XinnanZhang/Qwen3-1.7B-Base-Openthought400K-SFT
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: XinnanZhang/Qwen3-1.7B-Base-Openthought400K-SFT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-04 18:39:19 +08:00
commit 8789948a69
119 changed files with 23863 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
checkpoint-600/chat_template.jinja Normal file
View File

@@ -0,0 +1,85 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# 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>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\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" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

63
checkpoint-600/config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

10
checkpoint-600/generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"do_sample": false,
"eos_token_id": [
151645,
151643
],
"max_new_tokens": 2048,
"pad_token_id": 151643,
"transformers_version": "5.2.0"
}

3
checkpoint-600/global_step600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd0e74704706aa780dbb6b4d21bafc0f7a2dacfbfcc99628fe2d6ffea0657a5b
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ce29fe5b1ee8294154d5f97938b3a57a670c5dede7359474981a0d2c0d10d6d
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c506f8d09ca2edad7b1dcfb927466d6e182ece3c47dba59bb1a56cfc36ab2f1
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78161b5bd61ca75105aa22c7ec70c63ad11bb555ba9c9c64656e2571ae3851d2
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eaeb48e200f968f947a27f3273989ac9c84eed53717a4da271e485c8fd0bcaf6
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38427b000092d784bd9287e2a332629f4f797339d63e9536ad50b8bce9141836
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38ac3a6ba782aa2a59f46abe8392553756e13b3be52b8220963ec6ed9d78aca1
size 2580868101

3
checkpoint-600/global_step600/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eed71c2f9be91a7b469947f0e3c5916f5d453d53af5bdfb6bc94bf455a96ae25
size 2580868101

3
checkpoint-600/global_step600/zero_pp_rank_0_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a637ea4e22d67bf6bd00715a59d15f7eb906283ce0fea2439d5f00f6c2665996
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_1_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e968c7162eb225e323be18a3566af158caac6510ec0d050037c69b8f2b381294
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_2_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:83f5f3b1909ff1a1a51282e9965da6aa92b9db841fe0d4033828ceffb999de5d
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_3_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f5747da21e457ef836541cf66798786a675d749b98e1b2703b2e4373a70936b2
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_4_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:421c7a60713a7d6efc1ff36eee51b4b06c861605cc4ff955e1ac2c65e577b77e
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_5_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f781969de2301de67ca500cbaeb12ca0e5846b525caf83090090bca56e41714a
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_6_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9554aea63fb62b4193cbc69e9b0130dd95f36c23bd1ad2c44db9b481538708f6
size 156759

3
checkpoint-600/global_step600/zero_pp_rank_7_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97b13b4f90d3890956f68ff6762fd631730ba93ae9b73ffcc19b076f34fec8ce
size 156759

1
checkpoint-600/latest Normal file
View File

@@ -0,0 +1 @@
global_step600

3
checkpoint-600/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b431dee7bf331ad1f1840fe3a55182c596b9965f580dc328b2bdd5bf33931bd
size 3441185608

3
checkpoint-600/rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f8f92cf63e0989759370d24108b469c492c12202403f036015307ce49f12cedc
size 16389

3
checkpoint-600/rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ed40a0a4e9f365d2c6cc004d97e6705894eba46c8be4c160c1455bc3062dee1
size 16389

3
checkpoint-600/rng_state_2.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d688b304d19c260b5cfa471535ed51d7e1d60b3a0d0159dfd1a04b87904a9f42
size 16389

3
checkpoint-600/rng_state_3.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9967425ebcaee80d9b518fa0244d52f739b1b983d87cda71d5fede0c073e9d3b
size 16389

3
checkpoint-600/rng_state_4.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:469900fd39c667ffbd49c3c407c0ba317a1e9f5f9339a99b5d38423b7d0ce6d4
size 16389

3
checkpoint-600/rng_state_5.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:124688471ff2a6e80f2fcefedbf741fb18d08dd539d5bd07a52e81be545142a5
size 16389

3
checkpoint-600/rng_state_6.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1e69f1ced9f992a72c948698e5eb06088610788988cdb2fdbdd624e064319d60
size 16389

3
checkpoint-600/rng_state_7.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a376268a55d6ee10c371c06aa952334c4c6a1af9ea2d71b1951a57367a0c6722
size 16389

3
checkpoint-600/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e43da5c8864d25475680d157e6a16a83d6e24a146c02c8e15b49b768e611e45f
size 1465

3
checkpoint-600/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

30
checkpoint-600/tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"is_local": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

4234
checkpoint-600/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-600/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:165add90fc159a0276935c35029d907531f50a4278b16b40d16b361adb507aec
size 7441

760
checkpoint-600/zero_to_fp32.py Normal file
View File

@@ -0,0 +1,760 @@
#!/usr/bin/env python
# Copyright (c) Microsoft Corporation.
# SPDX-License-Identifier: Apache-2.0
# DeepSpeed Team
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
# application.
#
# example:
# python zero_to_fp32.py . output_dir/
# or
# python zero_to_fp32.py . output_dir/ --safe_serialization
import argparse
import torch
import glob
import math
import os
import re
import gc
import json
import numpy as np
from tqdm import tqdm
from collections import OrderedDict
from dataclasses import dataclass
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
# DeepSpeed data structures it has to be available in the current python environment.
from deepspeed.utils import logger
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
@dataclass
class zero_model_state:
buffers: dict()
param_shapes: dict()
shared_params: list
ds_version: int
frozen_param_shapes: dict()
frozen_param_fragments: dict()
debug = 0
# load to cpu
device = torch.device('cpu')
def atoi(text):
return int(text) if text.isdigit() else text
def natural_keys(text):
'''
alist.sort(key=natural_keys) sorts in human order
http://nedbatchelder.com/blog/200712/human_sorting.html
(See Toothy's implementation in the comments)
'''
return [atoi(c) for c in re.split(r'(\d+)', text)]
def get_model_state_file(checkpoint_dir, zero_stage):
if not os.path.isdir(checkpoint_dir):
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
# there should be only one file
if zero_stage <= 2:
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
elif zero_stage == 3:
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
if not os.path.exists(file):
raise FileNotFoundError(f"can't find model states file at '{file}'")
return file
def get_checkpoint_files(checkpoint_dir, glob_pattern):
# XXX: need to test that this simple glob rule works for multi-node setup too
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
if len(ckpt_files) == 0:
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
return ckpt_files
def get_optim_files(checkpoint_dir):
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
def get_model_state_files(checkpoint_dir):
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
def parse_model_states(files):
zero_model_states = []
for file in files:
state_dict = torch.load(file, map_location=device, weights_only=False)
if BUFFER_NAMES not in state_dict:
raise ValueError(f"{file} is not a model state checkpoint")
buffer_names = state_dict[BUFFER_NAMES]
if debug:
print("Found buffers:", buffer_names)
# recover just the buffers while restoring them to fp32 if they were saved in fp16
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
param_shapes = state_dict[PARAM_SHAPES]
# collect parameters that are included in param_shapes
param_names = []
for s in param_shapes:
for name in s.keys():
param_names.append(name)
# update with frozen parameters
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
if frozen_param_shapes is not None:
if debug:
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
param_names += list(frozen_param_shapes.keys())
# handle shared params
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
ds_version = state_dict.get(DS_VERSION, None)
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
z_model_state = zero_model_state(buffers=buffers,
param_shapes=param_shapes,
shared_params=shared_params,
ds_version=ds_version,
frozen_param_shapes=frozen_param_shapes,
frozen_param_fragments=frozen_param_fragments)
zero_model_states.append(z_model_state)
return zero_model_states
def parse_optim_states(files, ds_checkpoint_dir):
total_files = len(files)
state_dicts = []
for f in tqdm(files, desc='Loading checkpoint shards'):
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
# and also handle the case where it was already removed by another helper script
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
state_dicts.append(state_dict)
if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
raise ValueError(f"{files[0]} is not a zero checkpoint")
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
# parameters can be different from data parallelism for non-expert parameters. So we can just
# use the max of the partition_count to get the dp world_size.
if type(world_size) is list:
world_size = max(world_size)
if world_size != total_files:
raise ValueError(
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
)
# the groups are named differently in each stage
if zero_stage <= 2:
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
elif zero_stage == 3:
fp32_groups_key = FP32_FLAT_GROUPS
else:
raise ValueError(f"unknown zero stage {zero_stage}")
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
return zero_stage, world_size, fp32_flat_groups
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
"""
Returns fp32 state_dict reconstructed from ds checkpoint
Args:
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
"""
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
optim_files = get_optim_files(ds_checkpoint_dir)
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
model_files = get_model_state_files(ds_checkpoint_dir)
zero_model_states = parse_model_states(model_files)
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
if zero_stage <= 2:
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters)
elif zero_stage == 3:
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters)
def _zero2_merge_frozen_params(state_dict, zero_model_states):
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
return
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
if debug:
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
wanted_params = len(frozen_param_shapes)
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
print(f'Frozen params: Have {avail_numel} numels to process.')
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
total_params = 0
total_numel = 0
for name, shape in frozen_param_shapes.items():
total_params += 1
unpartitioned_numel = shape.numel()
total_numel += unpartitioned_numel
state_dict[name] = frozen_param_fragments[name]
if debug:
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
def _has_callable(obj, fn):
attr = getattr(obj, fn, None)
return callable(attr)
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
param_shapes = zero_model_states[0].param_shapes
# Reconstruction protocol:
#
# XXX: document this
if debug:
for i in range(world_size):
for j in range(len(fp32_flat_groups[0])):
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
# XXX: memory usage doubles here (zero2)
num_param_groups = len(fp32_flat_groups[0])
merged_single_partition_of_fp32_groups = []
for i in range(num_param_groups):
merged_partitions = [sd[i] for sd in fp32_flat_groups]
full_single_fp32_vector = torch.cat(merged_partitions, 0)
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
avail_numel = sum(
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
if debug:
wanted_params = sum([len(shapes) for shapes in param_shapes])
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
# not asserting if there is a mismatch due to possible padding
print(f"Have {avail_numel} numels to process.")
print(f"Need {wanted_numel} numels in {wanted_params} params.")
# params
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
# out-of-core computing solution
total_numel = 0
total_params = 0
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
offset = 0
avail_numel = full_single_fp32_vector.numel()
for name, shape in shapes.items():
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
total_numel += unpartitioned_numel
total_params += 1
if debug:
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
offset += unpartitioned_numel
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
# live optimizer object, so we are checking that the numbers are within the right range
align_to = 2 * world_size
def zero2_align(x):
return align_to * math.ceil(x / align_to)
if debug:
print(f"original offset={offset}, avail_numel={avail_numel}")
offset = zero2_align(offset)
avail_numel = zero2_align(avail_numel)
if debug:
print(f"aligned offset={offset}, avail_numel={avail_numel}")
# Sanity check
if offset != avail_numel:
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters):
state_dict = OrderedDict()
# buffers
buffers = zero_model_states[0].buffers
state_dict.update(buffers)
if debug:
print(f"added {len(buffers)} buffers")
if not exclude_frozen_parameters:
_zero2_merge_frozen_params(state_dict, zero_model_states)
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
# recover shared parameters
for pair in zero_model_states[0].shared_params:
if pair[1] in state_dict:
state_dict[pair[0]] = state_dict[pair[1]]
return state_dict
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
remainder = unpartitioned_numel % world_size
padding_numel = (world_size - remainder) if remainder else 0
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
return partitioned_numel, padding_numel
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
return
if debug:
for i in range(world_size):
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
wanted_params = len(frozen_param_shapes)
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
print(f'Frozen params: Have {avail_numel} numels to process.')
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
total_params = 0
total_numel = 0
for name, shape in zero_model_states[0].frozen_param_shapes.items():
total_params += 1
unpartitioned_numel = shape.numel()
total_numel += unpartitioned_numel
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
if debug:
print(
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
)
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
class GatheredTensor:
"""
A pseudo tensor that collects partitioned weights.
It is more memory efficient when there are multiple groups.
"""
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
self.flat_groups = flat_groups
self.flat_groups_offset = flat_groups_offset
self.offset = offset
self.partitioned_numel = partitioned_numel
self.shape = shape
self.dtype = self.flat_groups[0][0].dtype
def contiguous(self):
"""
Merge partitioned weights from flat_groups into a single tensor.
"""
end_idx = self.offset + self.partitioned_numel
world_size = len(self.flat_groups)
pad_flat_param_chunks = []
for rank_i in range(world_size):
# for each rank, we need to collect weights from related group/groups
flat_groups_at_rank_i = self.flat_groups[rank_i]
start_group_id = None
end_group_id = None
for group_id in range(len(self.flat_groups_offset)):
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
start_group_id = group_id
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
end_group_id = group_id
break
# collect weights from related group/groups
for group_id in range(start_group_id, end_group_id + 1):
flat_tensor = flat_groups_at_rank_i[group_id]
start_offset = self.offset - self.flat_groups_offset[group_id]
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
# collect weights from all ranks
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
return param
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
param_shapes = zero_model_states[0].param_shapes
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
# param, re-consolidating each param, while dealing with padding if any
# merge list of dicts, preserving order
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
if debug:
for i in range(world_size):
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
wanted_params = len(param_shapes)
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
# not asserting if there is a mismatch due to possible padding
avail_numel = fp32_flat_groups[0].numel() * world_size
print(f"Trainable params: Have {avail_numel} numels to process.")
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
# params
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
# out-of-core computing solution
offset = 0
total_numel = 0
total_params = 0
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
unpartitioned_numel = shape.numel()
total_numel += unpartitioned_numel
total_params += 1
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
if debug:
print(
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
)
# memory efficient tensor
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
state_dict[name] = tensor
offset += partitioned_numel
offset *= world_size
# Sanity check
if offset != avail_numel:
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters):
state_dict = OrderedDict()
# buffers
buffers = zero_model_states[0].buffers
state_dict.update(buffers)
if debug:
print(f"added {len(buffers)} buffers")
if not exclude_frozen_parameters:
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
# recover shared parameters
for pair in zero_model_states[0].shared_params:
if pair[1] in state_dict:
state_dict[pair[0]] = state_dict[pair[1]]
return state_dict
def to_torch_tensor(state_dict, return_empty_tensor=False):
"""
Convert state_dict of GatheredTensor to torch tensor
"""
torch_state_dict = {}
converted_tensors = {}
for name, tensor in state_dict.items():
tensor_id = id(tensor)
if tensor_id in converted_tensors: # shared tensors
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
torch_state_dict[name] = shared_tensor
else:
converted_tensors[tensor_id] = name
if return_empty_tensor:
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
else:
torch_state_dict[name] = tensor.contiguous()
return torch_state_dict
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
tag=None,
exclude_frozen_parameters=False,
lazy_mode=False):
"""
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
via a model hub.
Args:
- ``checkpoint_dir``: path to the desired checkpoint folder
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
- ``exclude_frozen_parameters``: exclude frozen parameters
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
Convert the pesduo tensor to torch tensor by ``.contiguous()``
Returns:
- pytorch ``state_dict``
A typical usage might be ::
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
# do the training and checkpoint saving
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
model = model.cpu() # move to cpu
model.load_state_dict(state_dict)
# submit to model hub or save the model to share with others
In this example the ``model`` will no longer be usable in the deepspeed context of the same
application. i.e. you will need to re-initialize the deepspeed engine, since
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
the checkpoint. Or you can load state_dict in lazy mode ::
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
for name, lazy_tensor in state_dict.item():
tensor = lazy_tensor.contiguous() # to cpu
print(name, tensor)
# del tensor to release memory if it no longer in use
"""
if tag is None:
latest_path = os.path.join(checkpoint_dir, 'latest')
if os.path.isfile(latest_path):
with open(latest_path, 'r') as fd:
tag = fd.read().strip()
else:
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
if not os.path.isdir(ds_checkpoint_dir):
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
if lazy_mode:
return state_dict
else:
return to_torch_tensor(state_dict)
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
output_dir,
max_shard_size="5GB",
safe_serialization=False,
tag=None,
exclude_frozen_parameters=False):
"""
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
Args:
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
- ``output_dir``: directory to the pytorch fp32 state_dict output files
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
- ``exclude_frozen_parameters``: exclude frozen parameters
"""
# Dependency pre-check
if safe_serialization:
try:
from safetensors.torch import save_file
except ImportError:
print('If you want to use `safe_serialization`, please `pip install safetensors`')
raise
if max_shard_size is not None:
try:
from huggingface_hub import split_torch_state_dict_into_shards
except ImportError:
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
raise
# Convert zero checkpoint to state_dict
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
tag,
exclude_frozen_parameters,
lazy_mode=True)
# Shard the model if it is too big.
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
if max_shard_size is not None:
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
# an memory-efficient approach for sharding
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
filename_pattern=filename_pattern,
max_shard_size=max_shard_size)
else:
from collections import namedtuple
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
state_dict_split = StateDictSplit(is_sharded=False,
filename_to_tensors={weights_name: list(state_dict.keys())})
# Save the model by shard
os.makedirs(output_dir, exist_ok=True)
filename_to_tensors = state_dict_split.filename_to_tensors.items()
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
shard_state_dict = to_torch_tensor(shard_state_dict)
output_path = os.path.join(output_dir, shard_file)
if safe_serialization:
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
else:
torch.save(shard_state_dict, output_path)
# release the memory of current shard
for tensor_name in list(shard_state_dict.keys()):
del state_dict[tensor_name]
del shard_state_dict[tensor_name]
del shard_state_dict
gc.collect()
# Save index if sharded
if state_dict_split.is_sharded:
index = {
"metadata": state_dict_split.metadata,
"weight_map": state_dict_split.tensor_to_filename,
}
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
save_index_file = os.path.join(output_dir, save_index_file)
with open(save_index_file, "w", encoding="utf-8") as f:
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
f.write(content)
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
"""
1. Put the provided model to cpu
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
3. Load it into the provided model
Args:
- ``model``: the model object to update
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
Returns:
- ``model`: modified model
Make sure you have plenty of CPU memory available before you call this function. If you don't
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
conveniently placed for you in the checkpoint folder.
A typical usage might be ::
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
# submit to model hub or save the model to share with others
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
"""
logger.info("Extracting fp32 weights")
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
logger.info("Overwriting model with fp32 weights")
model = model.cpu()
model.load_state_dict(state_dict, strict=False)
return model
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("checkpoint_dir",
type=str,
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
parser.add_argument("output_dir",
type=str,
help="directory to the pytorch fp32 state_dict output files"
"(e.g. path/checkpoint-12-output/)")
parser.add_argument(
"--max_shard_size",
type=str,
default="5GB",
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
"without CPU OOM issues.")
parser.add_argument(
"--safe_serialization",
default=False,
action='store_true',
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
parser.add_argument("-t",
"--tag",
type=str,
default=None,
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
args = parser.parse_args()
debug = args.debug
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
args.output_dir,
max_shard_size=args.max_shard_size,
safe_serialization=args.safe_serialization,
tag=args.tag,
exclude_frozen_parameters=args.exclude_frozen_parameters)