
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
{%- endif %}
{%- endfor %}
{%- if messages[0]["role"] == "system" %}
{%- set system_message = messages[0]["content"] %}
{%- set loop_messages = messages[1:] %}
{%- else %}
{%- set loop_messages = messages %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{%- if tools is defined %}
{%- set parallel_tool_prompt = "You are a helpful assistant that can call tools. If you call one or more tools, format them in a single JSON array or objects, where each object is a tool call, not as separate objects outside of an array or multiple arrays. Use the format [{\"name\": tool call name, \"arguments\": tool call arguments}, additional tool calls] if you call more than one tool. If you call tools, do not attempt to interpret them or otherwise provide a response until you receive a tool call result that you can interpret for the user." %}
{%- if system_message is defined %}
{%- set system_message = parallel_tool_prompt + "\n\n" + system_message %}
{%- else %}
{%- set system_message = parallel_tool_prompt %}
{%- endif %}
{%- endif %}
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
{%- for message in loop_messages | rejectattr("role", "equalto", "tool") | rejectattr("role", "equalto", "tool_results") | selectattr("tool_calls", "undefined") %}
{%- if (message["role"] == "user") != (loop.index0 % 2 == 0) %}
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
{%- endif %}
{%- endfor %}
{{- bos_token }}
{%- for message in loop_messages %}
{%- if message["role"] == "user" %}
{%- if tools is not none and (message == user_messages[-1]) %}
{{- "[AVAILABLE_TOOLS] [" }}
{%- for tool in tools %}
{%- set tool = tool.function %}
{{- '{"type": "function", "function": {' }}
{%- for key, val in tool.items() if key != "return" %}
{%- if val is string %}
{{- '"' + key + '": "' + val + '"' }}
{%- else %}
{{- '"' + key + '": ' + val|tojson }}
{%- endif %}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- "}}" }}
{%- if not loop.last %}
{{- ", " }}
{%- else %}
{{- "]" }}
{%- endif %}
{%- endfor %}
{{- "[/AVAILABLE_TOOLS]" }}
{%- endif %}
{%- if loop.last and system_message is defined %}
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
{%- else %}
{{- "[INST] " + message["content"] + "[/INST]" }}
{%- endif %}
{%- elif message["role"] == "tool_calls" or message.tool_calls is defined %}
{%- if message.tool_calls is defined %}
{%- set tool_calls = message.tool_calls %}
{%- else %}
{%- set tool_calls = message.content %}
{%- endif %}
{{- "[TOOL_CALLS] [" }}
{%- for tool_call in tool_calls %}
{%- set out = tool_call.function|tojson %}
{{- out[:-1] }}
{%- if not tool_call.id is defined or tool_call.id|length < 9 %}
{{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (1)" + tool_call.id) }}
{%- endif %}
{{- ', "id": "' + tool_call.id[-9:] + '"}' }}
{%- if not loop.last %}
{{- ", " }}
{%- else %}
{{- "]" + eos_token }}
{%- endif %}
{%- endfor %}
{%- elif message["role"] == "assistant" %}
{{- " " + message["content"] + eos_token }}
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
{%- if message.content is defined and message.content.content is defined %}
{%- set content = message.content.content %}
{%- else %}
{%- set content = message.content %}
{%- endif %}
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
{%- if not message.tool_call_id is defined or message.tool_call_id|length < 9 %}
{{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (2)" + message.tool_call_id) }}
{%- endif %}
{{- '"call_id": "' + message.tool_call_id[-9:] + '"}[/TOOL_RESULTS]' }}
{%- else %}
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
{%- endif %}
{%- endfor %}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment