Commit
•
055f7e6
1
Parent(s):
f35c6cc
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,6 @@ quantized_by: mradermacher
|
|
| 11 |
<!-- ### vocab_type: -->
|
| 12 |
static quants of https://huggingface.co/jspr/talosian-7b
|
| 13 |
|
| 14 |
-
|
| 15 |
<!-- provided-files -->
|
| 16 |
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.
|
| 17 |
## Usage
|
|
@@ -27,10 +26,17 @@ more details, including on how to concatenate multi-part files.
|
|
| 27 |
| Link | Type | Size/GB | Notes |
|
| 28 |
|:-----|:-----|--------:|:------|
|
| 29 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q2_K.gguf) | Q2_K | 3.2 | |
|
|
|
|
|
|
|
| 30 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.IQ3_S.gguf) | IQ3_S | 3.7 | beats Q3_K* |
|
| 31 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.IQ3_M.gguf) | IQ3_M | 3.8 | |
|
| 32 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
|
|
|
|
|
|
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q6_K.gguf) | Q6_K | 6.5 | very good quality |
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
| 36 |
|
|
|
|
| 11 |
<!-- ### vocab_type: -->
|
| 12 |
static quants of https://huggingface.co/jspr/talosian-7b
|
| 13 |
|
|
|
|
| 14 |
<!-- provided-files -->
|
| 15 |
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.
|
| 16 |
## Usage
|
|
|
|
| 26 |
| Link | Type | Size/GB | Notes |
|
| 27 |
|:-----|:-----|--------:|:------|
|
| 28 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q2_K.gguf) | Q2_K | 3.2 | |
|
| 29 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.IQ3_XS.gguf) | IQ3_XS | 3.5 | |
|
| 30 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q3_K_S.gguf) | Q3_K_S | 3.7 | |
|
| 31 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.IQ3_S.gguf) | IQ3_S | 3.7 | beats Q3_K* |
|
| 32 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.IQ3_M.gguf) | IQ3_M | 3.8 | |
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q3_K_L.gguf) | Q3_K_L | 4.3 | |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.IQ4_XS.gguf) | IQ4_XS | 4.5 | |
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q5_K_S.gguf) | Q5_K_S | 5.5 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q5_K_M.gguf) | Q5_K_M | 5.6 | |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q6_K.gguf) | Q6_K | 6.5 | very good quality |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/talosian-7b-GGUF/resolve/main/talosian-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
| 42 |
|