mradermacher
commited on
Commit
•
d6336da
1
Parent(s):
72f7b72
auto-patch README.md
Browse files
README.md
CHANGED
@@ -3,8 +3,12 @@ base_model: abacusai/Dracarys-72B-Instruct
|
|
3 |
language:
|
4 |
- en
|
5 |
library_name: transformers
|
|
|
|
|
|
|
6 |
quantized_by: mradermacher
|
7 |
-
tags:
|
|
|
8 |
---
|
9 |
## About
|
10 |
|
@@ -16,7 +20,7 @@ tags: []
|
|
16 |
static quants of https://huggingface.co/abacusai/Dracarys-72B-Instruct
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
-
weighted/imatrix quants
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -29,9 +33,19 @@ more details, including on how to concatenate multi-part files.
|
|
29 |
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.IQ3_S.gguf) | IQ3_S | 34.6 | beats Q3_K* |
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.IQ3_M.gguf) | IQ3_M | 35.6 | |
|
|
|
|
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
|
|
|
|
|
|
|
|
|
35 |
| [PART 1](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
|
36 |
|
37 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
3 |
language:
|
4 |
- en
|
5 |
library_name: transformers
|
6 |
+
license: other
|
7 |
+
license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
|
8 |
+
license_name: tongyi-qianwen
|
9 |
quantized_by: mradermacher
|
10 |
+
tags:
|
11 |
+
- chat
|
12 |
---
|
13 |
## About
|
14 |
|
|
|
20 |
static quants of https://huggingface.co/abacusai/Dracarys-72B-Instruct
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dracarys-72B-Instruct-i1-GGUF
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q2_K.gguf) | Q2_K | 29.9 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.IQ3_XS.gguf) | IQ3_XS | 32.9 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.IQ3_S.gguf) | IQ3_S | 34.6 | beats Q3_K* |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q3_K_S.gguf) | Q3_K_S | 34.6 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.IQ3_M.gguf) | IQ3_M | 35.6 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q3_K_L.gguf) | Q3_K_L | 39.6 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.IQ4_XS.gguf) | IQ4_XS | 40.3 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended |
|
46 |
+
| [PART 1](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 | |
|
47 |
+
| [PART 1](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
|
48 |
+
| [PART 1](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
|
49 |
| [PART 1](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dracarys-72B-Instruct-GGUF/resolve/main/Dracarys-72B-Instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|