rank_llm

rank_llm copied to clipboard

P4-Better estimate the max word length for passage truncating in prompts

1

For example: maybe in a oneline function that could be used both for LRL and rankGPT prompts? something like: num_words = (context size - num output tokens(current window size) )*...

sahel-sh

Adding support to Llama.cpp with quantized models. 8-bit model: https://huggingface.co/castorini/rank_vicuna_7b_v1_q8_0/ 4-bit model: https://huggingface.co/castorini/rank_vicuna_7b_v1_q4_0/

ArthurCamara

# Summary of changes - bug fix in `extract_kwargs`

xpbowler

Error in Installation using pip in AWS Workspace

1

I tried to install rank_llm using `pip install rank_llm` in my AWS workspace(windows), but it's throwing below error, tried after installing 'wheel' and 'nmslib ' still same error. ``` Building...

nikithakriz

[WIP] Add SGLang Support

1

# Pull Request Checklist ## Reference Issue Please provide the reference to issue this PR is addressing (# followed by the issue number). If there is no associated issue, write...

pjyi2147

Hey, thanks for providing the wonderful library. I am using the GPT-4o model as a Ranker. I use BM25 as the initial retriever (take top 100 results). My code breaks...

Mandeep-Rathee

# Pull Request Checklist ## Reference Issue This is a superset of issue [Top Down](https://github.com/castorini/ura-projects/issues/46). This PR reorganized the various reordering methods including sliding window, top down, as well as...

XKTZ

## Summary Prompt abstraction: - Renamed PromptMode to `Prompt` enum - Added `prefix()` and `suffix()` methods for each enum, where the prompt strings can be found

xpbowler

# Summary of changes - Introduce Pairwise Rerankers with the pairwise_rankllm ABC. - `DuoT5` concrete pairwise reranker @IR3KT4FUNZ

xpbowler

Does this repo contain your training code

1

I wanted to see how you implemented the loss function and back-propogated against it, but i cant find it in the code. Is the training code available to look at

arifsaeed