Update README.md

README.md

@@ -36,7 +36,9 @@ The model is developed to process diverse inputs, including images and text, fac
 
 Cephalo provides a robust framework for multimodal interaction and understanding, including the development of complex generative pipelines to create 2D and 3D renderings of material microstructures as input for additive manufacturing methods.
 
-This version of Cephalo, lamm-mit/Cephalo-Idefics-2-vision-10b-alpha, is based on a merged expansion of the https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-beta and the HuggingFaceM4/idefics2-8b-chatty model. This method allows us to increase the depth of the model and focus on learning more complex representations and associations in deeper layers of the network.
+This version of Cephalo, lamm-mit/Cephalo-Idefics-2-vision-10b-beta, is based on a merged expansion of the https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-beta and the HuggingFaceM4/idefics2-8b-chatty model. This method allows us to increase the depth of the model and focus on learning more complex representations and associations in deeper layers of the network. 
+
+The lamm-mit/Cephalo-Idefics-2-vision-10b-beta model is trained for two epochs, while the lamm-mit/Cephalo-Idefics-2-vision-10b-alpha version was trained for one epoch.
 
 The model was trained in several stages:
 
@@ -50,7 +52,7 @@ The model was trained on a combination of scientific text-image data extracted f
 
 ### Chat Format
 
-The lamm-mit/Cephalo-Idefics-2-vision-10b-alpha model is suitable for one or more image inputs, wih prompts using the chat format as follows:
+The lamm-mit/Cephalo-Idefics-2-vision-10b-beta model is suitable for one or more image inputs, wih prompts using the chat format as follows:
 
 ```raw
 User: You carefully study the image, and respond accurately, but succinctly. Think step-by-step.
@@ -86,7 +88,7 @@ DEVICE='cuda:0'
 from transformers import AutoProcessor, Idefics2ForConditionalGeneration 
 from tqdm.notebook import tqdm
  
-model_id='lamm-mit/Cephalo-Idefics-2-vision-10b-alpha'
+model_id='lamm-mit/Cephalo-Idefics-2-vision-10b-beta'
 
 model = Idefics2ForConditionalGeneration.from_pretrained(  model_id,
                                                            torch_dtype=torch.bfloat16, #if your GPU allows
@@ -266,7 +268,7 @@ If your GPU allows, load and run inference in half precision (`torch.float16` or
 
 ```diff
 model = AutoModelForVision2Seq.from_pretrained(
-    "lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+    "lamm-mit/Cephalo-Idefics-2-vision-10b-beta",
 +    torch_dtype=torch.float16,    
 ).to(DEVICE)
 ```
@@ -287,7 +289,7 @@ Mke sure to install `flash-attn`. Refer to the [original repository of Flash Att
 
 ```diff
 model = AutoModelForVision2Seq.from_pretrained(
-    "lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+    "lamm-mit/Cephalo-Idefics-2-vision-10b-beta",
 +    torch_dtype=torch.bfloat16,    
 +    _attn_implementation="flash_attention_2",
 ).to(DEVICE)
@@ -298,7 +300,7 @@ model = AutoModelForVision2Seq.from_pretrained(
 **4 bit quantization with bitsandbytes**
 
 <details><summary>Click to expand.</summary>
-It is possible to load Idefics2 in 4bits with `bitsandbytes`. Make sure that you have `accelerate` and `bitsandbytes` installed.
+It is possible to load Cephalo-Idefics-2-vision-10b-beta in 4bits with `bitsandbytes`. Make sure that you have `accelerate` and `bitsandbytes` installed.
 
 ```diff
 + from transformers import BitsAndBytesConfig
@@ -310,7 +312,7 @@ quantization_config = BitsAndBytesConfig(
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 model = AutoModelForVision2Seq.from_pretrained(
-    "lamm-mit/Cephalo-Idefics-2-vision-8b-beta",
+    "lamm-mit/Cephalo-Idefics-2-vision-10b-beta",
 +    torch_dtype=torch.bfloat16,    
 +    quantization_config=quantization_config,
 ).to(DEVICE)