Downloads · 30 days
32
4% of all-time downloads
Mathstral-7B-v0.1-GGUF
mukel/Mathstral-7B-v0.1-GGUF
Mathstral-7B-v0.1-GGUF is a machine learning model from mukel. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
In the wild, Q80 quantizations are fine, but Q40 quantizations are rarely pure e.g. the output.weights tensor is quantized with Q6K, instead of Q40. A pure Q40 quantization can be generated from a high precision (F32,…
All-time downloads
750
Public
Repo size
11.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf11.8 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 17, 2024
- Updated
- Jul 17, 2024
- SHA
- 128eb6e6
Model card
From the Hugging Face model README
Pure quantizations of Mathstral-7B-v0.1 for mistral.java.
In the wild, Q8_0 quantizations are fine, but Q4_0 quantizations are rarely pure e.g. the output.weights tensor is quantized with Q6_K, instead of Q4_0.
A pure Q4_0 quantization can be generated from a high precision (F32, F16, BFLOAT16) .gguf source with the quantize utility from llama.cpp as follows:
./llama-quantize --pure ./Mathstral-7B-v0.1-F32.gguf ./Mathstral-7B-v0.1-Q4_0.gguf Q4_0
Original model: https://huggingface.co/mistralai/mathstral-7B-v0.1
**Note that this model does not support a System prompt.
Mathstral 7B is a model specializing in mathematical and scientific tasks, based on Mistral 7B. You can read more in the official blog post.
- License
- apache-2.0
- Created
- Jul 17, 2024
- Updated
- Jul 17, 2024