Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
inference: false
|
4 |
+
datasets:
|
5 |
+
- PengQu/langchain-MRKL-finetune
|
6 |
+
- fnlp/moss-003-sft-data
|
7 |
+
- anon8231489123/ShareGPT_Vicuna_unfiltered
|
8 |
+
---
|
9 |
+
|
10 |
+
|
11 |
+
**NOTE: This "delta model" cannot be used directly.**
|
12 |
+
Users have to apply it on top of the original LLaMA weights to get actual Vicuna weights.
|
13 |
+
See https://github.com/pengqu123/vicuna-13b-delta-finetuned-langchain-MRKL for instructions.
|
14 |
+
<br>
|
15 |
+
<br>
|
16 |
+
|
17 |
+
# vicuna-13b-finetuned-langchain-MRKL
|
18 |
+
|
19 |
+
## Model details
|
20 |
+
|
21 |
+
**Model type:**
|
22 |
+
vicuna-13b-finetuned-langchain-MRKL is an open-source chatbot trained by fine-tuning vicuna-13b on 15 examples with langchain-MRKL format.
|
23 |
+
|
24 |
+
**Where to send questions or comments about the model:**
|
25 |
+
https://github.com/pengqu123/vicuna-13b-delta-finetuned-langchain-MRKL/issues
|
26 |
+
|
27 |
+
## Intended use
|
28 |
+
**Primary intended uses:**
|
29 |
+
The primary use of Vicuna is research on large language models and chatbots.
|
30 |
+
|
31 |
+
**Primary intended users:**
|
32 |
+
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
|
33 |
+
|
34 |
+
## Training dataset
|
35 |
+
train only one epoch on mix data (sharegpt + 32*my.json + moss-003-sft-data)
|
36 |
+
|
37 |
+
## Evaluation
|
38 |
+
demo code: https://github.com/pengqu123/vicuna-13b-delta-finetuned-langchain-MRKL/blob/main/demo.ipynb
|
39 |
+
No evaluation set. Because we don't improve the ability of model. we just make model fit langchain-MRKL strictly.
|
40 |
+
We just want to show vicuna-13b's powerful ability about thinking and action.
|
41 |
+
This is the first step. We hope if we get more samples about more tools, we can support more complicate plugins too.
|
42 |
+
|
43 |
+
## Major Improvement
|
44 |
+
- support langchain-MRKL(agent= "zero-shot-react-description")
|
45 |
+
- very fast because of stritcly format(it doesn't generate redundant tokens)
|