Comments (4)
You only need to finetune the model -- the tokenizer remains unchanged, e.g., the tokenizer princeton-nlp/AutoCompressor-Llama-2-7b-6k
is the same as the standard Llama-2 tokenizer.
from autocompressors.
This should be straightforward!
First, have a look at the train.sh and train_llama.sh scripts in the run/
folder. To fine-tune from an existing AutoCommpressor instead of an LM base model, simply change the model_url
variable to a AutoCompressor on huggingface-hub or from a local checkpoint, e.g., changing this line to model_url="princeton-nlp/AutoCompressor-Llama-2-7b-6k"
will fine-tune from this model.
from autocompressors.
Thanks!
Also, I couldn't find references to training/finetuning a tokenizer in the paper. But in the example usage, you refer to a custom tokenizer (I think).
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/AutoCompressor-Llama-2-7b-6k")
.
Do we need to finetune the tokenizer also and not just the model?
from autocompressors.
@imbalu007 Hi, have you finetuned the AutoCompressor model on downstream task? If so, what about the performance? Thanks.
from autocompressors.
Related Issues (20)
- Inquiry for the release date of the pre-trained model HOT 1
- Question on the preprocessed data HOT 3
- CUDA out of memory. HOT 3
- Summary Vector Failures and Incomplete Answers with Numerical Contexts HOT 4
- BUG REPORT HOT 1
- Install instructions are not clear HOT 2
- AttributeError: 'SubstepTrainer' object has no attribute 'do_grad_scaling' HOT 3
- Dimension of last_hidden_state size HOT 2
- RuntimeError: FlashAttention only support fp16 and bf16 data type HOT 3
- Held-out perplexity question HOT 3
- question about `position_ids` HOT 2
- Reduce the number of summary vectors HOT 2
- Question about the data preprocessing HOT 1
- Inquire on data of Table 1 HOT 1
- Some issue about ICL Experience HOT 3
- Install as python package? HOT 1
- substep & segment HOT 1
- torchrun error when generating training split HOT 3
- Your shared model trained on LLAMA2 is not trained on Lora, It's full-finetuned model. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from autocompressors.