Instructions to use masahiroid/Sentiment-Analysis-7B-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use masahiroid/Sentiment-Analysis-7B-4bit-mlx with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("masahiroid/Sentiment-Analysis-7B-4bit-mlx") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use masahiroid/Sentiment-Analysis-7B-4bit-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "masahiroid/Sentiment-Analysis-7B-4bit-mlx"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "masahiroid/Sentiment-Analysis-7B-4bit-mlx" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "masahiroid/Sentiment-Analysis-7B-4bit-mlx", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
|
Download README.md from masahiroid/Sentiment-Analysis-7B-4bit-mlx: direct link, hf CLI and curl.
- Browser
- Download file 1.85 kB
-
https://huggingface.co/masahiroid/Sentiment-Analysis-7B-4bit-mlx/resolve/main/README.md
- Command line
-
hf download hf://masahiroid/Sentiment-Analysis-7B-4bit-mlx/README.md
-
curl -L -o README.md https://huggingface.co/masahiroid/Sentiment-Analysis-7B-4bit-mlx/resolve/main/README.md
1.85 kB
| license: mit | |
| library_name: mlx | |
| pipeline_tag: text-generation | |
| base_model: microsoft/Sentiment-Analysis-7B | |
| tags: | |
| - mlx | |
| - 4bit | |
| # Sentiment-Analysis-7B-4bit-mlx | |
| [`microsoft/Sentiment-Analysis-7B`](https://huggingface.co/microsoft/Sentiment-Analysis-7B) を Apple Silicon 向けに [MLX](https://github.com/ml-explore/mlx) の 4bit(group size 64)へ量子化した非公式の変換版です。M2 16GB クラスの Mac(GPU に使えるメモリ約 8GB)で動くサイズのモデルを対象にしています。ベースモデルの開発・公開者の皆様に感謝いたします。 | |
| An unofficial 4-bit MLX conversion of [`microsoft/Sentiment-Analysis-7B`](https://huggingface.co/microsoft/Sentiment-Analysis-7B) for Apple Silicon Macs (sized for 16GB unified memory). All credit goes to the original authors. | |
| - Parameters: 7.24B / License: mit (same as the base model) | |
| ## Usage | |
| ```bash | |
| pip install -U mlx-lm | |
| mlx_lm.generate --model masahiroid/Sentiment-Analysis-7B-4bit-mlx --prompt "日本の首都はどこですか?" --max-tokens 256 | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("masahiroid/Sentiment-Analysis-7B-4bit-mlx") | |
| messages = [{"role": "user", "content": "日本の首都はどこですか?"}] | |
| prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True) | |
| print(generate(model, tokenizer, prompt=prompt, max_tokens=256)) | |
| ``` | |
| ## Security / セキュリティ | |
| 公開前に [model-audit-lite](https://github.com/masahiroid/model-audit-lite) で検査しています。 | |
| - ファイル検査(pickle 形式の重み・独自コードの有無、SHA256) | |
| - 変換前後のチャットテンプレートの一致 | |
| - 日本語の安全性プローブ(変換後モデル) | |
| 結果は [SECURITY.md](SECURITY.md) と [audit/report.md](audit/report.md) を参照してください。 | |