ddh0 commited on
Commit
09e6f8b
1 Parent(s): 15fb17e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -1
README.md CHANGED
@@ -7,4 +7,31 @@ pipeline_tag: text-generation
7
 
8
  # Nororcetacean-20b-10k
9
 
10
- Coming soon
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
 
8
  # Nororcetacean-20b-10k
9
 
10
+ This is Jeb Carter's [Psyonic-Cetacean-20B](https://huggingface.co/jebcarter/psyonic-cetacean-20B), merged with Undi's [no_robots-alpaca LoRA](https://huggingface.co/Undi95/Llama2-13B-no_robots-alpaca-lora) and extended to `10240` context length via YaRN.
11
+
12
+ The overall goal of this merge was to create a model with the unique brain of Psyonic-Cetacean and the human voice of the no_robots dataset, that would remain capable at long contexts.
13
+
14
+ The prompt format is Alpaca. You can use the standard format as shown, but for best results, I strongly recommend customizing the system prompt to your specific needs.
15
+
16
+ ```
17
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
18
+
19
+ ### Instruction:
20
+ {YOUR MESSAGE HERE}
21
+
22
+ ### Response:
23
+ {BOT MESSAGE HERE}
24
+
25
+
26
+ ```
27
+
28
+ ### Misc. information
29
+ - BOS token is `<s>`
30
+ - EOS token is `</s>`
31
+ - Native context length is `10240` via YaRN (original context length was `4096`)
32
+ - Base model is Llama 2
33
+ - Due to the inclusion of Orca-2-13b, the model is subject to the terms of the [Microsoft Research License](https://huggingface.co/microsoft/Orca-2-13b/blob/main/LICENSE)
34
+
35
+ ### Thanks
36
+ - Thanks to [Jeb Carter](https://huggingface.co/jebcarter) for Psyonic-Cetacean-20B
37
+ - Thanks to [Undi](https://ko-fi.com/undiai) for the no_robots-alpaca LoRA