Improve README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Vezora/Mistral-22B-v0.1
|
| 3 |
+
tags:
|
| 4 |
+
- moe
|
| 5 |
+
- mistral
|
| 6 |
+
- mixtral
|
| 7 |
+
- merge
|
| 8 |
+
- importance matrix
|
| 9 |
+
- imatrix
|
| 10 |
+
language:
|
| 11 |
+
- fr
|
| 12 |
+
- it
|
| 13 |
+
- de
|
| 14 |
+
- es
|
| 15 |
+
- en
|
| 16 |
+
model-index:
|
| 17 |
+
- name: Mistral-22B-v0.1-iMat-GGUF
|
| 18 |
+
results: []
|
| 19 |
license: apache-2.0
|
| 20 |
---
|
| 21 |
+
|
| 22 |
+
# Vezora/Mistral-22B-v0.1 GGUFs created with an importance matrix
|
| 23 |
+
|
| 24 |
+
Source Model: [Vezora/Mistral-22B-v0.1](https://huggingface.co/Vezora/Mistral-22B-v0.1)
|
| 25 |
+
|
| 26 |
+
Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [5dc9dd7152dedc6046b646855585bd070c91e8c8](https://github.com/ggerganov/llama.cpp/commit/5dc9dd7152dedc6046b646855585bd070c91e8c8) (master from 2024-04-09)
|
| 27 |
+
|
| 28 |
+
Imatrix was generated from the f16 gguf via this command:
|
| 29 |
+
|
| 30 |
+
./imatrix -c 512 -m $out_path/$base_quant_name -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat
|
| 31 |
+
|
| 32 |
+
Using the dataset from [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
|