rm old
Browse files
README.md
CHANGED
|
@@ -17,25 +17,6 @@ Monster collection & battle game leveraging Huggingface ZeroGPU spaces!
|
|
| 17 |
|
| 18 |
[Play Here!](https://fraser-piclets.static.hf.space/)
|
| 19 |
|
| 20 |
-
## Battle System
|
| 21 |
-
|
| 22 |
-
Making everything LLM based!
|
| 23 |
-
|
| 24 |
-
The LLM gets the piclet descriptions, stats and action descriptions and then creates a JSON object conveying the status updates (including emojis for effects).
|
| 25 |
-
|
| 26 |
-
This should give the battles a unique "real" feel with interesting effective/ineffective interactions.
|
| 27 |
-
|
| 28 |
-
Status updates come with probabilities allowing for chance in the game while LLM sampling temperature is low.
|
| 29 |
-
|
| 30 |
-
The LLM backed has a dynamic setup so it can switch between providers, for now will use `tencent/Hunyuan-Large` long term may switch to `BlinkDL/RWKV-Gradio-2`.
|
| 31 |
-
|
| 32 |
-
Options for LLM backend:
|
| 33 |
-
1. tencent/Hunyuan-Large (has been free for a while!)
|
| 34 |
-
2. yuntian-deng/ChatGPT (say it will have short term availability)
|
| 35 |
-
3. Fraser/zephyr-7b (runs on zero-gpu)
|
| 36 |
-
4. BlinkDL/RWKV-Gradio-2 (running on T4, never ran into rate limits)
|
| 37 |
-
5. make my own Cohere space (20 generations per minute)
|
| 38 |
-
|
| 39 |
## Old Battle System Ideas
|
| 40 |
|
| 41 |
## How to handle combat?
|
|
|
|
| 17 |
|
| 18 |
[Play Here!](https://fraser-piclets.static.hf.space/)
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## Old Battle System Ideas
|
| 21 |
|
| 22 |
## How to handle combat?
|