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

Merge pull request #61 from NanoCode012/feat/update-readme

Browse Source 
Feat: Update readme
This commit is contained in:
NanoCode012
2023-05-26 11:27:31 +09:00
committed by GitHub
parent 259262bf42 85326bfbf3
commit 3815c054b6
1 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@@ -33,12 +33,12 @@ pip3 install -e .[int4]
accelerate config accelerate config
# finetune # finetune lora
accelerate launch scripts/finetune.py examples/4bit-lora-7b/config.yml accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml
# inference # inference
accelerate launch scripts/finetune.py examples/4bit-lora-7b/config.yml \ accelerate launch scripts/finetune.py examples/lora-openllama-3b/config.yml \
--inference --lora_model_dir="./llama-7b-lora-int4" --inference --lora_model_dir="./lora-out"
``` ```
## Installation ## Installation
@@ -199,8 +199,7 @@ datasets:
# The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection] # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
type: alpaca # format OR format:prompt_style (chat/instruct) type: alpaca # format OR format:prompt_style (chat/instruct)
data_files: # path to source data files data_files: # path to source data files
shards: # true if use subset data. make sure to set `shards` param also shards: # number of shards to split data into
shards: # number of shards to split dataset into
# axolotl attempts to save the dataset as an arrow after packing the data together so # axolotl attempts to save the dataset as an arrow after packing the data together so
# subsequent training attempts load faster, relative path # subsequent training attempts load faster, relative path
@@ -326,6 +325,9 @@ debug:
# Seed # Seed
seed: seed:
# Allow overwrite yml config using from cli
strict:
``` ```
</details> </details>
@@ -382,6 +384,10 @@ Please reduce any below
Try set `fp16: true` Try set `fp16: true`
> NotImplementedError: No operator found for `memory_efficient_attention_forward` ...
Try to turn off xformers.
## Need help? 🙋‍♂️ ## Need help? 🙋‍♂️
Join our [Discord server](https://discord.gg/HhrNrHJPRb) where we can help you Join our [Discord server](https://discord.gg/HhrNrHJPRb) where we can help you