mradermacher
commited on
Commit
•
fa5ac22
1
Parent(s):
10e1b68
auto-patch README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,6 @@ tags:
|
|
17 |
<!-- ### vocab_type: -->
|
18 |
weighted/imatrix quants of https://huggingface.co/Undi95/Dawn-v2-70B
|
19 |
|
20 |
-
|
21 |
<!-- provided-files -->
|
22 |
static quants are available at https://huggingface.co/mradermacher/Dawn-v2-70B-GGUF
|
23 |
## Usage
|
@@ -32,9 +31,27 @@ more details, including on how to concatenate multi-part files.
|
|
32 |
|
33 |
| Link | Type | Size/GB | Notes |
|
34 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
|
|
|
|
|
|
|
|
|
38 |
|
39 |
|
40 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
17 |
<!-- ### vocab_type: -->
|
18 |
weighted/imatrix quants of https://huggingface.co/Undi95/Dawn-v2-70B
|
19 |
|
|
|
20 |
<!-- provided-files -->
|
21 |
static quants are available at https://huggingface.co/mradermacher/Dawn-v2-70B-GGUF
|
22 |
## Usage
|
|
|
31 |
|
32 |
| Link | Type | Size/GB | Notes |
|
33 |
|:-----|:-----|--------:|:------|
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
|
51 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
|
53 |
+
| [GGUF](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
|
54 |
+
| [PART 1](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Dawn-v2-70B-i1-GGUF/resolve/main/Dawn-v2-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
|
55 |
|
56 |
|
57 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|