Hugging Face's logo

cstr
/
llama3-8b-spaetzle-v13

Text Generation
Transformers
Safetensors
llama
Merge
mergekit
lazymergekit
Azure99/blossom-v5-llama3-8b
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
cstr commited on
Commit
c8736e2
•
1 Parent(s): bd83771

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -16,6 +16,7 @@ llama3-8b-spaetzle-v13 is a merge of the following models:
16
  * [VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct)
17
 
18
  It should work not too bad for German or English, e.g. it achieves 64.14(.10) on EQ Bench v2_de with 170(171)/171 per [q4km GGUF](https://huggingface.co/cstr/llama3-8b-spaetzle-v13-GGUF) (bpe fixed).
 
19
 
20
  No change in llama3 prompt format template.
21
 
 
16
  * [VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct)
17
 
18
  It should work not too bad for German or English, e.g. it achieves 64.14(.10) on EQ Bench v2_de with 170(171)/171 per [q4km GGUF](https://huggingface.co/cstr/llama3-8b-spaetzle-v13-GGUF) (bpe fixed).
19
+ And for English EQ-Bench Score (v2): 75.59, Parseable: 171.
20
 
21
  No change in llama3 prompt format template.
22