MLX
Safetensors
mistral3
rotorquant
kv-cache-quantization
2-bit
weight-quantization
leanstral
lean4
formal-proofs
theorem-proving
quantized
apple-silicon
mistral
Mixture of Experts
Instructions to use majentik/Leanstral-RotorQuant-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/Leanstral-RotorQuant-MLX-2bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Leanstral-RotorQuant-MLX-2bit majentik/Leanstral-RotorQuant-MLX-2bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)
Browse files
README.md
CHANGED
|
@@ -2,20 +2,23 @@
|
|
| 2 |
base_model: mistralai/Leanstral-2603
|
| 3 |
library_name: mlx
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 19 |
---
|
| 20 |
|
| 21 |
# Leanstral-RotorQuant-MLX-2bit
|
|
|
|
| 2 |
base_model: mistralai/Leanstral-2603
|
| 3 |
library_name: mlx
|
| 4 |
tags:
|
| 5 |
+
- rotorquant
|
| 6 |
+
- kv-cache-quantization
|
| 7 |
+
- mlx
|
| 8 |
+
- 2-bit
|
| 9 |
+
- weight-quantization
|
| 10 |
+
- leanstral
|
| 11 |
+
- lean4
|
| 12 |
+
- formal-proofs
|
| 13 |
+
- theorem-proving
|
| 14 |
+
- quantized
|
| 15 |
+
- apple-silicon
|
| 16 |
+
- mistral
|
| 17 |
+
- moe
|
| 18 |
license: apache-2.0
|
| 19 |
+
pipeline_tag: text-generation
|
| 20 |
+
language:
|
| 21 |
+
- en
|
| 22 |
---
|
| 23 |
|
| 24 |
# Leanstral-RotorQuant-MLX-2bit
|