Strata is a highly specialized, locally-deployable 7-billion parameter archaeological AI assistant. It is a QLoRA fine-tune of Qwen2.5-7B-Instruct designed specifically to act as the generation engine for a complex Retrieval-Augmented Generation (RAG) pipeline.
The model was trained to adopt the tone of an expert archaeologist, heavily prioritize supplied vector context, and strictly refuse to hallucinate historical facts when source documents are unavailable.
This model is designed to be paired with:
BAAI/bge-large-en-v1.5FastLanguageModel (4-bit optimized)from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "your-username/Strata-Qwen2.5-7B-Archaeology-LoRA",
max_seq_length = 8192,
dtype = None,
load_in_4bit = True,
)
FastLanguageModel.for_inference(model)
'EOF'
model-00002-of-00004.safetensors 4.9 GBmodel-00001-of-00004.safetensors 4.9 GBmodel-00003-of-00004.safetensors 4.3 GBmodel-00004-of-00004.safetensors 1.1 GBadapter_model.safetensors 162 MB