Views
No views yet
[!NOTE]
Note: this model is a re-train of the previous model. Read why the model was re-trained here: Findings for HumanPet X2.1 1.7B
1<|im_start|>system
2System message<|im_end|>
3<|im_start|>user
4User prompt<|im_end|>
5<|im_start|>assistant
6Assistant response<|im_end|>1<|im_start|>assistant
2<think>
3
4</think>
5
6What happened?
7
8<emote>:^</emote><|im_end|><think>...</think> tags are always empty, as this model was not trained on reasoning data.
The <emote>...</emote> tags contain a text emoji that the model thinks fits most with the response. The emojis it may output are:10^0
2u~u
3u.u
4:^
5:3
6x3
70w0
8u-u
9:P
10>.<
11>-<
12owo
13U.U
14:]
15^-^
16>:3
17:0
18:O
190~0
20o^o
21O^O
22@~@
23@.@
24o~o
25T^T
26>~<
27>.0
28o.o
29>^<
300.0
310-0
32-w-
33-.-
34T-T
35T.T
36T~T
37:<
38u^u