Update README.md

README.md

@@ -6,7 +6,7 @@ library_name: transformers
 pipeline_tag: text-generation
 inference: false
 model_creator: jphme
-model_name: EM German v01 7b
+model_name: EM German v01 70b
 model_type: llama
 prompt_template: >
   Du bist ein hilfreicher KI Assistent, der den Anweisungen des Nutzers sehr gut folgt und ausführliche Antworten gibt! USER: Was ist 1+1? ASSISTANT:
@@ -21,13 +21,13 @@ tags:
 ---
 ![EM Logo](em_model_logo_web.jpeg)
 
-# EM German 13b GPTQ
+# EM German 70b GPTQ
 
 ([Zur deutschen Version](#deutsch-em-german))
 
 **EM German (v01)** is an experimental llama2-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content.
 
-This is the 13b llama2 version, using the GPTQ quantization format with 4 bits, 32 groups and Actorder=True. If there is sufficient demand, I will probably add further formats/versions soon.
+This is the 70b llama2 version, using the GPTQ quantization format with 4 bits, 128 groups and Actorder=True. If there is sufficient demand, I will probably add further formats/versions soon.
 
 # Links & Demos