mradermacher
commited on
Commit
•
f7f4a79
1
Parent(s):
89d0cfe
auto-patch README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ more details, including on how to concatenate multi-part files.
|
|
27 |
| Link | Type | Size/GB | Notes |
|
28 |
|:-----|:-----|--------:|:------|
|
29 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
|
30 |
-
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ1_M.gguf) | i1-IQ1_M | 23.9 |
|
31 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_S.gguf) | i1-IQ2_S | 32.3 | |
|
@@ -42,7 +42,7 @@ more details, including on how to concatenate multi-part files.
|
|
42 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-ab) | i1-Q3_K_M | 50.0 | IQ3_S probably better |
|
43 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.5 | IQ3_M probably better |
|
44 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 55.5 | |
|
45 |
-
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_NL.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_NL.gguf.part2of2) | i1-IQ4_NL | 58.7 |
|
46 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 58.8 | fast, low quality |
|
47 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.3 | fast, recommended |
|
@@ -50,7 +50,6 @@ more details, including on how to concatenate multi-part files.
|
|
50 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
|
51 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 85.1 | practically like static Q6_K |
|
52 |
|
53 |
-
|
54 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
55 |
types (lower is better):
|
56 |
|
|
|
27 |
| Link | Type | Size/GB | Notes |
|
28 |
|:-----|:-----|--------:|:------|
|
29 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
|
30 |
+
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ1_M.gguf) | i1-IQ1_M | 23.9 | mostly desperate |
|
31 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_S.gguf) | i1-IQ2_S | 32.3 | |
|
|
|
42 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-ab) | i1-Q3_K_M | 50.0 | IQ3_S probably better |
|
43 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.5 | IQ3_M probably better |
|
44 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 55.5 | |
|
45 |
+
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_NL.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ4_NL.gguf.part2of2) | i1-IQ4_NL | 58.7 | prefer IQ4_XS |
|
46 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 58.8 | fast, low quality |
|
47 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.3 | fast, recommended |
|
|
|
50 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
|
51 |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 85.1 | practically like static Q6_K |
|
52 |
|
|
|
53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
54 |
types (lower is better):
|
55 |
|