starble-dev
/

mini-magnum-12b-v1.1-GGUF

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

starble-dev commited on Jul 25

Commit

fb27ed5

•

1 Parent(s): 8adf2e7

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -21,7 +21,8 @@ library_name: transformers
 **Release Used:** [b3452](https://github.com/ggerganov/llama.cpp/releases/tag/b3452)
 # Quants
-PPL = Perplexity, lower is better
 | Quant Type | Note | Size |
 | ---- | ---- | ---- |
 | [Q2_K](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q2_K.gguf) | +3.5199 ppl @ Llama-3-8B | ? GB |

 **Release Used:** [b3452](https://github.com/ggerganov/llama.cpp/releases/tag/b3452)
 # Quants
+PPL = Perplexity, lower is better<br>
+Comparisons are done against FP16 Llama-3-8B, recommended as a guideline and not as fact.
 | Quant Type | Note | Size |
 | ---- | ---- | ---- |
 | [Q2_K](https://huggingface.co/starble-dev/mini-magnum-12b-v1.1-GGUF/blob/main/mini-magnum-12b-v1.1-Q2_K.gguf) | +3.5199 ppl @ Llama-3-8B | ? GB |