totally-not-an-llm commited on
Commit
e287966
1 Parent(s): 1a95072

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -10
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: llama2
3
  ---
4
 
5
- # *work in progress!*
6
-
7
  # AlpacaCielo2-7b-8k
8
 
9
  <figure>
@@ -11,17 +9,13 @@ license: llama2
11
  <figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
12
  </figure>
13
 
14
- AlpacaCielo2-7b-8k is the second version of the AlpacaCielo series. It is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes. It is a triple model merge of Nous-Hermes + Guanaco + Storywriter. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
15
 
16
  ### Differences from V1:
17
 
18
  - Double context (4k->8k)
19
  - Better roleplaying abilities
20
 
21
- [GPTQ quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ)<br>
22
- [GGML quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGML)<br>
23
- (Courtesy of TheBloke)
24
-
25
  **Performs well with custom prompt format:**
26
 
27
  ```
@@ -32,6 +26,6 @@ AlpacaCielo2-7b-8k is the second version of the AlpacaCielo series. It is a lla
32
 
33
  *Thanks to previous similar models such as Alpacino, Alpasta, and AlpacaDente for inspiring the creation of this model. Thanks also to the creators of the models involved in the merge. Original models:*
34
 
35
- - [Nous-Hermes-Llama-2](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
36
- - [Guanaco QLoRA](https://huggingface.co/Mikael110/llama-2-13b-guanaco-qlora)
37
- - [Storywriter LoRA](https://huggingface.co/Blackroot/Llama-2-13B-Storywriter-LORA)
 
2
  license: llama2
3
  ---
4
 
 
 
5
  # AlpacaCielo2-7b-8k
6
 
7
  <figure>
 
9
  <figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
10
  </figure>
11
 
12
+ AlpacaCielo2-7b-8k is the second version of the AlpacaCielo series. It is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes. It is a triple model merge of Nous-Hermes + Guanaco + LimaRP. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
13
 
14
  ### Differences from V1:
15
 
16
  - Double context (4k->8k)
17
  - Better roleplaying abilities
18
 
 
 
 
 
19
  **Performs well with custom prompt format:**
20
 
21
  ```
 
26
 
27
  *Thanks to previous similar models such as Alpacino, Alpasta, and AlpacaDente for inspiring the creation of this model. Thanks also to the creators of the models involved in the merge. Original models:*
28
 
29
+ - [Hermes-LLongMA-2](https://huggingface.co/conceptofmind/Hermes-LLongMA-2-7b-8k)
30
+ - [Guanaco QLoRA](https://huggingface.co/Mikael110/llama-2-7b-guanaco-qlora)
31
+ - [LimaRP LoRA](https://huggingface.co/lemonilia/limarp-llama2)