Commit
•
6ffee46
1
Parent(s):
741753e
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,6 @@ quantized_by: mradermacher
|
|
| 15 |
<!-- ### vocab_type: -->
|
| 16 |
static quants of https://huggingface.co/HachiML/Swallow-MS-7b-instruct-v0.1
|
| 17 |
|
| 18 |
-
|
| 19 |
<!-- provided-files -->
|
| 20 |
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
| 21 |
## Usage
|
|
@@ -31,14 +30,19 @@ more details, including on how to concatenate multi-part files.
|
|
| 31 |
| Link | Type | Size/GB | Notes |
|
| 32 |
|:-----|:-----|--------:|:------|
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q2_K.gguf) | Q2_K | 2.9 | |
|
|
|
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.IQ3_M.gguf) | IQ3_M | 3.4 | |
|
|
|
|
|
|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
| 37 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q6_K.gguf) | Q6_K | 6.1 | very good quality |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.f16.gguf) | f16 | 14.8 | 16 bpw, overkill |
|
| 40 |
|
| 41 |
-
|
| 42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 43 |
types (lower is better):
|
| 44 |
|
|
|
|
| 15 |
<!-- ### vocab_type: -->
|
| 16 |
static quants of https://huggingface.co/HachiML/Swallow-MS-7b-instruct-v0.1
|
| 17 |
|
|
|
|
| 18 |
<!-- provided-files -->
|
| 19 |
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
| 20 |
## Usage
|
|
|
|
| 30 |
| Link | Type | Size/GB | Notes |
|
| 31 |
|:-----|:-----|--------:|:------|
|
| 32 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q2_K.gguf) | Q2_K | 2.9 | |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.IQ3_M.gguf) | IQ3_M | 3.4 | |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.7 | lower quality |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.0 | |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.2 | |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.3 | |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q6_K.gguf) | Q6_K | 6.1 | very good quality |
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Swallow-MS-7b-instruct-v0.1-GGUF/resolve/main/Swallow-MS-7b-instruct-v0.1.f16.gguf) | f16 | 14.8 | 16 bpw, overkill |
|
| 45 |
|
|
|
|
| 46 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 47 |
types (lower is better):
|
| 48 |
|