Update README.md

README.md

@@ -2491,15 +2491,6 @@ model-index:
 
 For more details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
 
-FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently:
-- **LLM-based Dense Retrieval**: BGE-EN-Mistral, BGE-Multilingual-Gemma2
-- **Long-Context LLM**: [Activation Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon)
-- **Fine-tuning of LM** : [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail)
-- **Dense Retrieval**: [BGE-M3](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3), [LLM Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), [BGE Embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding)
-- **Reranker Model**: [BGE Reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
-- **Benchmark**: [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB)
-
-
 **BGE-EN-Mistral** primarily demonstrates the following capabilities:
 - In-context learning ability: By providing few-shot examples in the query, it can significantly enhance the model's ability to handle new tasks.
 - Outstanding performance: The model has achieved state-of-the-art (SOTA) performance on both BEIR and AIR-Bench.
@@ -2519,9 +2510,10 @@ We will release the technical report and training data for **BGE-EN-Mistral** in
 
 ### Using FlagEmbedding
 ```
-pip install -U FlagEmbedding
+git clone https://github.com/FlagOpen/FlagEmbedding.git
+cd FlagEmbedding
+pip install -e .
 ```
-If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding.
 
 ```python
 from FlagEmbedding import FlagICLModel
@@ -2603,8 +2595,8 @@ documents = [
 ]
 input_texts = queries + documents
 
-tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-en-mistral')
-model = AutoModel.from_pretrained('BAAI/bge-en-mistral')
+tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-en-icl')
+model = AutoModel.from_pretrained('BAAI/bge-en-icl')
 model.eval()
 
 max_length = 4096