GGUF
aashish1904 commited on
Commit
d116b3f
1 Parent(s): dc6a982

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +59 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ inference: false
5
+ license: llama2
6
+
7
+ ---
8
+
9
+ ![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
10
+
11
+ # QuantFactory/vicuna-13b-v1.5-GGUF
12
+ This is quantized version of [lmsys/vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5) created using llama.cpp
13
+
14
+ # Original Model Card
15
+
16
+
17
+ # Vicuna Model Card
18
+
19
+ ## Model Details
20
+
21
+ Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
22
+
23
+ - **Developed by:** [LMSYS](https://lmsys.org/)
24
+ - **Model type:** An auto-regressive language model based on the transformer architecture
25
+ - **License:** Llama 2 Community License Agreement
26
+ - **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)
27
+
28
+ ### Model Sources
29
+
30
+ - **Repository:** https://github.com/lm-sys/FastChat
31
+ - **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
32
+ - **Paper:** https://arxiv.org/abs/2306.05685
33
+ - **Demo:** https://chat.lmsys.org/
34
+
35
+ ## Uses
36
+
37
+ The primary use of Vicuna is research on large language models and chatbots.
38
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
39
+
40
+ ## How to Get Started with the Model
41
+
42
+ - Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
43
+ - APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api
44
+
45
+ ## Training Details
46
+
47
+ Vicuna v1.5 is fine-tuned from Llama 2 with supervised instruction fine-tuning.
48
+ The training data is around 125K conversations collected from ShareGPT.com.
49
+ See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
50
+
51
+ ## Evaluation
52
+
53
+ ![Evaluation Results](https://github.com/lm-sys/lm-sys.github.io/blob/main/public/images/webdata/vicuna_v1.5_eval.png?raw=true)
54
+
55
+ 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).
56
+
57
+ ## Difference between different versions of Vicuna
58
+
59
+ See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)