jovyan commited on
Commit
f25c81d
·
verified ·
1 Parent(s): 837105b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -11,9 +11,13 @@ model_type: mistral
11
 
12
  Japanese "instruction tuned" model made by the technique of [Chat Vector](https://arxiv.org/abs/2310.04799)
13
 
14
- The weights of this model obtained not by any instruction tuning but by the following arithmetic:
15
  > [Swallow-MS-7b-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1) + [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) - [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
16
 
 
 
 
 
17
  ## Instruction format
18
 
19
  The promot format should be the same as [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
 
11
 
12
  Japanese "instruction tuned" model made by the technique of [Chat Vector](https://arxiv.org/abs/2310.04799)
13
 
14
+ The weights of this model are obtained not by any instruction tuning but by the following arithmetic:
15
  > [Swallow-MS-7b-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1) + [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) - [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
16
 
17
+ -----------------------
18
+ [Chat Vector](https://arxiv.org/abs/2310.04799)の手法を使って、学習済み重みの足し引きのみで[Swallow-MS-7b-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1)モデルにチャット形式の対話能力を与えたモデルです。
19
+
20
+
21
  ## Instruction format
22
 
23
  The promot format should be the same as [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).