初始化项目，由ModelHub XC社区提供模型
Model: jhu-clsp/rank1-llama3-8b Source: Original Platform
This commit is contained in:
ModelHub XC
180
README.md
Normal file
180
README.md
Normal file
@@ -0,0 +1,180 @@
|
||||
---
|
||||
license: mit
|
||||
datasets:
|
||||
- jhu-clsp/rank1-training-data
|
||||
base_model:
|
||||
- meta-llama/Llama-3.1-8B
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- reranker
|
||||
- retrieval
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# rank1-llama3-8b: Test-Time Compute for Reranking in Information Retrieval
|
||||
|
||||
📄 [Paper](https://arxiv.org/abs/2502.18418) | 🚀 [GitHub Repository](https://github.com/orionw/rank1)
|
||||
|
||||
rank1 is a reasoning reranker model that "thinks" before making relevance judgments. This 8B parameter model is trained from the Llama 3.1 8B base model and leverages test-time compute to generate reasoning chains before deciding if a document is relevant to a query.
|
||||
|
||||
## Model Description
|
||||
|
||||
rank1 introduces a novel approach to information retrieval by generating explicit reasoning chains before making relevance judgments. Unlike traditional rerankers that directly output scores, rank1:
|
||||
|
||||
1. Receives a query and document pair
|
||||
2. Generates a reasoning chain within a `<think>...</think>` section
|
||||
3. Makes a binary relevance judgment (`true` or `false`)
|
||||
4. Returns a confidence score based on the logits of the true/false tokens
|
||||
|
||||
This approach helps the model break down complex relevance decisions into logical steps, improving performance across diverse retrieval tasks.
|
||||
|
||||
## Model Family
|
||||
|
||||
| Model | Base | Description |
|
||||
|:------|:-----|:------------|
|
||||
| [rank1-7b](https://huggingface.co/jhu-clsp/rank1-7b) | Qwen2.5-7B | Qwen variant (7B parameters) |
|
||||
| [rank1-14b](https://huggingface.co/jhu-clsp/rank1-14b) | Qwen2.5-14B | Qwen variant (14B parameters) |
|
||||
| [rank1-32b](https://huggingface.co/jhu-clsp/rank1-32b) | Qwen2.5-32B | Qwen variant (32B parameters) |
|
||||
| [rank1-mistral-2501-24b](https://huggingface.co/jhu-clsp/rank1-mistral-2501-24b) | Mistral-Small 2501 24B | Mistral variant (24B parameters) |
|
||||
| [rank1-llama3-8b](https://huggingface.co/jhu-clsp/rank1-llama3-8b) | Llama 3.1 8B | Current model (8B parameters) |
|
||||
|
||||
### Quantized Variants
|
||||
|
||||
| Model | Description |
|
||||
|:------|:------------|
|
||||
| [rank1-7b-awq](https://huggingface.co/jhu-clsp/rank1-7b-awq) | Quantized version of rank1-7b |
|
||||
| [rank1-14b-awq](https://huggingface.co/jhu-clsp/rank1-14b-awq) | Quantized version of rank1-14b |
|
||||
| [rank1-32b-awq](https://huggingface.co/jhu-clsp/rank1-32b-awq) | Quantized version of rank1-32b |
|
||||
| [rank1-mistral-2501-24b-awq](https://huggingface.co/jhu-clsp/rank1-mistral-2501-24b-awq) | Quantized version of rank1-mistral-24b |
|
||||
| [rank1-llama3-8b-awq](https://huggingface.co/jhu-clsp/rank1-llama3-8b-awq) | Quantized version of rank1-llama3-8b |
|
||||
|
||||
## Associated Data and Resources
|
||||
|
||||
| Resource | Description |
|
||||
|:---------|:------------|
|
||||
| [rank1-r1-msmarco](https://huggingface.co/datasets/jhu-clsp/rank1-r1-msmarco) | All R1 output examples from MS MARCO |
|
||||
| [rank1-training-data](https://huggingface.co/datasets/jhu-clsp/rank1-training-data) | Training data used for rank1 models |
|
||||
| [rank1-run-files](https://huggingface.co/datasets/jhu-clsp/rank1-run-files) | Pre-computed run files for use in top 100 doc reranking |
|
||||
| [GitHub Repository](https://github.com/orionw/rank1) | Official rank1 repository |
|
||||
|
||||
## Usage
|
||||
Note that official usage is found on the Github and accounts for edge cases. But for simple use cases the minimal example below works.
|
||||
|
||||
<details>
|
||||
<summary>Click to expand: Minimal example with vLLM</summary>
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
import math
|
||||
|
||||
# Initialize the model with vLLM
|
||||
model = LLM(
|
||||
model="jhu-clsp/rank1-llama3-8b",
|
||||
tensor_parallel_size=1, # Number of GPUs
|
||||
trust_remote_code=True,
|
||||
max_model_len=16000, # Context length
|
||||
gpu_memory_utilization=0.9,
|
||||
dtype="float16",
|
||||
)
|
||||
|
||||
# Set up sampling parameters
|
||||
sampling_params = SamplingParams(
|
||||
temperature=0,
|
||||
max_tokens=8192,
|
||||
logprobs=20,
|
||||
stop=["</think> true", "</think> false"],
|
||||
skip_special_tokens=False
|
||||
)
|
||||
|
||||
# Prepare the prompt
|
||||
def create_prompt(query, document):
|
||||
return (
|
||||
"Determine if the following passage is relevant to the query. "
|
||||
"Answer only with 'true' or 'false'.\n"
|
||||
f"Query: {query}\n"
|
||||
f"Passage: {document}\n"
|
||||
"<think>"
|
||||
)
|
||||
|
||||
# Example usage
|
||||
query = "What are the effects of climate change?"
|
||||
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."
|
||||
|
||||
# Generate prediction
|
||||
prompt = create_prompt(query, document)
|
||||
outputs = model.generate([prompt], sampling_params)
|
||||
|
||||
# Extract score
|
||||
output = outputs[0].outputs[0]
|
||||
text = output.text
|
||||
final_logits = output.logprobs[-1]
|
||||
|
||||
# Get token IDs for "true" and "false" tokens
|
||||
from transformers import AutoTokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-llama3-8b")
|
||||
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
|
||||
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]
|
||||
|
||||
# Calculate relevance score (probability of "true")
|
||||
true_logit = final_logits[true_token].logprob
|
||||
false_logit = final_logits[false_token].logprob
|
||||
true_score = math.exp(true_logit)
|
||||
false_score = math.exp(false_logit)
|
||||
relevance_score = true_score / (true_score + false_score)
|
||||
|
||||
print(f"Reasoning chain: {text}")
|
||||
print(f"Relevance score: {relevance_score}")
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
## Performance
|
||||
|
||||
rank1-llama3-8b demonstrates strong performance on retrieval benchmarks, particularly on tasks requiring complex reasoning. The model's ability to "think through" relevance decisions makes it especially effective for nuanced topics.
|
||||
|
||||
For specific benchmark results and comparisons with other models, please refer to the paper and the official GitHub repository.
|
||||
|
||||
## Installation
|
||||
|
||||
Please see the Github for detailed installation instructions.
|
||||
|
||||
## MTEB Integration
|
||||
|
||||
rank1 is compatible with the [MTEB benchmarking framework](https://github.com/embeddings-benchmark/mteb):
|
||||
|
||||
```python
|
||||
from mteb import MTEB
|
||||
from rank1 import rank1 # From the official repo
|
||||
|
||||
# Initialize the model
|
||||
model = rank1(
|
||||
model_name_or_path="jhu-clsp/rank1-llama3-8b",
|
||||
num_gpus=1,
|
||||
device="cuda"
|
||||
)
|
||||
|
||||
# Run evaluation on specific tasks
|
||||
evaluation = MTEB(tasks=["NevIR"])
|
||||
results = evaluation.run(model)
|
||||
```
|
||||
|
||||
## Citation
|
||||
|
||||
If you use rank1 in your research, please cite our work:
|
||||
|
||||
```bibtex
|
||||
@misc{weller2025rank1testtimecomputereranking,
|
||||
title={Rank1: Test-Time Compute for Reranking in Information Retrieval},
|
||||
author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
|
||||
year={2025},
|
||||
eprint={2502.18418},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.IR},
|
||||
url={https://arxiv.org/abs/2502.18418},
|
||||
}
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
[MIT License](https://github.com/orionw/rank1/blob/main/LICENSE)
|
||||
Reference in New Issue
Block a user