TheBloke commited on
Commit
267e97e
1 Parent(s): b4172ab

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md CHANGED
@@ -1,3 +1,48 @@
1
  ---
2
  license: other
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: other
3
  ---
4
+ # Vicuna 7B 1.1 HF
5
+
6
+ This is an HF version of the [Vicuna 7B 1.1 model](https://huggingface.co/lmsys/vicuna-7b-delta-v1.1).
7
+
8
+ It was created by merging the deltas provided in the above repo with the original Llama 7B model, [using the code provided on their Github page](https://github.com/lm-sys/FastChat#vicuna-weights).
9
+
10
+ # Vicuna Model Card
11
+
12
+ ## Model details
13
+
14
+ **Model type:**
15
+ Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
16
+ It is an auto-regressive language model, based on the transformer architecture.
17
+
18
+ **Model date:**
19
+ Vicuna was trained between March 2023 and April 2023.
20
+
21
+ **Organizations developing the model:**
22
+ The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
23
+
24
+ **Paper or resources for more information:**
25
+ https://vicuna.lmsys.org/
26
+
27
+ **License:**
28
+ Apache License 2.0
29
+
30
+ **Where to send questions or comments about the model:**
31
+ https://github.com/lm-sys/FastChat/issues
32
+
33
+ ## Intended use
34
+ **Primary intended uses:**
35
+ The primary use of Vicuna is research on large language models and chatbots.
36
+
37
+ **Primary intended users:**
38
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
39
+
40
+ ## Training dataset
41
+ 70K conversations collected from ShareGPT.com.
42
+
43
+ ## Evaluation dataset
44
+ 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.
45
+
46
+ ## Major updates of weights v1.1
47
+ - Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `"</s>"`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
48
+ - Fix the supervised fine-tuning loss computation for better model quality.