Update README.md

README.md

@@ -15,13 +15,19 @@ datasets:
 ---
 # Llama 2 13b Chat Norwegian GPTQ
 **This is a GPTQ version of Llama 2 13b Norwegian**
-Read more about [GPTQ here](https://towardsdatascience.com/4-bit-quantization-with-gptq-36b0f4f02c34). For a demo script, see [here](#demo-script).
 
-Llama-2-13b-chat-norwegian is a variant of [Meta](https://huggingface.co/meta-llama)´s [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned on a mix of norwegian datasets created in [Ruter AI Lab](https://ruter.no) the summer of 2023.
+Read more about [GPTQ here](https://towardsdatascience.com/4-bit-quantization-with-gptq-36b0f4f02c34). 
+
+For a demo script, see [here](#demo-script).
+
+Llama-2-13b-chat-norwegian-GPTQ is a variant of [Meta](https://huggingface.co/meta-llama)´s [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned on a mix of norwegian datasets created in [Ruter AI Lab](https://ruter.no) the summer of 2023.
 
 The model is tuned to understand and generate text in Norwegian. It's trained for one epoch on norwegian-alpaca + 15000 samples of machine-translated data from OpenOrca (the dataset to be released). A small subset of custom-made instructional data is also included.
 
-We are currently investigating the possibility of releasing a larger, more powerful model and making GGML and GPTQ versions available for this model.
+For other versions of this model see:
+* [Llama-2-13b-chat-norwegian](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian)
+* [Llama-2-13b-chat-norwegian-LoRa](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-LoRa)
+* [Llama-2-13b-chat-norwegian-GPTQ](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)
 
 
 ## Data
@@ -85,13 +91,32 @@ This model was made at Ruters AI Lab - summer of 2023 as part of their AI initia
 The team wants to thank the support we got from the entire Ruter organization, and especially the Data Science team.
 
 ___
-# Llama 2 13b Chat Norwegian LoRA-adapter (Norsk)
-**Dette er LoRA-adapteren for Llama 2 13b Chat Norwegian modellen, og krever den orginale basismodellen for å kjøre**
-Llama-2-13b-chat-norwegian er en versjon av [Meta](https://huggingface.co/meta-llama) sin [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned på en kombinasjon av diverse norske datasett. Modellen ble laget i [Ruter AI Lab](https://ruter.no) 2023.
+# Llama 2 13b Chat Norwegian GPTQ (Norsk)
+**Dette er en GPTQ versjon av Llama 2 13b Chat Norwegian modellen**
+Llama-2-13b-chat-norwegian-GPQT er en versjon av [Meta](https://huggingface.co/meta-llama) sin [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned på en kombinasjon av diverse norske datasett. Modellen ble laget i [Ruter AI Lab](https://ruter.no) 2023.
+
+Les mer om [GPTQ her](https://towardsdatascience.com/4-bit-quantization-with-gptq-36b0f4f02c34). 
+
+For demo script, se [her](#demo-script).
+
+Andre versjoner av modellen:
+
+* [Llama-2-13b-chat-norwegian](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian)
+* [Llama-2-13b-chat-norwegian-LoRa](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-LoRa)
+* [Llama-2-13b-chat-norwegian-GPTQ](https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)
+
+
+Modellen er finetuned til å forstå og generere tekst på Norsk. Den er trent i én epoch med norwegian-alpaca + et utvalg av 15000 maskinoversatt data fra OpenOrca (datasett venter på utgivelse). Det består og av et lite sett med selvlagde instruksjonsdata.
 
-Modellen er finetuned til å forstå og generere tekst på Norsk. Den er trent i én epoch med norwegian-alpaca + et utvalg av 15000 maskinoversatt data fra OpenOrca (datasett venter på utgivelse). Det består og av et lite sett med selvlagde instruksjonsdata
+**This is a GPTQ version of Llama 2 13b Norwegian**
+
+
+
+
+Llama-2-13b-chat-norwegian is a variant of [Meta](https://huggingface.co/meta-llama)´s [Llama 2 13b Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model, finetuned on a mix of norwegian datasets created in [Ruter AI Lab](https://ruter.no) the summer of 2023.
+
+The model is tuned to understand and generate text in Norwegian. It's trained for one epoch on norwegian-alpaca + 15000 samples of machine-translated data from OpenOrca (the dataset to be released). A small subset of custom-made instructional data is also included.
 
-Vi undersøker for øyeblikekt muligheten for å gi ut en større og sterkere modell i framtiden, og å lage en GGML og GPTQ versjon tilgjengelig for denne modellen.
 
 
 ## Data