Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,27 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: zai-org/GLM-4.5V
|
| 4 |
+
base_model_relation: quantized
|
| 5 |
+
quantized_by: turboderp
|
| 6 |
+
tags:
|
| 7 |
+
- exl3
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
EXL3 quants of [GLM-4.5V](https://huggingface.co/zai-org/GLM-4.5V)
|
| 11 |
+
|
| 12 |
+
⚠️ Requires ExLlamaV3 v0.0.15 (or v0.0.14 `dev` branch)
|
| 13 |
+
|
| 14 |
+
Base bitrates:
|
| 15 |
+
|
| 16 |
+
[2.00 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/2.00bpw)
|
| 17 |
+
[3.00 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/3.00bpw)
|
| 18 |
+
[4.00 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/4.00bpw)
|
| 19 |
+
|
| 20 |
+
Optimized:
|
| 21 |
+
|
| 22 |
+
[2.13 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/2.13bpw)
|
| 23 |
+
[2.32 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/2.32bpw)
|
| 24 |
+
[2.55 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/2.55bpw)
|
| 25 |
+
[2.80 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/2.80bpw)
|
| 26 |
+
[3.07 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/3.07bpw)
|
| 27 |
+
[3.49 bits per weight](https://huggingface.co/turboderp/GLM-4.5V-exl3/tree/3.49bpw)
|