Downloads · 30 days
130
26% of all-time downloads
GritLM-8x7B-iMat.GGUF
dranger003/GritLM-8x7B-iMat.GGUF
GritLM-8x7B-iMat.GGUF is a text generation model from dranger003. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
GGUF importance matrix (imatrix) quants for https://huggingface.co/GritLM/GritLM-8x7B The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
All-time downloads
500
Public
Repo size
129 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf129 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Feb 27, 2024
- Updated
- Feb 28, 2024
- SHA
- 104da616
Try a prompt
Model card
From the Hugging Face model README
GGUF importance matrix (imatrix) quants for https://huggingface.co/GritLM/GritLM-8x7B
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.
| Layers | Context | Template (Text Representation) | Template (Text Generation) |
|---|---|---|---|
| <pre>32</pre> | <pre>32768</pre> | <pre><s><|user|><br>{instruction}<br><|embed|><br>{sample}</pre> | <pre><s><|user|><br>{prompt}<br><|assistant|><br>{response}</pre> |
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Created
- Feb 27, 2024
- Updated
- Feb 28, 2024