初始化项目，由ModelHub XC社区提供模型

Model: alv001/MiniGpt-4-7B
Source: Original Platform

.gitattributes

@@ -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
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+tasks:
+- text-generation
+model-type:
+- glm
+domain:
+- nlp
+studios:
+- AI-ModelScope/MiniGpt-7B-unofficial
+frameworks:
+- pytorch
+backbone:
+- transformer
+metrics:
+- CER
+license: Apache License 2.0
+language: 
+- cn
+tags:
+- 文本生成
+- text-generation
+- Minigpt-7b
+- 中英
+
+---
+```bash
+ git clone https://www.modelscope.cn/alv001/minigpt.git
+```
+### 须知
+## 无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可
+无需在量化模型，直接使用即可

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/Users/tdo/Desktop/7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1,11 @@
+{
+    "framework": "pytorch",
+    "task": "text-generation",
+    "pipeline": {
+        "type": "minigpt-7b-text-generation"
+    },
+    "preprocessor": {
+        "type": "minigpt-7b-text-preprocessor"
+    },
+    "allow_remote": true
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0.dev0"
+}

ms_wrapper.py

@@ -0,0 +1,106 @@
+# Copyright (c) 2022 Zhipu.AI
+import copy
+from typing import Optional, Tuple, Union, List, Callable, Dict, Any
+from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig
+from transformers.generation.logits_process import LogitsProcessor
+
+import torch
+
+from modelscope.models.base import Model, TorchModel
+from modelscope.models.builder import MODELS
+from modelscope.outputs import OutputKeys
+from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+from modelscope.pipelines.base import Pipeline
+from modelscope.pipelines.builder import PIPELINES
+from modelscope.preprocessors import Preprocessor
+from modelscope.utils.constant import Tasks
+
+
+from transformers import AutoTokenizer,LlamaForCausalLM
+from transformers import PreTrainedModel, PreTrainedTokenizer
+
+
+@MODELS.register_module(Tasks.text_generation, module_name='minigpt7b')
+class MiniGPT7bForTextGeneration(TorchModel):
+
+    def __init__(self, model_dir: str, *args, **kwargs):
+        """initialize the minigpt7b from the `model_dir` path.
+
+        Args:
+            model_dir (str): the model path.
+        """
+        super().__init__(model_dir, *args, **kwargs)
+        self.logger = get_logger()
+        self.device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
+        # loading tokenizer
+        self.tokenizer = AutoTokenizer.from_pretrained(model_dir)
+        # loading model
+        self.model = LlamaForCausalLM.from_pretrained(model_dir,torch_dtype=torch.float16)
+        
+
+
+    def answer(self, inputs, max_new_tokens=300, num_beams=1, min_length=1, top_p=0.9,
+               repetition_penalty=1.0, length_penalty=1, temperature=1.0, max_length=2000,device=None):
+
+        input_ids = self.tokenizer(inputs, return_tensors="pt").input_ids
+        input_ids = input_ids.to(device)
+        model_ids = self.model.to(device)
+        outputs = model_ids.generate(
+            #inputs_embeds=embs,
+            input_ids,
+            max_new_tokens=max_new_tokens,
+            #stopping_criteria=self.stopping_criteria,
+            num_beams=num_beams,
+            do_sample=True,
+            min_length=min_length,
+            top_p=top_p,
+            repetition_penalty=repetition_penalty,
+            length_penalty=length_penalty,
+            temperature=temperature,
+        )
+        
+        rets = self.tokenizer.batch_decode(outputs, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+
+        return rets
+
+
+    def forward(self, input: Dict) -> Dict:
+        output = {}
+        res = self.answer(input,device=self.device)
+        output['text'] = res
+        return output
+
+    def quantize(self, bits: int):
+        self.model = self.model.quantize(bits)
+        return self
+
+
+@PIPELINES.register_module(
+    group_key=Tasks.text_generation,
+    module_name='minigpt-7b-text-generation')
+class MiniGPT7bTextGenerationPipeline(Pipeline):
+
+    def __init__(self,
+                 model: Union[Model, str],
+                 preprocessor: [Preprocessor] = None,
+                 *args,
+                 **kwargs):
+        model = MiniGPT7bForTextGeneration(model) if isinstance(model,
+                                                               str) else model
+        self.model = model
+        self.model.eval()
+
+        super().__init__(model=model, **kwargs)
+
+    def preprocess(self, inputs, **preprocess_params) -> Dict[str, Any]:
+        return inputs
+
+    # define the forward pass
+    def forward(self, inputs: Dict, **forward_params) -> Dict[str, Any]:
+        return self.model(inputs)
+
+    # format the outputs from pipeline
+    def postprocess(self, input, **kwargs) -> Dict[str, Any]:
+        return input
+    

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed572be140240b212049a3e791271eed8a04c40bc732c91a4da4b1469db23b1
+size 9976634558

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9382da358f0ec38c4fca3bcf1e3e65274ae4c78090e0775b4bb4dea6a518e08
+size 3500315539

requirements.txt

@@ -0,0 +1,49 @@
+accelerate==0.16.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+async-timeout==4.0.2
+attrs==22.2.0
+bitsandbytes==0.37.0
+cchardet==2.1.7
+chardet==5.1.0
+contourpy==1.0.7
+cycler==0.11.0
+filelock==3.9.0
+fonttools==4.38.0
+frozenlist==1.3.3
+huggingface-hub==0.13.4
+importlib-resources==5.12.0
+kiwisolver==1.4.4
+matplotlib==3.7.0
+multidict==6.0.4
+openai==0.27.0
+packaging==23.0
+psutil==5.9.4
+pycocotools==2.0.6
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pyyaml==6.0
+regex==2022.10.31
+tokenizers==0.13.3
+tqdm==4.64.1
+transformers==4.28.0
+timm==0.6.13
+spacy==3.5.1
+webdataset==0.2.48
+scikit-learn==1.2.2
+scipy==1.10.1
+yarl==1.8.2
+zipp==3.14.0
+omegaconf==2.3.0
+opencv-python==4.7.0.72
+iopath==0.1.10
+decord==0.6.0
+tenacity==8.2.2
+peft
+pycocoevalcap
+sentence-transformers
+umap-learn
+notebook
+gradio==3.24.1
+gradio-client==0.0.8
+wandb

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}