wang7776 commited on
Commit
2a256b5
1 Parent(s): 18f5d8f

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -1
README.md CHANGED
@@ -1,3 +1,43 @@
1
  ---
2
- license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ inference: false
3
  ---
4
+ # Vicuna Model Card
5
+
6
+ ## Model Details
7
+
8
+ Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
9
+
10
+ - **Developed by:** [LMSYS](https://lmsys.org/)
11
+ - **Model type:** An auto-regressive language model based on the transformer architecture.
12
+ - **License:** Non-commercial license
13
+ - **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971).
14
+
15
+ ### Model Sources
16
+
17
+ - **Repository:** https://github.com/lm-sys/FastChat
18
+ - **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
19
+ - **Paper:** https://arxiv.org/abs/2306.05685
20
+ - **Demo:** https://chat.lmsys.org/
21
+
22
+ ## Uses
23
+
24
+ The primary use of Vicuna is research on large language models and chatbots.
25
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
26
+
27
+ ## How to Get Started with the Model
28
+
29
+ - Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights.
30
+ - APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api.
31
+
32
+ ## Training Details
33
+
34
+ Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
35
+ The training data is around 125K conversations collected from ShareGPT.com.
36
+ See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
37
+
38
+ ## Evaluation
39
+
40
+ Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
41
+
42
+ ## Difference between different versions of Vicuna
43
+ See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)