Sentence Similarity
sentence-transformers
Safetensors
Transformers
qwen2
feature-extraction
Qwen2
custom_code
Instructions to use khulnasoft/NeoAI-Embed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use khulnasoft/NeoAI-Embed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("khulnasoft/NeoAI-Embed", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use khulnasoft/NeoAI-Embed with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("khulnasoft/NeoAI-Embed", trust_remote_code=True) model = AutoModel.from_pretrained("khulnasoft/NeoAI-Embed", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "151643": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151644": { | |
| "content": "<|im_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "151645": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>" | |
| ], | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_qwen.Qwen2Tokenizer", | |
| "tokenization_qwen.Qwen2TokenizerFast" | |
| ] | |
| }, | |
| "bos_token": null, | |
| "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|endoftext|>", | |
| "errors": "replace", | |
| "extra_special_tokens": {}, | |
| "model_max_length": 32768, | |
| "pad_token": "<|endoftext|>", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null, | |
| "add_eos_token": true | |
| } |