Here is the CodeR model trained on both text-only data and the full code data.
Usage
Using FlagEmbedding
git clone https://github.com/FlagOpen/FlagEmbedding.git
cd FlagEmbedding
pip install -e .
from FlagEmbedding import FlagLLMModel
queries = [
"Delete the record with ID 4 from the 'Staff' table.",
'Delete all records in the "Livestock" table where age is greater than 5'
]
documents = [
"DELETE FROM Staff WHERE StaffID = 4;",
"DELETE FROM Livestock WHERE age > 5;"
]
model = FlagLLMModel('nebula2025/CodeR-full',
query_instruction_format="<instruct>{}\n<query>{}",
query_instruction_for_retrieval="Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
trust_remote_code=True,
use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
embeddings_1 = model.encode_queries(queries)
embeddings_2 = model.encode_corpus(documents)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
By default, FlagLLMModel will use all available GPUs when encoding. Please set os.environ["CUDA_VISIBLE_DEVICES"] to select specific GPUs. You also can set os.environ["CUDA_VISIBLE_DEVICES"]="" to make all GPUs unavailable.
Using Sentence Transformers
from sentence_transformers import SentenceTransformer
import torch
# Load the model, optionally in float16 precision for faster inference
model = SentenceTransformer("nebula2025/CodeR-full", model_kwargs={"torch_dtype": torch.float16, "trust_remote_code": True}, tokenizer_kwargs={"trust_remote_code": True})
# Prepare a prompt given an instruction
instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
prompt = f'<instruct>{instruction}\n<query>'
# Prepare queries and documents
queries = [
"Delete the record with ID 4 from the 'Staff' table.",
'Delete all records in the "Livestock" table where age is greater than 5'
]
documents = [
"DELETE FROM Staff WHERE StaffID = 4;",
"DELETE FROM Livestock WHERE age > 5;"
]
# Compute the query and document embeddings
query_embeddings = model.encode(queries, prompt=prompt)
document_embeddings = model.encode(documents)
# Compute the cosine similarity between the query and document embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
Using HuggingFace Transformers
import torch
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def last_token_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
if left_padding:
return last_hidden_states[:, -1]
else:
sequence_lengths = attention_mask.sum(dim=1) - 1
batch_size = last_hidden_states.shape[0]
return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'<instruct>{task_description}\n<query>{query}'
instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
queries = [
"Delete the record with ID 4 from the 'Staff' table.",
'Delete all records in the "Livestock" table where age is greater than 5'
]
documents = [
"DELETE FROM Staff WHERE StaffID = 4;",
"DELETE FROM Livestock WHERE age > 5;"
]
input_texts = queries + documents
tokenizer = AutoTokenizer.from_pretrained('nebula2025/CodeR-full', trust_remote_code=True)
model = AutoModel.from_pretrained('nebula2025/CodeR-full', trust_remote_code=True)
model.eval()
max_length = 4096
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt', pad_to_multiple_of=8)
with torch.no_grad():
outputs = model(**batch_dict)
embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())