Update README.md

README.md

@@ -91,11 +91,11 @@ goto loop
 12. Enjoy having a model play Minecraft with you, hopefully it is smarter than regular Gemini models!
 #
 
-I'm aware it does say there are multiple Qwen2.5 files, even though there are two, and it also says there are Gemma2 models, even though there isn't, I am aware and have been trying to train the rest of these models.
+**WARNING** The new v3 generation of models suck! That is because they were also trained for building *(coding)* and often do not use commands! I recommend using the v2 generation still, it is in the [deprecated models folder](https://huggingface.co/Sweaterdog/MindCraft-LLM-tuning/tree/main/deprecated-models).
 
 # 
 
-For Anybody who is wondering what the context length is, for the Hermesv1, they have a context window of 8196 tokens. For the Qwen version, it will have a length of 64000 tokens, for the Llama version, it will have 128000 tokens.  they will use a larger dataset, at about 1.6 times the size of the v1 generation.
+For Anybody who is wondering what the context length is, for the Hermesv1, they have a context window of 8196 tokens. For the Qwen version, it will have a length of 64000 tokens, for the Llama version, it will have 128000 tokens.
 
 # 
 
@@ -103,7 +103,7 @@ I wanted to include the google colab link, in case you wanted to know how to tra
 
 # 
 
-**UPDATE** The Qwen and Llama models are out, with the expanded dataset! I have found the llama models are incredibly dumb, but changing the Modelfile may provide better results, With the Qwen version of Andy, the Q4_K_M, it took 2 minutes to craft a wooden pickaxe, collected stone after that, took 5 minutes,
+**UPDATE** The Qwen and Llama models are out, with the expanded dataset! I have found the llama models are incredibly dumb, but changing the Modelfile may provide better results, With the Qwen version of Andy, the Q4_K_M, it took 2 minutes to craft a wooden pickaxe, collected stone after that, took 5 minutes.
 
 #