Delete test.py and update README

Contributors.md

+# Contributors
+None
\ No newline at end of file

README.md

 # FlagEmbedding
-智源开源库FlagEmbedding
+智源开源库FlagEmbedding，专注于检索增强llm领域。
 
 ## 已适配模型
 - **Embedding Model**: [BGE Embedding](./FlagEmbedding/baai_general_embedding)
@@ -14,7 +14,7 @@
 docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
 docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
 
-cd /your_code_path/FlagEmbedding
+cd /your_code_path/FlagEmbedding_pytorch
 pip install -e .
 pip install faiss-1.7.2_dtk24.04_gitb7348e7df780-py3-none-any.whl
 ```
@@ -25,7 +25,7 @@ cd docker
 docker build --no-cache -t FlagEmbedding:latest .
 docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
 
-cd /your_code_path/FlagEmbedding
+cd /your_code_path/FlagEmbedding_pytorch
 pip install -e .
 pip install faiss-1.7.2_dtk24.04_gitb7348e7df780-py3-none-any.whl
 ```
@@ -41,7 +41,7 @@ torch: 2.1.0
 
 其它非深度学习库安装方式如下：
 ```bash
-cd /your_code_path/FlagEmbedding
+cd /your_code_path/FlagEmbedding_pytorch
 pip install -e .
 pip install faiss-1.7.2_dtk24.04_gitb7348e7df780-py3-none-any.whl
 ```
@@ -70,13 +70,14 @@ BGE Embedding是一个通用向量模型。 我们使用[retromae](https://githu
 
 ## 应用场景
 ### 算法类别
-
+检索增强
 
 ### 热点应用行业
-制造,广媒,家居,教育
+广媒,教育,政府
 
 ## 预训练权重
 通过[SCNet AIModels](http://113.200.138.88:18080/aimodels)下载预训练模型:
+
 ### BGE Embedding
 - [bge-large-zh-v1.5](http://113.200.138.88:18080/aimodels/bge-large-zh-v1.5)
 - [bge-base-zh-v1.5](http://113.200.138.88:18080/aimodels/baai/bge-base-zh-v1.5)
@@ -90,7 +91,7 @@ BGE Embedding是一个通用向量模型。 我们使用[retromae](https://githu
 - [bge-reranker-large](http://113.200.138.88:18080/aimodels/bge-reranker-large)
 
 ## 源码仓库及问题反馈
-- https://developer.hpccube.com/codes/modelzoo/
+- https://developer.hpccube.com/codes/modelzoo/flagembedding_pytorch
 
 ## 参考资料
 - https://github.com/FlagOpen/FlagEmbedding

model.properties

+# 模型唯一标识
+modelCode=822
+# 模型名称
+modelName=FlagEmbedding_pytorch
+# 模型描述
+modelDescription=智源开源仓，FlagEmbedding专注于检索增强llm领域。
+# 应用场景
+appScenario=推理,训练,检索增强,广媒,教育,政府
+# 框架类型
+frameType=pytorch

test_embedding.py

-import argparse
-
-def use_hf(model_path):
-    from transformers import AutoTokenizer, AutoModel
-    import torch
-    # Sentences we want sentence embeddings for
-    sentences = ["怎么优化网卡性能及丢包问题", "按电源键启动几秒后机器自动掉电"]
-
-    # Load model from HuggingFace Hub
-    tokenizer = AutoTokenizer.from_pretrained(model_path)
-    model = AutoModel.from_pretrained(model_path)
-    model.eval()
-
-    # Tokenize sentences
-    encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
-    # for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages)
-    # encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt')
-
-    # Compute token embeddings
-    with torch.no_grad():
-        model_output = model(**encoded_input)
-        # Perform pooling. In this case, cls pooling.
-        sentence_embeddings = model_output[0][:, 0]
-    # normalize embeddings
-    sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
-    print("Sentence embeddings:", sentence_embeddings)
-
-
-
-def use_stf(model_path):
-    from sentence_transformers import SentenceTransformer
-    sentences_1 = ["怎么优化网卡性能及丢包问题", "按电源键启动几秒后机器自动掉电"]
-    sentences_2 = ["存储设备开机关机的顺序有哪些要求", "按电源键启动几秒自动掉电"]
-    model = SentenceTransformer(model_path)
-    embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
-    embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
-    similarity = embeddings_1 @ embeddings_2.T
-    print(similarity)
-
-    queries = ['售前咨询', '存储设备开机关机的顺序有哪些要求']
-    passages = ["售前咨询需要联系您所在地平台,平台联系方式可以通过以下途径进行获取:\n<平台联系方式>", "存储设备开机关机顺序:\n开机流程:启动交换机和存储扩展柜--启动存储控制器--启动物理服务器--启动物理服务器上的业务\n关机流程:停止物理服务器上的业务--关闭物理服务器--关闭存储控制器--关闭交换机和存储扩展柜"]
-
-    instruction = "为这个句子生成表示以用于检索相关文章："
-
-    model = SentenceTransformer(model_path)
-    q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True)
-    p_embeddings = model.encode(passages, normalize_embeddings=True)
-    scores = q_embeddings @ p_embeddings.T
-    print(scores)
-
-
-def use_flagE(model_path):
-    # from FlagEmbedding
-    from FlagEmbedding import FlagModel
-    sentences_1 = ["怎么优化网卡性能及丢包问题", "按电源键启动几秒后机器自动掉电"]
-    sentences_2 = ["存储设备开机关机的顺序有哪些要求", "按电源键启动几秒自动掉电"]
-    model = FlagModel(model_path,
-                    query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章：",
-                    use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
-    embeddings_1 = model.encode(sentences_1)
-    embeddings_2 = model.encode(sentences_2)
-    similarity = embeddings_1 @ embeddings_2.T
-    print(similarity)
-
-    # for s2p(short query to long passage) retrieval task, suggest to use encode_queries() which will automatically add the instruction to each query
-    # corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction
-    queries = ['售前咨询', '存储设备开机关机的顺序有哪些要求']
-    passages = ["售前咨询需要联系您所在地平台,平台联系方式可以通过以下途径进行获取:\n<平台联系方式>", "存储设备开机关机顺序:\n开机流程:启动交换机和存储扩展柜--启动存储控制器--启动物理服务器--启动物理服务器上的业务\n关机流程:停止物理服务器上的业务--关闭物理服务器--关闭存储控制器--关闭交换机和存储扩展柜"]
-    q_embeddings = model.encode_queries(queries)
-    p_embeddings = model.encode(passages)
-    scores = q_embeddings @ p_embeddings.T
-    print(scores)
-
-
-def get_args():
-    parse = argparse.ArgumentParser('Testing reranker in FlagEmbedding or Transformers.')
-    parse.add_argument('--model_path', default='BAAI/bge-large-zh-v1.5')
-    parse.add_argument('--use_hf', action='store_true')
-    parse.add_argument('--use_stf', action='store_true')
-    args = parse.parse_args()
-    return args
-
-
-if __name__ == '__main__':
-    args = get_args()
-    model_path = args.model_path
-
-    if args.use_hf:
-        use_hf(model_path)
-    elif args.use_stf:
-        use_stf(model_path)
-    else:
-        use_flagE(model_path)

test_reranker.py

-import argparse
-
-
-def use_hf(model_path):
-    import torch
-    from transformers import AutoModelForSequenceClassification, AutoTokenizer
-
-    # from transformers
-    tokenizer = AutoTokenizer.from_pretrained(model_path)
-    model = AutoModelForSequenceClassification.from_pretrained(model_path)
-    model.eval()
-
-    pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
-    with torch.no_grad():
-        inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
-        scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
-        print(scores)
-
-
-def use_flagE(model_path):
-    # from FlagEmbedding
-    from FlagEmbedding import FlagReranker
-    reranker = FlagReranker(model_path, use_fp16=True) #use fp16 can speed up computing
-
-    score = reranker.compute_score(['售前咨询', '售前咨询需要联系您所在地平台,平台联系方式可以通过以下途径进行获取:\n<平台联系方式>'])
-    print(score)
-
-    scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
-    print(scores)
-
-
-def get_args():
-    parse = argparse.ArgumentParser('Testing reranker in FlagEmbedding or Transformers.')
-    parse.add_argument('--model_path', default='BAAI/bge-reranker-base')
-    parse.add_argument('--use_hf', action='store_true')
-    args = parse.parse_args()
-    return args
-
-
-if __name__ == '__main__':
-    args = get_args()
-    model_path = args.model_path
-
-    if args.use_hf:
-        use_hf(model_path)
-    else:
-        use_flagE(model_path)