TheBloke commited on
Commit
8f56843
1 Parent(s): 7be0aee

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -0
README.md CHANGED
@@ -1,3 +1,51 @@
1
  ---
2
  license: other
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: other
3
+ inference: false
4
  ---
5
+ # Vicuna 13B 1.1 GPTQ 4bit 128g
6
+
7
+ This is a 4-bit GPTQ version of the [Vicuna 13B 1.1 model](https://huggingface.co/lmsys/vicuna-13b-delta-v1.1).
8
+
9
+ It was created by merging the deltas provided in the above repo with the original Llama 13B model, [using the code provided on their Github page](https://github.com/lm-sys/FastChat#vicuna-weights).
10
+
11
+ It was then quantized to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
12
+
13
+ # Vicuna Model Card
14
+
15
+ ## Model details
16
+
17
+ **Model type:**
18
+ Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
19
+ It is an auto-regressive language model, based on the transformer architecture.
20
+
21
+ **Model date:**
22
+ Vicuna was trained between March 2023 and April 2023.
23
+
24
+ **Organizations developing the model:**
25
+ The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
26
+
27
+ **Paper or resources for more information:**
28
+ https://vicuna.lmsys.org/
29
+
30
+ **License:**
31
+ Apache License 2.0
32
+
33
+ **Where to send questions or comments about the model:**
34
+ https://github.com/lm-sys/FastChat/issues
35
+
36
+ ## Intended use
37
+ **Primary intended uses:**
38
+ The primary use of Vicuna is research on large language models and chatbots.
39
+
40
+ **Primary intended users:**
41
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
42
+
43
+ ## Training dataset
44
+ 70K conversations collected from ShareGPT.com.
45
+
46
+ ## Evaluation dataset
47
+ 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.
48
+
49
+ ## Major updates of weights v1.1
50
+ - 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.
51
+ - Fix the supervised fine-tuning loss computation for better model quality.