10.4 GB
10 files
Updated about 2 months ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.57 kB xet | aacf151a | |
| README.md | 897 Bytes xet | 68aa6c83 | |
| chat_template.jinja | 7.82 kB xet | cc892d80 | |
| config.json | 3.68 kB xet | 6ae758eb | |
| model-00001-of-00002.safetensors | 5.34 GB xet | 1c672bfb | |
| model-00002-of-00002.safetensors | 5.09 GB xet | d50d33d3 | |
| model.safetensors.index.json | 124 kB xet | 12bf556f | |
| processor_config.json | 991 Bytes xet | 184e52e7 | |
| tokenizer.json | 20 MB xet | 458bcbf4 | |
| tokenizer_config.json | 1.2 kB xet | 6ac70a1c |
This model is an MLX conversion quantized to q8 for the prompt enhancer included with Sulphur-2-base. It's tested in LM Studio, and roughly doubles the tokenization rate vs. running the original GGUF model on Apple M-series Macs.
To use, download the files and place them in your LM Studio models directory using the "owner/model" path structure other models use.
Or use HF Hub and just symlink it
hf download MLXBits/sulphur-promptenhancer-mlx-q8
mkdir -p $HOME/.lmstudio/models/sulphur/prompt-enhancer-mlx-q8
ln -s $HOME/.cache/huggingface/hub/models--MLXBits--sulphur-prompt-enhancers-mlx-q8/snapshots/<snapshot hash> $HOME/.lmstudio/models/sulphur/prompt-enhancer-mlx-q8
- Total size
- 10.4 GB
- Files
- 10
- Last updated
- May 30
- Pre-warmed CDN
- US EU US EU