theblackcat102/galactica-1.3b-conversation-finetuned
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: theblackcat102/galactica-1.3b-conversation-finetuned
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-22 11:55:38 +08:00
commit 7bd019c20a
10 changed files with 102348 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

65
README.md Normal file
View File

@@ -0,0 +1,65 @@
---
license: afl-3.0
language:
- en
widget:
- text: "<question>What's my name?<answer>"
example_title: "Who am I?"
- text: "<question>How to make a campfire<answer>"
example_title: "Tutorial"
---
# Supervised Finetuning demonstration
Models are finetuned on generated conversation curated from the [Open Assistant](https://github.com/LAION-AI/Open-Assistant).
# Mixing reward model with sampling
We can use reward model to rank the best answer using this example code:
```
import torch
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-1.3b-base-finetuned/checkpoint-1000")
model = AutoModelForCausalLM.from_pretrained("facebook/galactica-1.3b-base-finetuned/checkpoint-1000").eval().half().cuda()
reward_name = "theblackcat102/electra-large-reward-model"
rank_model, rank_tokenizer = AutoModelForSequenceClassification.from_pretrained(reward_name), AutoTokenizer.from_pretrained(reward_name)
rank_model = rank_model.eval().half().cuda()
questions = ["<question>How do I make a resume?<answer>"]
for question in questions:
inputs = tokenizer(question, return_tensors="pt", padding=True).to(0)
if 'token_type_ids' in inputs:
inputs.pop('token_type_ids')
outputs = model.generate(**inputs, do_sample=True,
top_k=60,
max_length=220,
num_return_sequences=80,
early_stopping=True
)
print(question)
results = []
for i, beam_output in enumerate(outputs):
output = tokenizer.decode(beam_output, truncate_before_pattern=[r"\n\n^#", "^'''", "\n\n\n"])
question, answer = output.split('<answer>', maxsplit=1)
answer = answer.split('<question>')[0].replace('<|endoftext|>', '').lstrip().split('<answer>')[0]
rank_inputs = rank_tokenizer(question, answer, return_tensors="pt", padding=True, max_length=512, truncation=True).to(1)
score = rank_model(**rank_inputs).logits[0].cpu().detach()
results.append((answer, score, output))
full_results[question] = results
sorted_result = sorted(results, key=lambda x:x[1], reverse=True)
total_scores += sorted_result[0][1].item()
print('score',sorted_result[0][1].item())
print('-----Best rank-----')
print(sorted_result[0][0])
print('-------------------')
```
Checkout weights and biases [report](https://api.wandb.ai/report/theblackcat102/8yg0c0r2) for training detail.
Thanks to [BASIC lab](https://basiclab.lab.nycu.edu.tw/Yummy/index.html#) for compute resource. BASIC Lab is an academic research lab which focuses in multi-modality learning and data mining domain.

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_name_or_path": "facebook/galactica-1.3b",
"_remove_final_layer_norm": false,
"activation_dropout": 0.0,
"activation_function": "gelu",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"do_layer_norm_before": true,
"dropout": 0.1,
"enable_bias": true,
"eos_token_id": 2,
"ffn_dim": 8192,
"hidden_size": 2048,
"init_std": 0.02,
"layer_norm_elementwise_affine": true,
"layerdrop": 0.0,
"learned_embeddings": true,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"pad_token_id": 1,
"scale_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.25.1",
"use_cache": true,
"vocab_size": 50002,
"word_embed_proj_dim": 2048
}

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37f3def097356b3be26f8a392ccd4c39aa7ea999f705035efdf31dc8a728c486
size 2630533369

8
special_tokens_map.json Normal file
View File

@@ -0,0 +1,8 @@
{
"additional_special_tokens": [
"<question>",
"<answer>"
],
"eos_token": "</s>",
"pad_token": "<pad>"
}

100019
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

6
tokenizer_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "facebook/galactica-1.3b",
"special_tokens_map_file": "/content/tokenizer/special_tokens_map.json",
"tokenizer_class": "PreTrainedTokenizerFast"
}

1696
trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eb9607fb0053bbe67a5f7e6792f0aaef0aa879aef697c0b5c8814f6482f93625
size 4719

482
zero_to_fp32.py Normal file
View File

@@ -0,0 +1,482 @@
#!/usr/bin/env python
# This script extracts fp32 consolidated weights from a zero 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 . pytorch_model.bin
import argparse
import torch
import glob
import math
import os
import re
from collections import OrderedDict
# 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)
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_optim_files(checkpoint_dir):
# XXX: need to test that this simple glob rule works for multi-node setup too
optim_files = sorted(glob.glob(os.path.join(checkpoint_dir,
"*_optim_states.pt")),
key=natural_keys)
if len(optim_files) == 0:
raise FileNotFoundError(
f"can't find '*_optim_states.pt' files in directory '{checkpoint_dir}'")
return optim_files
def parse_model_state(file):
state_dict = torch.load(file, map_location=device)
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]
ds_version = state_dict.get(DS_VERSION, None)
return buffers, param_shapes, ds_version
def parse_optim_states(files, ds_checkpoint_dir):
total_files = len(files)
state_dicts = []
for f in files:
state_dicts.append(torch.load(f, map_location=device))
if not ZERO_STAGE 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}")
if zero_stage == 2:
fp32_flat_groups = [
state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key]
for i in range(len(state_dicts))
]
elif zero_stage == 3:
# if there is more than one param group, there will be multiple flattened tensors - one
# flattened tensor per group - for simplicity merge them into a single tensor
#
# XXX: could make the script more memory efficient for when there are multiple groups - it
# will require matching the sub-lists of param_shapes for each param group flattened tensor
fp32_flat_groups = [
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key],
0) 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):
"""
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_file = get_model_state_file(ds_checkpoint_dir, zero_stage)
buffers, param_shapes, ds_version = parse_model_state(model_file)
print(f'Parsing checkpoint created by deepspeed=={ds_version}')
if zero_stage == 2:
return _get_fp32_state_dict_from_zero2_checkpoint(world_size,
param_shapes,
fp32_flat_groups,
buffers)
elif zero_stage == 3:
return _get_fp32_state_dict_from_zero3_checkpoint(world_size,
param_shapes,
fp32_flat_groups,
buffers)
def _get_fp32_state_dict_from_zero2_checkpoint(world_size,
param_shapes,
fp32_flat_groups,
buffers):
# 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.")
state_dict = OrderedDict()
# buffers
state_dict.update(buffers)
if debug:
print(f"added {len(buffers)} buffers")
# 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()
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"
)
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 _get_fp32_state_dict_from_zero3_checkpoint(world_size,
param_shapes,
fp32_flat_groups,
buffers):
# 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
avail_numel = fp32_flat_groups[0].numel() * world_size
# 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
print(f"Have {avail_numel} numels to process.")
print(f"Need {wanted_numel} numels in {wanted_params} params.")
state_dict = OrderedDict()
# buffers
state_dict.update(buffers)
if debug:
print(f"added {len(buffers)} buffers")
# 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
for name, shape in param_shapes.items():
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"{total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
)
# XXX: memory usage doubles here
state_dict[name] = torch.cat(
tuple(fp32_flat_groups[i].narrow(0,
offset,
partitioned_numel)
for i in range(world_size)),
0).narrow(0,
0,
unpartitioned_numel).view(shape)
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 fp32 state dict with {total_params} params {total_numel} elements"
)
return state_dict
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
"""
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``
Returns:
- pytorch ``state_dict``
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
the checkpoint.
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.
"""
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")
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
"""
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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
- ``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``
"""
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
print(f"Saving fp32 state dict to {output_file}")
torch.save(state_dict, output_file)
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(f"Extracting fp32 weights")
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
logger.info(f"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_file",
type=str,
help=
"path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)"
)
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_file)