加载中…
加载中…
The sentence-transformers all-MiniLM-L6-v2 embedding model in MNN form, which TokForge keeps as its fallback embedder for document and memory search.
Published by TokForge for on-device inference.
| What it is | Embedding model (helper model, 384-dim vectors; legacy fallback) |
| Format | MNN model, plus GGUF files (Q8_0 and f16) and the original ONNX graph |
| Runs on | Android phones (CPU, MNN) |
| Phone class | 4 GB RAM or more (TokForge helper module) |
| Download | 207 MB (5 files) |
| Base model | sentence-transformers/all-MiniLM-L6-v2 |
| License | Apache-2.0 |
Runs on-device in the TokForge app.
minilm.mnn and vocab.txt on its own when it needs them and you allow it.Collections: TokForge Voice and Helper Models.
| File | Size | What it is |
|---|---|---|
all-MiniLM-L6-v2-f16.gguf |
45.9 MB | GGUF, 16-bit (f16), for llama.cpp (not used by the current app) |
all-MiniLM-L6-v2-Q8_0.gguf |
25.0 MB | GGUF, 8-bit (Q8_0), for llama.cpp (not used by the current app) |
minilm.mnn |
45.4 MB | MNN model (what TokForge downloads) |
model.onnx |
90.4 MB | ONNX graph, unchanged from sentence-transformers/all-MiniLM-L6-v2 (not used by the app) |
vocab.txt |
232 KB | WordPiece vocabulary (what TokForge downloads) |
TokForge downloads only minilm.mnn and vocab.txt. The GGUF files are for llama.cpp, and model.onnx and
vocab.txt are unchanged copies of the files in sentence-transformers/all-MiniLM-L6-v2.
all-MiniLM-L6-v2 maps sentences and short paragraphs to 384-dimensional vectors for semantic search, clustering and sentence similarity. It is a 6-layer MiniLM (BERT-style) encoder, trained by sentence-transformers from Microsoft's MiniLM-L6-H384-uncased. TokForge uses mean pooling, L2-normalized vectors and up to 128 tokens per input.
minilm.mnn was converted with MNN's converter, and the GGUF files were made with
llama.cpp.
all-MiniLM-L6-v2 is released by sentence-transformers under the Apache-2.0 license. The MiniLM-L6-H384-uncased model it was trained from is released by Microsoft under the MIT license.