dranger003
commited on
Commit
•
62bcfc7
1
Parent(s):
ce94b17
Update README.md
Browse files
README.md
CHANGED
@@ -4,8 +4,9 @@ pipeline_tag: text-generation
|
|
4 |
library_name: gguf
|
5 |
base_model: CohereForAI/c4ai-command-r-v01
|
6 |
---
|
7 |
-
GGUF importance matrix (imatrix) quants for https://huggingface.co/CohereForAI/c4ai-command-r-v01
|
8 |
-
The importance matrix was trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
|
|
|
9 |
|
10 |
**NOTE**: This is a preview of upcoming [PR#6033](https://github.com/ggerganov/llama.cpp/pull/6033).
|
11 |
|
|
|
4 |
library_name: gguf
|
5 |
base_model: CohereForAI/c4ai-command-r-v01
|
6 |
---
|
7 |
+
* GGUF importance matrix (imatrix) quants for https://huggingface.co/CohereForAI/c4ai-command-r-v01
|
8 |
+
* The importance matrix was trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
|
9 |
+
* [Which GGUF is right for me? (Opinionated, from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
|
10 |
|
11 |
**NOTE**: This is a preview of upcoming [PR#6033](https://github.com/ggerganov/llama.cpp/pull/6033).
|
12 |
|