Update README.md

README.md

@@ -15,7 +15,6 @@ For enhancing the VLM's perception of fine-grained details w.r.t small objects i
 
 🤗 To get started with Falcon-vlm (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost from HF](https://huggingface.co/blog/falcon)!
 
-⚠️ **This is a raw, pretrained model, which should be further finetuned for most usecases.** 
 
 ```python
 from transformers import LlavaNextForConditionalGeneration, LlavaNextProcessor
@@ -49,7 +48,7 @@ print(generated_captions)
 
 For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost](https://huggingface.co/blog/falcon). 
 
-# Model Card for Falcon2-11B
+# Model Card for Falcon2-11B-VLM
 
 ## Model Details
 
@@ -76,13 +75,13 @@ Production use without adequate assessment of risks and mitigation; any use case
 
 ## Bias, Risks, and Limitations
 
-Falcon2-11B-vlm is trained mostly on English, but also German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish. It will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
+Falcon2-11B is trained mostly on English, but also German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish. It will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
 
 ## Training Details
 
 The training is done in two stages: pretraining and finetuning. In both stages, the visual encoder weights are kept frozen. In the pretraining stage, the LLM is kept frozen and only the multimodal projector is trained on 558K image-caption pairs.
 This enables the multimodal projector to learn a mapping from visual to text embedding space. During finetuning, both the projector and LLM weights are trained on a corpus of 1.2M image-text instruction data from public datasets, which also includes multi-round conversations.
-Falcon2-11B- was trained on 16 A100 80GB GPUs with ZeRO and Flash-Attention 2.
+Falcon2-11B-VLM was trained on 16 A100 80GB GPUs with ZeRO and Flash-Attention 2.
 
 The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[11B](https://huggingface.co/tiiuae/falcon-11B) tokenizer.