dranger003 commited on
Commit
d5940ef
1 Parent(s): 560d22e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -9,7 +9,7 @@ I am currently re-uploading all the quants compatible with the PR (WIP).
9
 
10
  * GGUF importance matrix (imatrix) quants for https://huggingface.co/CohereForAI/c4ai-command-r-plus
11
  * The importance matrix is trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
12
- * [Which GGUF is right for me? (from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) - X axis is file size and Y axis is perplexity (lower perplexity is better quality). Some of the sweet spots (size vs PPL) are IQ4_XS, IQ3_S, IQ3_XXS, IQ2_M and IQ2_XS.
13
  * The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well (only for < Q6_K).
14
  * You can merge GGUFs with `gguf-split --merge <first-chunk> <output-file>` although this is not required since [f482bb2e](https://github.com/ggerganov/llama.cpp/commit/f482bb2e4920e544651fb832f2e0bcb4d2ff69ab).
15
  * What is importance matrix (imatrix)? You can [read more about it from the author here](https://github.com/ggerganov/llama.cpp/pull/4861). Some other info [here](https://huggingface.co/dranger003/c4ai-command-r-plus-iMat.GGUF/discussions/2#6612840b8377af8668066682).
 
9
 
10
  * GGUF importance matrix (imatrix) quants for https://huggingface.co/CohereForAI/c4ai-command-r-plus
11
  * The importance matrix is trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
12
+ * [Which GGUF is right for me? (from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) - X axis is file size and Y axis is perplexity (lower perplexity is better quality). Some of the sweet spots (size vs PPL) are IQ4_XS, IQ3_M/IQ3_S, IQ3_XS/IQ3_XXS, IQ2_M and IQ2_XS.
13
  * The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well (only for < Q6_K).
14
  * You can merge GGUFs with `gguf-split --merge <first-chunk> <output-file>` although this is not required since [f482bb2e](https://github.com/ggerganov/llama.cpp/commit/f482bb2e4920e544651fb832f2e0bcb4d2ff69ab).
15
  * What is importance matrix (imatrix)? You can [read more about it from the author here](https://github.com/ggerganov/llama.cpp/pull/4861). Some other info [here](https://huggingface.co/dranger003/c4ai-command-r-plus-iMat.GGUF/discussions/2#6612840b8377af8668066682).