GGUF
English
qwen2
minecraft
Mindcraft
Minecraft
MindCraft
conversational
Sweaterdog commited on
Commit
f9c2dc5
·
verified ·
1 Parent(s): dba48d7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -41,6 +41,8 @@ tags:
41
  4. Run the command in your terminal
42
  5. Now you have Andy-3.6 installed!
43
 
 
 
44
  # How was model trained?
45
 
46
  The model was trained on the [MindCraft dataset](https://huggingface.co/datasets/Sweaterdog/Andy-3.5-MASSIVE) for Andy-3.6, a curated dataset for Q & A, reasoning, and playing, which includes ~22,000 prompts.
@@ -52,8 +54,7 @@ Andy-3.6 also knows how to build / use !newAction to perform commands, it was tr
52
 
53
  # What models can I choose?
54
 
55
- There are going to be 3 model sizes avaliable, Regular, Large, and Small
56
- * Large will be a 32B parameter model, tuned from [Deepseek-R1 Distilled](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit)
57
  * Regular is a 7B parameter model, tuned from [Deepseek-R1 Distilled](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
58
  * Small is a 3B parameter model, tuned from [Qwen2.5 3B](Qwen/Qwen2.5-3B-Instruct)
59
 
@@ -61,8 +62,6 @@ All models will have **case-by-case reasoning** baked **into** the model, meanin
61
 
62
  You can also *prompt* Andy-3.6 to reason for better performance
63
 
64
- There will be a Andy-3.6-code, a model designed strictly for coding tasks, which can be found [here](https://huggingface.co/Sweaterdog/Andy-3.6-code)
65
-
66
  # Safety and FAQ
67
 
68
  Q: Is this model safe to use?
@@ -83,8 +82,8 @@ A. No, if you are making a post about MindCraft, and using this model, you only
83
 
84
  # 🔥UPDATE🔥
85
 
86
- ## **Andy-3.6 Release!**
87
- Andy-3.6 is our Next Generation model, feature more capabilties, and stronger performance over ANY other local LLM in Mindcraft!
88
 
89
  > # I want to thank all supporters! [!NOTE]
90
  > I would love to thank everyone who supported this project, there is a list of supporters in the files section.
 
41
  4. Run the command in your terminal
42
  5. Now you have Andy-3.6 installed!
43
 
44
+ If you would prefer to use Andy-3.6-small, you can find that model [here](https://huggingface.co/Sweaterdog/Andy-3.6-small)
45
+
46
  # How was model trained?
47
 
48
  The model was trained on the [MindCraft dataset](https://huggingface.co/datasets/Sweaterdog/Andy-3.5-MASSIVE) for Andy-3.6, a curated dataset for Q & A, reasoning, and playing, which includes ~22,000 prompts.
 
54
 
55
  # What models can I choose?
56
 
57
+ There are going to be 2 model sizes avaliable, Regular, and Small
 
58
  * Regular is a 7B parameter model, tuned from [Deepseek-R1 Distilled](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
59
  * Small is a 3B parameter model, tuned from [Qwen2.5 3B](Qwen/Qwen2.5-3B-Instruct)
60
 
 
62
 
63
  You can also *prompt* Andy-3.6 to reason for better performance
64
 
 
 
65
  # Safety and FAQ
66
 
67
  Q: Is this model safe to use?
 
82
 
83
  # 🔥UPDATE🔥
84
 
85
+ ## **Andy-3.6-small Release!**
86
+ Andy-3.6-small is the latest model, as well as the last model in the Andy-3.6 generation. That model is capable of more reasoning than Andy-3.6 is.
87
 
88
  > # I want to thank all supporters! [!NOTE]
89
  > I would love to thank everyone who supported this project, there is a list of supporters in the files section.