Files changed (1) hide show
  1. README.md +46 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ ---
4
+ # Vicuna 7B without "ethics" filtering
5
+
6
+ This repository contains an alternative version of the [Vicuna 7B model](https://huggingface.co/lmsys/vicuna-7b-delta-v0).
7
+
8
+ This model was natively fine-tuned using ShareGPT data, but without the "ethics" filtering used for the original Vicuna.
9
+
10
+ [A GPTQ quantised 4-bit version is available here](https://huggingface.co/TheBloke/vicuna-AlekseyKorshuk-7B-GPTQ-4bit-128g).
11
+
12
+ # Original Vicuna Model Card
13
+
14
+ ## Model details
15
+
16
+ **Model type:**
17
+ Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
18
+ It is an auto-regressive language model, based on the transformer architecture.
19
+
20
+ **Model date:**
21
+ Vicuna was trained between March 2023 and April 2023.
22
+
23
+ **Organizations developing the model:**
24
+ The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
25
+
26
+ **Paper or resources for more information:**
27
+ https://vicuna.lmsys.org/
28
+
29
+ **License:**
30
+ Apache License 2.0
31
+
32
+ **Where to send questions or comments about the model:**
33
+ https://github.com/lm-sys/FastChat/issues
34
+
35
+ ## Intended use
36
+ **Primary intended uses:**
37
+ The primary use of Vicuna is research on large language models and chatbots.
38
+
39
+ **Primary intended users:**
40
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
41
+
42
+ ## Training dataset
43
+ 70K conversations collected from ShareGPT.com.
44
+
45
+ ## Evaluation dataset
46
+ A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.