auto-patch README.md

README.md

@@ -1,10 +1,21 @@
 ---
 base_model: mpasila/Viking-Magnum-v0.1-7B
+datasets:
+- mpasila/Magnum-V2-Mix
+- anthracite-org/Stheno-Data-Filtered
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- anthracite-org/nopm_claude_writing_fixed
 language:
 - en
+- fi
+- sv
+- no
+- da
+- is
+- nn
 library_name: transformers
 license: apache-2.0
-no_imatrix: "nan1"
+no_imatrix: nan1
 quantized_by: mradermacher
 tags:
 - text-generation-inference
@@ -24,7 +35,6 @@ tags:
 static quants of https://huggingface.co/mpasila/Viking-Magnum-v0.1-7B
 
 <!-- provided-files -->
-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.
 ## Usage
 
 If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -37,7 +47,21 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q2_K.gguf) | Q2_K | 3.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.IQ3_XS.gguf) | IQ3_XS | 3.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.IQ3_M.gguf) | IQ3_M | 3.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.IQ4_XS.gguf) | IQ4_XS | 4.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q6_K.gguf) | Q6_K | 6.3 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Viking-Magnum-v0.1-7B-GGUF/resolve/main/Viking-Magnum-v0.1-7B.f16.gguf) | f16 | 15.2 | 16 bpw, overkill |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):