Update README.md

README.md

@@ -11,28 +11,23 @@ This is a version of the LLama-2-70B-chat-hf model quantized to 2-bit via Half-Q
 ### Basic Usage
 To run the model, install the HQQ library from https://github.com/mobiusml/hqq and use it as follows:
 ``` Python
-from hqq.models.llama_hf import LlamaHQQ
-import transformers
-
 model_id = 'mobiuslabsgmbh/Llama-2-70b-chat-hf-2bit_g16_s128-HQQ'
-#Load the tokenizer
-tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
-#Load the model
-model = LlamaHQQ.from_quantized(model_id)
+
+from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model     = HQQModelForCausalLM.from_quantized(model_id)
 ```
 
 ### Basic Chat Example
 ``` Python
-import transformers
-from hqq.models.llama_hf import LlamaHQQ
+model_id = 'mobiuslabsgmbh/Llama-2-70b-chat-hf-2bit_g16_s128-HQQ'
 
-model_id  = 'mobiuslabsgmbh/Llama-2-70b-chat-hf-2bit_g16_s128-HQQ'
-#Load the tokenizer
-tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
-#Load the model
-model     = LlamaHQQ.from_quantized(model_id)
+from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model     = HQQModelForCausalLM.from_quantized(model_id)
 
 ##########################################################################################################
+import transformers
 from threading import Thread
 
 from sys import stdout