Feature Extraction
Transformers
Safetensors
sentence-transformers
qwen2
text-generation
mteb
🇪🇺 Region: EU
Instructions to use jinaai/jina-code-embeddings-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jinaai/jina-code-embeddings-1.5b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jinaai/jina-code-embeddings-1.5b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jinaai/jina-code-embeddings-1.5b") model = AutoModelForCausalLM.from_pretrained("jinaai/jina-code-embeddings-1.5b") - sentence-transformers
How to use jinaai/jina-code-embeddings-1.5b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("jinaai/jina-code-embeddings-1.5b") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Technical question: Lineage of jinaai/jina-code-embeddings-1.5b
#2
by dqdw - opened
Dear [Developer/Team],
I've been using jinaai/jina-code-embeddings-1.5b recently, and I find it quite useful for my tasks.
Before building on top of it, I would like to understand its connection with Qwen/Qwen2.5-Coder-1.5B:
Direct Fine-tuning: Is it derived directly from Qwen/Qwen2.5-Coder-1.5B, or through other checkpoints?
Inheritance: Are the weights directly inherited from Qwen/Qwen2.5-Coder-1.5B?
This clarification would help me avoid compatibility issues.
I really appreciate your help.
Hey @dqdw ,
Yes it's a direct fine-tuning of Qwen/Qwen2.5-Coder-1.5B and the weights are inherited from that checkpoint