Skip to content

GitLab

Commit 4488627c authored by wangsen's avatar wangsen
Browse files

Update examples/1.jpeg, examples/2.jpeg, examples/3.jpeg, examples/WECHAT.md,... 

Update examples/1.jpeg, examples/2.jpeg, examples/3.jpeg, examples/WECHAT.md, examples/chat_example1.png, examples/chat_example2.png, examples/chat_example3.png, examples/example_inputs.jsonl, examples/thu.png, examples/web_demo.png, examples/wechat.jpg, web_demo.py files
Deleted requirements, requirements.txt, requirements_wo_ds.txt, MODEL_LICENSE.txt, LICENSE.txt, finetune_visualglm.py, cli_demo_mp.py, api_hf.py, web_demo_hf.py files
parent 416736ea
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 566 deletions
LICENSE.txt deleted 100644 → 0
View file @ 416736ea
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright Zhengxiao Du
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
\ No newline at end of file
MODEL_LICENSE.txt deleted 100644 → 0
View file @ 416736ea
The VisualGLM-6B License
1. Definitions
“Licensor” means the VisualGLM-6B Model Team that distributes its Software.
“Software” means the VisualGLM-6B model parameters made available under this license.
2. License Grant
Subject to the terms and conditions of this License, the Licensor hereby grants to you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty-free copyright license to use the Software solely for your non-commercial research purposes.
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
3. Restriction
You will not use, copy, modify, merge, publish, distribute, reproduce, or create derivative works of the Software, in whole or in part, for any commercial, military, or illegal purposes.
You will not use the Software for any act that may undermine China's national security and national unity, harm the public interest of society, or infringe upon the rights and interests of human beings.
4. Disclaimer
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
5. Limitation of Liability
EXCEPT TO THE EXTENT PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER BASED IN TORT, NEGLIGENCE, CONTRACT, LIABILITY, OR OTHERWISE WILL ANY LICENSOR BE LIABLE TO YOU FOR ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES, OR ANY OTHER COMMERCIAL LOSSES, EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
6. Dispute Resolution
This license shall be governed and construed in accordance with the laws of People’s Republic of China. Any dispute arising from or in connection with this License shall be submitted to Haidian District People's Court in Beijing.
Note that the license is subject to update to a more comprehensive version. For any questions related to the license and copyright, please contact us.
api_hf.py deleted 100644 → 0
View file @ 416736ea
import os
import json
from transformers import AutoTokenizer, AutoModel
import uvicorn
from fastapi import FastAPI, Request
import datetime
from model import process_image
import torch
tokenizer = AutoTokenizer.from_pretrained("THUDM/visualglm-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/visualglm-6b", trust_remote_code=True).half().cuda()
app = FastAPI()
@app.post('/')
async def visual_glm(request: Request):
json_post_raw = await request.json()
print("Start to process request")
json_post = json.dumps(json_post_raw)
request_data = json.loads(json_post)
history = request_data.get("history")
image_encoded = request_data.get("image")
query = request_data.get("text")
image_path = process_image(image_encoded)
with torch.no_grad():
result = model.stream_chat(tokenizer, image_path, query, history=history)
last_result = None
for value in result:
last_result = value
answer = last_result[0]
if os.path.isfile(image_path):
os.remove(image_path)
now = datetime.datetime.now()
time = now.strftime("%Y-%m-%d %H:%M:%S")
response = {
"result": answer,
"history": history,
"status": 200,
"time": time
}
return response
if __name__ == "__main__":
uvicorn.run(app, host='0.0.0.0', port=8080, workers=1)
\ No newline at end of file
cli_demo_mp.py deleted 100644 → 0
View file @ 416736ea
# -*- encoding: utf-8 -*-
import os
import sys
import torch
import argparse
from transformers import AutoTokenizer
from sat.model.mixins import CachedAutoregressiveMixin
from sat.quantization.kernels import quantize
from model import VisualGLMModel, chat
from finetune_visualglm import FineTuneVisualGLMModel
from sat.model import AutoModel
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--max_length", type=int, default=2048, help='max length of the total sequence')
parser.add_argument("--top_p", type=float, default=0.4, help='top p for nucleus sampling')
parser.add_argument("--top_k", type=int, default=100, help='top k for top k sampling')
parser.add_argument("--temperature", type=float, default=.8, help='temperature for sampling')
parser.add_argument("--english", action='store_true', help='only output English')
parser.add_argument("--quant", choices=[8, 4], type=int, default=None, help='quantization bits')
parser.add_argument("--from_pretrained", type=str, default="/data", help='pretrained ckpt')
parser.add_argument("--prompt_zh", type=str, default="描述这张图片。", help='Chinese prompt for the first round')
parser.add_argument("--prompt_en", type=str, default="Describe the image.", help='English prompt for the first round')
args = parser.parse_args()
# load model
model, model_args = AutoModel.from_pretrained(
args.from_pretrained,
args=argparse.Namespace(
fp16=True,
skip_init=True,
use_gpu_initialization=True if (torch.cuda.is_available() and args.quant is None) else False,
device='cuda' if (torch.cuda.is_available() and args.quant is None) else 'cpu',
), overwrite_args={'model_parallel_size': 2})
model = model.eval()
if args.quant:
quantize(model.transformer, args.quant)
if torch.cuda.is_available():
model = model.cuda()
model.add_mixin('auto-regressive', CachedAutoregressiveMixin())
tokenizer = AutoTokenizer.from_pretrained("/data", trust_remote_code=True)
image_path = 'fewshot-data/meme.png'
query = args.prompt_en if args.english else args.prompt_zh
history = None
cache_image = None
response, history, cache_image = chat(
image_path,
model,
tokenizer,
query,
history=history,
image=cache_image,
max_length=args.max_length,
top_p=args.top_p,
temperature=args.temperature,
top_k=args.top_k,
english=args.english,
invalid_slices=[slice(63823, 130000)] if args.english else []
)
sep = 'A:' if args.english else '答：'
print(response.split(sep)[-1].strip())
if __name__ == "__main__":
main()
finetune_visualglm.py deleted 100644 → 0
View file @ 416736ea
import os
import torch
import argparse
from sat import mpu, get_args, get_tokenizer
from sat.training.deepspeed_training import training_main
from model import VisualGLMModel
from sat.model.finetune import PTuningV2Mixin
from sat.model.finetune.lora2 import LoraMixin
class FineTuneVisualGLMModel(VisualGLMModel):
def __init__(self, args, transformer=None, parallel_output=True, **kw_args):
super().__init__(args, transformer=transformer, parallel_output=parallel_output, **kw_args)
if args.use_ptuning:
self.add_mixin("ptuning", PTuningV2Mixin(args.num_layers, args.hidden_size // args.num_attention_heads, args.num_attention_heads, args.pre_seq_len))
if args.use_lora:
self.add_mixin("lora", LoraMixin(args.num_layers, args.lora_rank, layer_range=args.layer_range), reinit=True)
# self.get_mixin("eva").model.glm_proj = replace_linear_with_lora(self.get_mixin("eva").model.glm_proj, LoraLinear, args.lora_rank)
elif args.use_qlora:
self.add_mixin("lora", LoraMixin(args.num_layers, args.lora_rank, layer_range=args.layer_range, qlora=True), reinit=True)
self.args = args
@classmethod
def add_model_specific_args(cls, parser):
group = parser.add_argument_group('VisualGLM-finetune', 'VisualGLM finetune Configurations')
group.add_argument('--pre_seq_len', type=int, default=8)
group.add_argument('--lora_rank', type=int, default=10)
group.add_argument('--use_ptuning', action="store_true")
group.add_argument('--use_lora', action="store_true")
group.add_argument('--use_qlora', action="store_true")
group.add_argument('--layer_range', nargs='+', type=int, default=None)
return super().add_model_specific_args(parser)
def disable_untrainable_params(self):
enable = []
if self.args.use_ptuning:
enable.extend(['ptuning'])
if self.args.use_lora or self.args.use_qlora:
enable.extend(['matrix_A', 'matrix_B'])
for n, p in self.named_parameters():
flag = False
for e in enable:
if e.lower() in n.lower():
flag = True
break
if not flag:
p.requires_grad_(False)
else:
print(n)
def get_batch(data_iterator, args, timers):
# Items and their type.
keys = ['input_ids', 'labels']
datatype = torch.int64
# Broadcast data.
timers('data loader').start()
if data_iterator is not None:
data = next(data_iterator)
else:
data = None
timers('data loader').stop()
data_b = mpu.broadcast_data(keys, data, datatype)
data_i = mpu.broadcast_data(['image'], data, torch.float32)
# Unpack.
tokens = data_b['input_ids'].long()
labels = data_b['labels'].long()
img = data_i['image']
if args.fp16:
img = img.half()
return tokens, labels, img, data['pre_image']
from torch.nn import CrossEntropyLoss
def forward_step(data_iterator, model, args, timers):
"""Forward step."""
# Get the batch.
timers('batch generator').start()
tokens, labels, image, pre_image = get_batch(
data_iterator, args, timers)
timers('batch generator').stop()
logits = model(input_ids=tokens, image=image, pre_image=pre_image)[0]
dtype = logits.dtype
lm_logits = logits.to(torch.float32)
# Shift so that tokens < n predict n
shift_logits = lm_logits[..., :-1, :].contiguous()
shift_labels = labels[..., 1:].contiguous()
# Flatten the tokens
loss_fct = CrossEntropyLoss(ignore_index=-100)
loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
lm_logits = lm_logits.to(dtype)
loss = loss.to(dtype)
return loss, {'loss': loss}
from model.blip2 import BlipImageEvalProcessor
from torch.utils.data import Dataset
import json
from PIL import Image
class FewShotDataset(Dataset):
def __init__(self, path, processor, tokenizer, args):
max_seq_length = args.max_source_length + args.max_target_length
with open(path, 'r', encoding='utf-8') as f:
data = json.load(f)
self.images = []
self.input_ids = []
self.labels = []
for item in data:
image = processor(Image.open(item['img']).convert('RGB'))
input0 = tokenizer.encode("<img>", add_special_tokens=False)
input1 = [tokenizer.pad_token_id] * args.image_length
input2 = tokenizer.encode("</img>问："+item['prompt']+"\n答：", add_special_tokens=False)
a_ids = sum([input0, input1, input2], [])
b_ids = tokenizer.encode(text=item['label'], add_special_tokens=False)
if len(a_ids) > args.max_source_length - 1:
a_ids = a_ids[: args.max_source_length - 1]
if len(b_ids) > args.max_target_length - 2:
b_ids = b_ids[: args.max_target_length - 2]
pre_image = len(input0)
input_ids = tokenizer.build_inputs_with_special_tokens(a_ids, b_ids)
context_length = input_ids.index(tokenizer.bos_token_id)
mask_position = context_length - 1
labels = [-100] * context_length + input_ids[mask_position+1:]
pad_len = max_seq_length - len(input_ids)
input_ids = input_ids + [tokenizer.pad_token_id] * pad_len
labels = labels + [tokenizer.pad_token_id] * pad_len
if args.ignore_pad_token_for_loss:
labels = [(l if l != tokenizer.pad_token_id else -100) for l in labels]
self.images.append(image)
self.input_ids.append(input_ids)
self.labels.append(labels)
self.pre_image = pre_image
def __len__(self):
return len(self.images)
def __getitem__(self, idx):
return {
"image": self.images[idx],
"input_ids": self.input_ids[idx],
"labels": self.labels[idx],
"pre_image": self.pre_image
}
def create_dataset_function(path, args):
tokenizer = get_tokenizer(args)
image_processor = BlipImageEvalProcessor(224)
dataset = FewShotDataset(path, image_processor, tokenizer, args)
return dataset
if __name__ == '__main__':
py_parser = argparse.ArgumentParser(add_help=False)
py_parser.add_argument('--max_source_length', type=int)
py_parser.add_argument('--max_target_length', type=int)
py_parser.add_argument('--ignore_pad_token_for_loss', type=bool, default=True)
# py_parser.add_argument('--old_checkpoint', action="store_true")
py_parser.add_argument('--source_prefix', type=str, default="")
py_parser = FineTuneVisualGLMModel.add_model_specific_args(py_parser)
known, args_list = py_parser.parse_known_args()
args = get_args(args_list)
args = argparse.Namespace(**vars(args), **vars(known))
args.device = 'cpu'
model_type = 'visualglm-6b'
model, args = FineTuneVisualGLMModel.from_pretrained(model_type, args)
if torch.cuda.is_available():
model = model.to('cuda')
tokenizer = get_tokenizer(args)
label_pad_token_id = -100 if args.ignore_pad_token_for_loss else tokenizer.pad_token_id
def data_collator(examples):
for example in examples:
example['input_ids'] = torch.tensor(example['input_ids'], dtype=torch.long)
example['labels'] = torch.tensor(example['labels'], dtype=torch.long)
ret = {
'input_ids': torch.stack([example['input_ids'] for example in examples]),
'labels': torch.stack([example['labels'] for example in examples]),
'image': torch.stack([example['image'] for example in examples]),
'pre_image': example['pre_image']
}
return ret
training_main(args, model_cls=model, forward_step_function=forward_step, create_dataset_function=create_dataset_function, collate_fn=data_collator)
\ No newline at end of file
requirements_wo_ds.txt deleted 100644 → 0
View file @ 416736ea
torch>1.10.0
torchvision
transformers>=4.27.1
mdtex2html
gradio
sentencepiece
tensorboardX
datasets
cpm_kernels
einops
web_demo.py
View file @ 4488627c
...@@ -126,4 +126,4 @@ if __name__ == '__main__': ...@@ -126,4 +126,4 @@ if __name__ == '__main__':
parser.add_argument("--share", action="store_true") parser.add_argument("--share", action="store_true")
args = parser.parse_args() args = parser.parse_args()
main(args) main(args)
\ No newline at end of file
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