初始化项目，由ModelHub XC社区提供模型

Model: AI-ModelScope/Vicuna-7B
Source: Original Platform

.gitattributes

@@ -0,0 +1,32 @@
+*.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

README.md

@@ -0,0 +1,85 @@
+---
+license: Apache License 2.0
+tasks:
+- text-generation
+language:
+- en
+library_name: transformers
+inference: false
+widgets:
+  - task: text-generation
+    version: 1
+    inputs:
+      - type: text
+        name: text
+        title: 输入文字
+        validator:
+        max_words: 128
+    examples:
+      - name: 1
+        title: 示例1
+        inputs:
+          - name: text
+            data:  你好
+    inferencespec:
+      cpu: 4
+      memory: 24000
+      gpu: 1
+      gpu_memory: 16000
+---
+**NOTE: This model has delta files applied and can be used directly.**  
+
+
+# Vicuna Model Card
+
+## Model details
+
+```
+pip install fschat
+```
+
+```python
+from modelscope.utils.constant import Tasks
+from modelscope.pipelines import pipeline
+pipe = pipeline(task=Tasks.text_generation, model='AI-ModelScope/Vicuna-7B', model_revision='v1.0.1', device='cuda')
+inputs = '你好'
+result = pipe(inputs)
+print(result)
+
+```
+
+**Model type:**
+Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
+It is an auto-regressive language model, based on the transformer architecture.
+
+**Model date:**
+Vicuna was trained between March 2023 and April 2023.
+
+**Organizations developing the model:**
+The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
+
+**Paper or resources for more information:**
+https://vicuna.lmsys.org/
+
+**License:**
+Apache License 2.0
+
+**Where to send questions or comments about the model:**
+https://github.com/lm-sys/FastChat/issues
+
+## Intended use
+**Primary intended uses:**
+The primary use of Vicuna is research on large language models and chatbots.
+
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
+
+## Training dataset
+70K conversations collected from ShareGPT.com.
+
+## Evaluation dataset
+A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
+
+## Major updates of weights v1.1
+- Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `"</s>"`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
+- Fix the supervised fine-tuning loss computation for better model quality.

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",
+    "model": {
+        "type": "Vicuna7b"
+    },
+    "pipeline": {
+        "type": "Vicuna7b-text-generation-pipe"
+    },
+    "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 +1,77 @@
+import os
+from typing import Any, Dict, Union
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, LlamaTokenizer
+
+from modelscope.models.base import Model, TorchModel
+from modelscope.models.builder import MODELS
+from modelscope.pipelines.base import Pipeline
+from modelscope.pipelines.builder import PIPELINES
+from modelscope.pipelines.nlp.text_generation_pipeline import \
+    TextGenerationPipeline
+from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+
+Vicuna_PROMPT_FORMAT = "### Human:\n{prompt} \n ### Assistant:\n"
+
+@PIPELINES.register_module(Tasks.text_generation,
+                           module_name='Vicuna7b-text-generation-pipe')
+class Vicuna7bTextGenerationPipeline(TextGenerationPipeline):
+    def __init__(self, model: Union[Model, str], *args, **kwargs):
+        model = Vicuna7bTextGeneration(model) if isinstance(model,
+                                                            str) else model
+        super().__init__(model=model, **kwargs)
+
+    def preprocess(self, inputs, **preprocess_params) -> Dict[str, Any]:
+        return inputs
+
+    def _sanitize_parameters(self, **pipeline_parameters):
+        return {}, pipeline_parameters, {}
+
+    # define the forward pass
+    def forward(self, inputs: Dict, **forward_params) -> Dict[str, Any]:
+        return self.model(inputs, **forward_params)
+
+    # format the outputs from pipeline
+    def postprocess(self, input, **kwargs) -> Dict[str, Any]:
+        return input
+
+
+@MODELS.register_module(Tasks.text_generation, module_name='Vicuna7b')
+class Vicuna7bTextGeneration(TorchModel):
+    def __init__(self, model_dir=None, *args, **kwargs):
+        super().__init__(model_dir, *args, **kwargs)
+        self.logger = get_logger()
+        # loading tokenizer
+        self.tokenizer = LlamaTokenizer.from_pretrained(model_dir,
+                                                       use_fast=False)
+        self.model = AutoModelForCausalLM.from_pretrained(
+            model_dir,
+            low_cpu_mem_usage=True,
+            device_map="auto",
+            torch_dtype=torch.float16)
+        self.model = self.model.eval()
+
+    def forward(self, input: Dict, *args, **kwargs) -> Dict[str, Any]:
+        output = {}
+        res = self.infer(input, **kwargs)
+        output['text'] = res
+        return output
+
+    def quantize(self, bits: int):
+        self.model = self.model.quantize(bits)
+        return self
+
+    def infer(self, input, max_new_tokens=1024, **kwargs):
+        kwargs['max_new_tokens'] = max_new_tokens
+        device = self.model.device
+        input = Vicuna_PROMPT_FORMAT.format(prompt=input)
+        input_ids = self.tokenizer(input,
+                                   return_tensors="pt").input_ids.to(device)
+        output_ids = self.model.generate(input_ids, **kwargs)
+        output_ids = output_ids[0][len(input_ids[0]):]
+
+        outputs = self.tokenizer.decode(output_ids,
+                                        skip_special_tokens=True).strip()
+        return outputs

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

pytorch_model.bin.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6789c806fad05c6b65baa1d30c706ffc43c725283d6e5e1c82dedd9326cc31
+size 27118

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

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
+  }
+}