added airllm experiment

AirLLM.py

@@ -11,7 +11,7 @@ class AirLLM(LLM):
 
     def __init__(self, llama2_model_id : str, max_len : int, compression = ""):            
         # could use hugging face model repo id:
-        self.model = AirLLMLlama2(llama2_model_id,compression=compression)
+        self.model = AirLLMLlama2(llama2_model_id)#,compression=compression
         self.max_len = max_len
 
     @property

RBotReloaded.py

@@ -34,7 +34,7 @@ from typing import Any, Dict, List
 import torch
 from diffusers.pipelines.stable_diffusion.convert_from_ckpt import download_from_original_stable_diffusion_ckpt
 import inspect
-import AirLLM
+from AirLLM import AirLLM
 
 # Config  
 EMBD_CHUNK_SIZE = 512  

agent_llama_ui.py

@@ -43,7 +43,7 @@ def get_models():
     models = os.listdir(models_directory)
     # Filter out any subdirectories, if any
     models = [model for model in models if (model.lower().split(".")[-1] in supported_extensions) and os.path.isfile(os.path.join(models_directory, model))]  
-    
+    models.append("garage-bAInd/Platypus2-70B-instruct")
     if len(models) == 0:
         st.write("Downloading models")
         from huggingface_hub import hf_hub_download