Instructions to use tapiocaTakeshi/qubit-medium-litertlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use tapiocaTakeshi/qubit-medium-litertlm with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=tapiocaTakeshi/qubit-medium-litertlm \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
| license: mit | |
| language: ja | |
| library_name: litert-lm | |
| pipeline_tag: text-generation | |
| tags: | |
| - litertlm | |
| - litert-lm | |
| - on-device | |
| - neuroquantum | |
| - qbnn | |
| # Qubit NeuroQuantum (medium) — LiteRT-LM bundle | |
| NeuroQuantum / QBNN モデルを Google LiteRT-LM 互換のバンドル形式 | |
| (`.litertlm`) で配布しています。 | |
| ## ファイル | |
| - `qubit-neuroquantum-medium.litertlm` — モデルバンドル (26.80 MB) | |
| - `TFLITE_MODEL_OR_WEIGHTS` セクション: モデル重み (fp16 NPZ archive) | |
| - `SP_MODEL` セクション: SentencePiece トークナイザ | |
| - `LLM_METADATA_JSON` セクション: モデル / ランタイム設定 | |
| - `MODEL_CARD_MD` セクション: モデルカード | |
| ## モデル仕様 | |
| | Field | Value | | |
| |---|---| | |
| | Architecture | NeuroQuantum | | |
| | Size | `medium` | | |
| | Parameters | 13,550,606 | | |
| | embed_dim | 128 | | |
| | hidden_dim | 256 | | |
| | num_heads | 4 | | |
| | num_layers | 2 | | |
| | max_seq_len | 1024 | | |
| | vocab_size | 32000 | | |
| ## 推奨ランタイム設定 | |
| ```json | |
| { | |
| "n_ctx": 1024, | |
| "n_batch": 64, | |
| "n_threads": 4, | |
| "n_gpu_layers": 0, | |
| "temperature": 0.8, | |
| "top_p": 0.9, | |
| "top_k": 40 | |
| } | |
| ``` | |
| ## ロード例 | |
| ```python | |
| import struct, json | |
| from pathlib import Path | |
| MAGIC = b"LITERTLM" | |
| with open("qubit-neuroquantum-medium.litertlm", "rb") as f: | |
| assert f.read(8) == MAGIC | |
| version, count = struct.unpack("<II", f.read(8)) | |
| # ... see generate_litertlm_models.py:read_litertlm_header | |
| ``` | |
| 完全なパーサ実装と生成スクリプトは | |
| [tapiocatakeshi/Qubit](https://github.com/tapiocatakeshi/Qubit) の | |
| `generate_litertlm_models.py` を参照してください。 | |
| ## License | |
| MIT | |