TheMelonGod
commited on
Commit
•
3a58bce
1
Parent(s):
ef1f02a
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,54 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
quantized_by: TheMelonGod
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
tags:
|
8 |
+
- quantized
|
9 |
+
- safetensors
|
10 |
+
- exllamav2
|
11 |
+
- gemma2
|
12 |
+
base_model:
|
13 |
+
- qingy2024/GRMR-2B-Instruct
|
14 |
+
base_model_relation: quantized
|
15 |
+
---
|
16 |
+
**Orignal Model by:** [Qingyun Li](https://huggingface.co/qingy2024)
|
17 |
+
**Orignal Model:** [GRMR-2B-Instruct](https://huggingface.co/qingy2024/GRMR-2B-Instruct)
|
18 |
+
|
19 |
+
For more information about the model, I highly recommend checking out the original model page and the creator while you're at it.
|
20 |
+
|
21 |
+
**ExLlamaV2 Quantizations:**
|
22 |
+
**8.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-8.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-8.0bpw)
|
23 |
+
**7.75bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-7.75bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-7.75bpw)
|
24 |
+
**7.5bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-7.5bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-7.5bpw)
|
25 |
+
**7.25bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-7.25bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-7.25bpw)
|
26 |
+
**7.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-7.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-7.0bpw)
|
27 |
+
**6.75bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-6.75bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-6.75bpw)
|
28 |
+
**6.5bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-6.5bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-6.5bpw)
|
29 |
+
**6.25bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-6.25bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-6.25bpw)
|
30 |
+
**6.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-6.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-6.0bpw)
|
31 |
+
**5.75bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-5.75bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-5.75bpw)
|
32 |
+
**5.5bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-5.5bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-5.5bpw)
|
33 |
+
**5.25bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-5.25bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-5.25bpw)
|
34 |
+
**5.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-5.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-5.0bpw)
|
35 |
+
**4.75bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-4.75bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-4.75bpw)
|
36 |
+
**4.5bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-4.5bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-4.5bpw)
|
37 |
+
**4.25bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-4.25bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-4.25bpw)
|
38 |
+
**4.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-4.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-4.0bpw)
|
39 |
+
**3.75bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-3.75bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-3.75bpw)
|
40 |
+
**3.5bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-3.5bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-3.5bpw)
|
41 |
+
**3.25bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-3.25bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-3.25bpw)
|
42 |
+
**3.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-3.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-3.0bpw)
|
43 |
+
**2.75bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-2.75bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-2.75bpw)
|
44 |
+
**2.5bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-2.5bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-2.5bpw)
|
45 |
+
**2.25bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-2.25bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-2.25bpw)
|
46 |
+
**2.0bpw**: [8hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/8hb-2.0bpw) | [6hb](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/tree/6hb-2.0bpw)
|
47 |
+
|
48 |
+
[Measurement File](https://huggingface.co/TheMelonGod/GRMR-2B-Instruct-exl2/blob/main/GRMR-2B-Instruct-measurement.json) _(Default/built-in calibration dataset was used)_
|
49 |
+
|
50 |
+
If you need a specific model quantized or particular bits per weight, please let me know. I’m happy to help.
|
51 |
+
|
52 |
+
Your feedback and suggestions are always welcome! They help me improve and make quantizations better for everyone.
|
53 |
+
|
54 |
+
Special thanks to [turboderp](https://huggingface.co/turboderp) for developing the tools that made these quantizations possible. Your contributions are greatly appreciated!
|