AdarshSingh7647 / Eklav-Passage-8B

Eklav-Passage-8B

Qwen3-8B passage reranker trained with Eklav : the teacher's reasoning is given as a hint in the prompt and the loss is on the final answer only. Code · Std-SFT version

Results

Usage

Pointwise reranker in the style of Rank1 : the model writes its reasoning, ending in </think> true or </think> false , and relevance is the probability of true at that last token.

from vllm import LLM, SamplingParams
import math

model_id = "AdarshSingh7647/Eklav-Passage-8B"
model = LLM(model=model_id, max_model_len=20000)
tokenizer = model.get_tokenizer()

SYSTEM_PROMPT = "You are a careful retrieval assistant that judges whether a passage is relevant to a user's query."
TASK_INSTRUCTION = "Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'."

def create_prompt(query: str, passage: str) -> str:
    messages = [
        {"role": "system", "content": SYSTEM_PROMPT},
        {"role": "user", "content": f"{TASK_INSTRUCTION}\n\nQuery: {query}\nPassage: {passage}"},
    ]
    return tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True, enable_thinking=True
    )

sampling_params = SamplingParams(
    temperature=0,
    max_tokens=4096,
    logprobs=20,
    stop=["</think> true", "</think> false", "</think>\ntrue", "</think>\nfalse",
          "</think>\n\ntrue", "</think>\n\nfalse"],
)

def score(query: str, passage: str) -> float:
    prompt = create_prompt(query, passage)
    output = model.generate([prompt], sampling_params)[0].outputs[0]
    # the answer token is usually the second to last logprob step (vLLM's stop
    # string match can consume one extra token, e.g. <|im_end|>, after it), but
    # scan from the end so this is robust to that off by one
    for step in reversed(output.logprobs or []):
        true_lp = next((v.logprob for k, v in step.items() if tokenizer.decode([k]).strip().lower() == "true"), None)
        false_lp = next((v.logprob for k, v in step.items() if tokenizer.decode([k]).strip().lower() == "false"), None)
        if true_lp is not None and false_lp is not None:
            true_score, false_score = math.exp(true_lp), math.exp(false_lp)
            return true_score / (true_score + false_score)
    return 0.5

query = "What causes seasons on Earth?"
passages = [
    "Seasons are caused by the tilt of Earth's axis relative to its orbit around the Sun.",
    "The Great Wall of China is visible from space, according to popular belief.",
]
ranked = sorted(passages, key=lambda p: score(query, p), reverse=True)
for p in ranked:
    print(p)