Comments (1)
I figured out the fifth line in algorithm self_rag inference.the meaning of "M predicts ISREL given x, d and yt given x, d, y<t for each d ∈ D". In my opinion, given x, d and yt is no need. "given x, d, y<t " is right." is very easy if you read the code in eval demos.
here is the explaination:
- input of the slef_rag model(real data)
evidence_augmented_inputs = "### Instruction:\nWhat is Henry Feilden's occupation?\n\n### Response:\n[Retrieval]<paragraph>Henry Feilden (Conservative politician)\n Henry Master Feilden (21 February 1818 – 5 September 1875) was an English Conservative Party politician.</paragraph>"
preds = model.generate(evidence_augmented_inputs, sampling_params)
(Pdb) pred_token_ids
[32004, 24030, 719, 5169, 789, 264, 338, 263, 14099, 29889, 32012, 32011, 2]
(Pdb) pred_text
'Henry Feilden is a politician.'
(Pdb) tokenizer.convert_ids_to_tokens(pred_token_ids)
['[Relevant]', 'Hen', 'ry', '▁Fe', 'ild', 'en', '▁is', '▁a', '▁politician', '.', '[Fully supported]', '[Utility:5]', '</s>']
As you can see the value above. '[Fully supported]' and '[Utility:5]' will be output after model output yt.
- In paper
d = [Retrieval]Henry Feilden (Conservative politician)\n Henry Master Feilden (21 February 1818 – 5 September 1875) was an English Conservative Party politician.
yt = 'Henry Feilden is a politician.'
y<t = ### Instruction:\nWhat is Henry Feilden's occupation?\n\n### Response:\n (there is no preceeding sentence, because the number of retrieval is one, )
I will close this comment, bucause I have aleardy understand this algorithm. fell free to reopen and comment~
from self-rag.
Related Issues (20)
- Where does the retrieval done?
- Questions about Critic model HOT 2
- Retrieval-augmented baselines - Huggingface models HOT 4
- I have create a virtual enviroment in anaconda. However, something went wrong when i try to 'pip install -r requirement' HOT 2
- 4 bit quantized version of 7B?
- How long does it takes to train an epoch for critic/generator model on llama-7B with 8 A100?
- What does YOUR_INPUT_FILE look like? Can you provide an example? Thanks very much! HOT 1
- Explanation needed for [Continue to Use Evidence] HOT 1
- How can I get initial input file for generator?
- model issues
- Processed Input Dataset and Flan-3B Critic Generated Dataset
- Reproducing Self-RAG
- accuracy metric HOT 3
- About parameter `max_depth` HOT 2
- Doesn't the generator need to call the retriever when training the model?
- The critic model will generate different type of token when I use run_reward_vllm.py to generate tokens HOT 1
- some problem with run_long_form_static.py
- Data formatting to call the retriever
- Question Regarding Formula Error in Your Paper
- FactScore Inference Fails with KeyError: 'original_splitted_sentences'
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 self-rag.