Upload README.md with huggingface_hub

README.md

@@ -1,104 +1,20 @@
 ---
 language:
 - en
-pipeline_tag: text-classification
 tags:
-- pretrained
+- embeddings
+- base-model
+- qwen
 license: apache-2.0
-library_name: sentence-transformers
 ---
 
 # Qwen2-7B-embed-base
 
-## Model Details
-Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.
-
-## Requirements
-The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
-```
-KeyError: 'qwen2'
-```
-
-## Usage
-The 'lm_head' layer of this model has been removed, which means it can be used for embeddings. It will not perform greatly, as it needs to be further fine-tuned, as shown by [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct).
-The basic Sentence-Transformers implementation is working correctly. This would imply other more sophisticated embeddings techniques such as adding a custom classification head, will work correctly as well.
-
-## Inference (sentence-transformers)
-```python
-from sentence_transformers import SentenceTransformer
-import torch
-
-# 1. Load a pretrained Sentence Transformer model
-model = SentenceTransformer("ssmits/Qwen2-7B-embed-base") # device = "cpu" when <= 24 GB VRAM
-
-# The sentences to encode
-sentences = [
-    "The weather is lovely today.",
-    "It's so sunny outside!",
-    "He drove to the stadium.",
-]
-
-# 2. Calculate embeddings by calling model.encode()
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# (3, 3584)
-
-# 3. Calculate the embedding similarities
-# Assuming embeddings is a numpy array, convert it to a torch tensor
-embeddings_tensor = torch.tensor(embeddings)
-
-# Using torch to compute cosine similarity matrix
-similarities = torch.nn.functional.cosine_similarity(embeddings_tensor.unsqueeze(0), embeddings_tensor.unsqueeze(1), dim=2)
-
-print(similarities)
-# tensor([[1.0000, 0.8735, 0.7051],
-#         [0.8735, 1.0000, 0.7199],
-#         [0.7051, 0.7199, 1.0000]])
-```
-
-Note: In my tests it utilizes more than 24GB (RTX 4090), so an A100 or A6000 would be required for inference.
-
+This is a base model derived from Qwen2.5-7B-Instruct with the language modeling head removed. 
+It's intended to be used as a base for embedding tasks and further fine-tuning.
 
-## Inference (HuggingFace Transformers)
-Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
-
-```python
-from transformers import AutoTokenizer, AutoModel
-import torch
-
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
-
-# Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
-
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('ssmits/Qwen2-7B-embed-base')
-model = AutoModel.from_pretrained('ssmits/Qwen2-7B-embed-base') # device = "cpu" when <= 24 GB VRAM
-
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
-
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
-
-# Perform pooling. In this case, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-
-print("Sentence embeddings:")
-print(sentence_embeddings)
-```
-
-### How to enable Multi-GPU
-```python
-from transformers import AutoModel
-from torch.nn import DataParallel
-
-model = AutoModel.from_pretrained("ssmits/Qwen2-7B-embed-base")
-for module_key, module in model._modules.items():
-    model._modules[module_key] = DataParallel(module)
-```
+## Model Details
+- Base model: Qwen2.5-7B-Instruct
+- The 'lm_head' layer has been removed
+- Maintains the original model's norm layers
+- Suitable for embedding tasks and custom head additions