Skip to content

Commit 03b6943

Browse files
Update Llama2-for-non-engineers.md (#1540)
1 parent eeb8915 commit 03b6943

File tree

1 file changed

+10
-10
lines changed

1 file changed

+10
-10
lines changed

Llama2-for-non-engineers.md

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ authors:
99
<!-- {blog_metadata} -->
1010
<!-- {authors} -->
1111

12-
# I trained a LLaMA 2 chatbot without code, you can too
12+
# Non-engineers guide: Train a LLaMA 2 chatbot
1313

1414
## Introduction
1515

@@ -47,7 +47,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
4747
1.1 Go to [huggingface.co/spaces](https://huggingface.co/docs/hub/spaces) and select “Create new Space”.
4848

4949
<p align="center">
50-
<img src="/blog/assets/78_ml_director_tuto1.png"><br>
50+
<img src="/blog/assets/78_ml_director_insights/tuto1.png"><br>
5151
</p>
5252

5353
1.2 Give your Space a name and select a preferred usage license if you plan to make your model or Space public.
@@ -56,7 +56,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
5656

5757

5858
<p align="center">
59-
<img src="/blog/assets/78_ml_director_tuto2.png"><br>
59+
<img src="/blog/assets/78_ml_director_insights/tuto2.png"><br>
6060
</p>
6161

6262
1.4 Select your “Space hardware” for running the app. (Note: For the AutoTrain app the free CPU basic option will suffice, the model training later on will be done using separate compute which we can choose later)
@@ -69,7 +69,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
6969

7070

7171
<p align="center">
72-
<img src="/blog/assets/78_ml_director_tuto3.png"><br>
72+
<img src="/blog/assets/78_ml_director_insights/tuto3.png"><br>
7373
</p>
7474

7575
### Step 2: Launch a Model Training in AutoTrain
@@ -83,7 +83,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
8383
2.4 Of course to fine-tune a model you’ll need to upload “Training Data”. When you do, make sure the dataset is correctly formatted and in CSV file format. An example of the required format can be found [here](https://huggingface.co/docs/autotrain/main/en/llm_finetuning). If your dataset contains multiple columns, be sure to select the “Text Column” from your file that contains the training data. In this example we’ll be using the Alpaca instruction tuning dataset, more information about this dataset is available [here](https://huggingface.co/datasets/tatsu-lab/alpaca).
8484

8585
<p align="center">
86-
<img src="/blog/assets/78_ml_director_tuto4.png"><br>
86+
<img src="/blog/assets/78_ml_director_insights/tuto4.png"><br>
8787
</p>
8888

8989
2.5 Optional: You can upload “Validation Data” to test your newly trained model against, but this isn’t required.
@@ -94,7 +94,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
9494

9595

9696
<p align="center">
97-
<img src="/blog/assets/78_ml_director_tuto5.png"><br>
97+
<img src="/blog/assets/78_ml_director_insights/tuto5.png"><br>
9898
</p>
9999

100100
2.8 Now everything is set up, select “Add Job” to add the model to your training queue then select “Start Training” (Note: If you want to train multiple models versions with different hyper-parameters you can add multiple jobs to run simultaneously)
@@ -105,7 +105,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
105105

106106

107107
<p align="center">
108-
<img src="/blog/assets/78_ml_director_tuto6.png"><br>
108+
<img src="/blog/assets/78_ml_director_insights/tuto6.png"><br>
109109
</p>
110110

111111
### Step 3: Create a new ChatUI Space using your model
@@ -116,7 +116,7 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
116116

117117

118118
<p align="center">
119-
<img src="/blog/assets/78_ml_director_tuto7.png"><br>
119+
<img src="/blog/assets/78_ml_director_insights/tuto7.png"><br>
120120
</p>
121121

122122
3.3 If you have your own Mongo DB you can provide those details in order to store chat logs under “MONGODB_URL”. Otherwise leave the field blank and a local DB will be created automatically.
@@ -127,13 +127,13 @@ You can read more about ChatUI [here](https://github.com/huggingface/chat-ui).
127127

128128

129129
<p align="center">
130-
<img src="/blog/assets/78_ml_director_tuto8.png"><br>
130+
<img src="/blog/assets/78_ml_director_insights/tuto8.png"><br>
131131
</p>
132132

133133
3.5 Now you are ready to hit “Create” and launch your very own open-source ChatGPT. Congratulations! If you’ve done it right it should look like this.
134134

135135
<p align="center">
136-
<img src="/blog/assets/78_ml_director_tuto9.png"><br>
136+
<img src="/blog/assets/78_ml_director_insights/tuto9.png"><br>
137137
</p>
138138

139139

0 commit comments

Comments
 (0)