Update README.md

README.md

@@ -3,9 +3,9 @@ base_model: casperhansen/llama-3-70b-fp16
 tags:
 - llama
 - NorskGPT
-- instruct
-- finetune
 - qlora
+- base model
+- Norwegian
 language:
 - 'no'
 license: cc-by-nc-sa-4.0
@@ -14,7 +14,7 @@ license: cc-by-nc-sa-4.0
 
 # NorskGPT-Llama-3-70b-v0.1-adapter
 
-This is a Norwegian adapter for [Llama-3-70b-fp16](casperhansen/llama-3-70b-fp16), fine-tuned on a carefully selected mix of Norwegian instruction pairs. The model is tuned to understand and generate text in Norwegain. 
+This is a Norwegian adapter for [Llama-3-70b-fp16](casperhansen/llama-3-70b-fp16), where the model was trained on 1M tokens from Norwegian text. It should be used as a base model, that would need more training in order to be able to chat with the user.
 
 
 ## Intended Use
@@ -23,19 +23,6 @@ This model is free to use for personal and research use. However a commercial li
 This model can be used as an assistant-like chat. Try it out :)
 
 
-## Prompt Template
-
-```
-### Instruction:
-Summarize following text.
-### Input:
-Text to be summarized
-### Response:
-```
-## How to run the model
-
-A guide will be released in the following week.
-
 
 ## Limitations
 *   This is an LLM, not a knowledge model. It can not be expected to have more information about Norway than the base model.