chimbiwide commited on
Commit
6b18a0a
·
verified ·
1 Parent(s): fa3482f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -5
README.md CHANGED
@@ -25,6 +25,13 @@ Rest in peace 4070.
25
  ---
26
 
27
  ### Our Work:
 
 
 
 
 
 
 
28
  **[Gemma3NPC models](https://huggingface.co/collections/npcLM/gemma3npc-all)**
29
 
30
  - `Gemma3NPC-it` - Specialized for NPC dialogues(Recommended)
@@ -32,20 +39,45 @@ Rest in peace 4070.
32
  - `Gemma3NPC` - General Roleplaying
33
  - `Gemma3NPC-filtered` - filtered model, more censored
34
 
 
 
 
 
 
35
  **[GemmaReLe](https://huggingface.co/collections/npcLM/rele)**
36
 
37
  - A model finetuned specifically for ReLe, performance requires further evaluation.
38
 
39
- **[Datasets](https://huggingface.co/collections/npcLM/finetuning-datasets)**
 
 
 
 
 
40
 
41
- - PIPPA(processed, includes original&filtered)
42
- - NPC-Dialogue (v1&v2)
 
 
 
43
  - SonnetRolePlay
44
  - ReLe_Synthetic_v1
45
 
46
- **[Technical Blog](https://huggingface.co/blog/chimbiwide/gemma3npc)**
 
 
 
 
 
 
 
 
 
 
 
 
47
 
48
- **[Demo Video](https://youtu.be/N8-XZQ8C6kc?si=X48VmhDfSukgpSLT)**
49
 
50
  ---
51
 
 
25
  ---
26
 
27
  ### Our Work:
28
+
29
+ **[Gemma4NPC models](https://huggingface.co/collections/npcLM/gemma4npc)**
30
+ Our newest version of the GemmaNPC series, using the new Gemma 4 models.
31
+ - `Gemma4NPC-E4B` - larger (Recommended)
32
+ - `Gemma4NPC-E2B` - for edge devices
33
+ Both have vision and audio functining properly.
34
+
35
  **[Gemma3NPC models](https://huggingface.co/collections/npcLM/gemma3npc-all)**
36
 
37
  - `Gemma3NPC-it` - Specialized for NPC dialogues(Recommended)
 
39
  - `Gemma3NPC` - General Roleplaying
40
  - `Gemma3NPC-filtered` - filtered model, more censored
41
 
42
+ **[GemmaThink models](https://huggingface.co/collections/npcLM/gemmathink)**
43
+
44
+ - `gemma-3-1b-it-thinking-32k-grpo-merged` - The **complete** model trained on the 32k row reasoning dataset(recommended)
45
+ - `gemma-3-1b-it-thinking-20k-sft-rl` - Trained on the 20k row reasoning dataset
46
+
47
  **[GemmaReLe](https://huggingface.co/collections/npcLM/rele)**
48
 
49
  - A model finetuned specifically for ReLe, performance requires further evaluation.
50
 
51
+ **[Finetuning Datasets](https://huggingface.co/collections/npcLM/finetuning-datasets)**
52
+ The datasets used to train our models.
53
+ - PIPPA (processed, includes original & filtered)
54
+ - NPC-Dialogue (v1 & v2)
55
+ - SonnetRolePlay
56
+ - ReLe_Synthetic_v1
57
 
58
+ **[RP Datasets](https://huggingface.co/collections/npcLM/rp-datasets)**
59
+ Individual roleplaying datasets.
60
+ - PIPPA (original & filtered)
61
+ - NPC-Dialogue (v1 & v2)
62
+ - NPC-Quest-Dialogue
63
  - SonnetRolePlay
64
  - ReLe_Synthetic_v1
65
 
66
+ **[Reasoning Datasets](https://huggingface.co/collections/npcLM/reasoning-datasets)
67
+ Synthetically generated reasoning data using Qwen3-14b.
68
+ - code-thinking
69
+ - Creative-Writing-Thinking
70
+ - sciqa-thinking
71
+ - brainstorming-thinking
72
+ - gsm8k-thinking
73
+ - databricks-thinking
74
+ - cnn-summarization
75
+
76
+ Gemma3NPC **[Technical Blog](https://huggingface.co/blog/chimbiwide/gemma3npc)**
77
+
78
+ Gemma3NPC **[Demo Video](https://youtu.be/N8-XZQ8C6kc?si=X48VmhDfSukgpSLT)**
79
 
80
+ GemmaThink **[Demo Video](https://youtu.be/MrwM3-S6DVs?si=cKUUkWeWQ-Z_ffu-)**
81
 
82
  ---
83