tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
Wing Lian
2023-04-18 01:58:32 -04:00
parent 87d7825435
commit 34af1b465f
2 changed files with 34 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
README.md
View File

@@ -1,35 +1,27 @@
# Axolotl
~~# Axolotl
#### You know you're going to axolotl questions
## Getting Started
- Download some datasets.
- Point the config you are using to a huggingface hub dataset (see [configs/llama_7B_4bit.yml](https://github.com/winglian/axolotl/blob/main/configs/llama_7B_4bit.yml#L6-L8))
```shell
curl https://raw.githubusercontent.com/tloen/alpaca-lora/main/alpaca_data_gpt4.json -o data/raw/alpaca_data_gpt4.json
curl https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json -L -o data/raw/vicuna_cleaned.json
curl https://github.com/teknium1/GPTeacher/blob/main/Instruct/gpt4-instruct-similarity-0.6-dataset.json?raw=true -L -o data/raw/gpt4-instruct-similarity-0.6-dataset.json
curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarity_0.6-instruct-dataset.json?raw=true -L -o data/raw/roleplay-similarity_0.6-instruct-dataset.json
```yaml
datasets:
- path: vicgalle/alpaca-gpt4
type: alpaca
```
- Convert the JSON data files to JSONL.
- Optionally Download some datasets, see [data/README.md](data/README.md)
```shell
python3 ./scripts/alpaca_json_to_jsonl.py --input data/alpaca_data_gpt4.json > data/alpaca_data_gpt4.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/vicuna_cleaned.json > data/vicuna_cleaned.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/roleplay-similarity_0.6-instruct-dataset.json > data/roleplay-similarity_0.6-instruct-dataset.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/gpt4-instruct-similarity-0.6-dataset.json > data/gpt4-instruct-similarity-0.6-dataset.jsonl
```
- Using JSONL makes it easier to subset the data if you want a smaller training set, i.e get 2000 random examples.
- Create a new or update the existing YAML config [config/pythia_1_2B_alpaca.yml](config/pythia_1_2B_alpaca.yml)
- Install python dependencies with ONE of the following:
```shell
shuf -n2000 data/vicuna_cleaned.jsonl > data/vicuna_cleaned.subset0.jsonl
```
- Create a new or update the existing YAML config (config/pythia_1_2B_alpaca.yml)[config/pythia_1_2B_alpaca.yml]
- Install python dependencies `pip3 install -e .[int4_triton]` or `pip3 install -e .[int4]`
- `pip3 install -e .[int4]` (recommended)
- `pip3 install -e .[int4_triton]`
- `pip3 install -e .`
-
- If not using `int4` or `int4_triton`, run `pip install "peft @ git+https://github.com/huggingface/peft.git"`
- Configure accelerate `accelerate config` or update `~/.cache/huggingface/accelerate/default_config.yaml`
@@ -52,4 +44,4 @@ use_cpu: false
```
- Train! `accelerate launch scripts/finetune.py`, make sure to choose the correct YAML config file
- Alternatively you can pass in the config file like: `accelerate launch scripts/finetune.py configs/llama_7B_alpaca.yml`
- Alternatively you can pass in the config file like: `accelerate launch scripts/finetune.py configs/llama_7B_alpaca.yml`~~

24
data/README.md
View File

@@ -1,8 +1,24 @@
- Download some datasets
-
```shell
curl https://raw.githubusercontent.com/tloen/alpaca-lora/main/alpaca_data_gpt4.json -o data/raw/alpaca_data_gpt4.json
curl https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json -L -o data/raw/vicuna_cleaned.json
curl https://github.com/teknium1/GPTeacher/blob/main/Instruct/gpt4-instruct-similarity-0.6-dataset.json?raw=true -L -o data/raw/gpt4-instruct-similarity-0.6-dataset.json
curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarity_0.6-instruct-dataset.json?raw=true -L -o data/raw/roleplay-similarity_0.6-instruct-dataset.json
```
- Convert the JSON data files to JSONL.
```shell
curl https://raw.githubusercontent.com/tloen/alpaca-lora/main/alpaca_data_gpt4.json -o raw/alpaca_data_gpt4.json
curl https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json -L -o raw/vicuna_cleaned.json
curl https://github.com/teknium1/GPTeacher/blob/main/Instruct/gpt4-instruct-similarity-0.6-dataset.json?raw=true -L -o raw/gpt4-instruct-similarity-0.6-dataset.json
curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarity_0.6-instruct-dataset.json?raw=true -L -o raw/roleplay-similarity_0.6-instruct-dataset.json
python3 ./scripts/alpaca_json_to_jsonl.py --input data/alpaca_data_gpt4.json > data/alpaca_data_gpt4.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/vicuna_cleaned.json > data/vicuna_cleaned.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/roleplay-similarity_0.6-instruct-dataset.json > data/roleplay-similarity_0.6-instruct-dataset.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/gpt4-instruct-similarity-0.6-dataset.json > data/gpt4-instruct-similarity-0.6-dataset.jsonl
```
- Using JSONL makes it easier to subset the data if you want a smaller training set, i.e get 2000 random examples.
```shell
shuf -n2000 data/vicuna_cleaned.jsonl > data/vicuna_cleaned.subset0.jsonl
```