Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,22 @@ Everyone-Coder-33b-Base
|
|
12 |
|
13 |
EveryoneLLM series of models made by the community, for the community. This is a coding specific model made using fine-tunes of deekseekcoder-33b-base.
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
The models that were used in this merger were as follow:
|
16 |
|
17 |
- https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct
|
|
|
12 |
|
13 |
EveryoneLLM series of models made by the community, for the community. This is a coding specific model made using fine-tunes of deekseekcoder-33b-base.
|
14 |
|
15 |
+
Ive recently noticed this model has trouble with end tokens so I made a custom prompt template for it. Made sure to add (Always end with "<|EOT|>") In addition to your system prompt and (Always end your response with "<|EOT|>") at the end of the User message is the preset.
|
16 |
+
|
17 |
+
```
|
18 |
+
Always end with "<|EOT|>"
|
19 |
+
|
20 |
+
{System}
|
21 |
+
|
22 |
+
<|User|>
|
23 |
+
|
24 |
+
{User}. Always end your response with "<|EOT|>"
|
25 |
+
|
26 |
+
<|Assistant|>
|
27 |
+
|
28 |
+
{Assistant}
|
29 |
+
```
|
30 |
+
|
31 |
The models that were used in this merger were as follow:
|
32 |
|
33 |
- https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct
|