This is a quantized GGUF port (Q8_0) of the Microsoft Harrier-oss-v1-270m multilingual text embedding model. It has been specifically ported and tested for integration with the Sovereign Engine, optimized for extremely high-throughput batch inference on CPU and Apple Silicon via the Rust candle framework.
Parameter
Value
Architecture
Decoder-only Autoregressive Transformer
Parameters
270 Million
Embedding Dimension
640 ($f32$, $L_2$ Normalized)
Max Context Length
32,768 tokens
Quantization
Q8_0 (8-bit)
⚠️ Critical Usage Rules (READ BEFORE USE)
Unlike standard BERT-based sentence transformers, Harrier-oss-v1 utilizes a causal decoder-only architecture. If you are implementing custom inference engines, you must follow these strict architectural rules, otherwise, your retrieval accuracy will drop to near zero.
1. Last-Token Pooling
This model does not use [CLS] token pooling or Mean Pooling. You must extract the embedding from the very last non-padding token (EOS) of the sequence.
2. Instruction Prompting (Asymmetric)
The model is instruction-trained. You must apply strict asymmetric prompting for queries vs. documents:
Documents / Passages: Embed as-is (raw text).
Search Queries: Must be prefixed with the following template:
Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: <Your Query>
3. No Embedding Scaling
Standard implementations of Gemma-based architectures often multiply the input embeddings by a scaling factor of $\sqrt{\text{hidden_size}}$ (e.g., $\sqrt{640}$).
Do not apply this scaling factor to this specific GGUF export. The weights have been aligned such that applying the $\sqrt{d}$ scalar will completely blow out the attention activations and destroy the latent space representation.
4. KV-Cache Purging
Because it is an autoregressive model, your inference engine will accumulate KV-cache states. If you are batching or running multiple independent documents sequentially in the same memory context, you must manually clear the KV-cache between documents to prevent semantic context bleeding.
