How to use stonefish-labs/d3-mini-agentcode with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="stonefish-labs/d3-mini-agentcode", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("stonefish-labs/d3-mini-agentcode", trust_remote_code=True) model = AutoModel.from_pretrained("stonefish-labs/d3-mini-agentcode", trust_remote_code=True, device_map="auto")
21a9138
1
2
3
4
5
# Versions used to build the training and evaluation states. Without tree-sitter the extractor falls back to line # regexes (reduced coverage) and says so in its notes. tree-sitter==0.26.0 tree-sitter-language-pack==1.12.5
