GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
brutusxu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
brutusxu
Model Tree
Qwen/Qwen3-8B-Base
Input Modalities
Output Modalities
Supported Functionality
This checkpoint is a causal-LM yes/no scorer, saved as Qwen3ForCausalLM
(Qwen3MoeForCausalLM for MoE). The relevance score of a (query, passage) pair
is the yes/no log-odds at the final prompt token:
text
score = logit(" yes") − logit(" no")evaluated right after the prompt suffix "\nIs the passage relevant to the query?".
The prompt is "query: {{query}} passage: {{title}} {{text}}\nIs the passage relevant to the query?"
and no EOS token is appended.
This differs from the HF sequence-classification rerankers in this release (
*-hf,*-lora-hf), which score a single regression logit at EOS.
Score with Tevatron's reranker eval backend (see the Tevatron repo), or directly:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer name = "brutusxu/tevatron3-reranker-8b-distill"tok = AutoTokenizer.from_pretrained(name)model = AutoModelForCausalLM.from_pretrained(name, dtype=torch.bfloat16).cuda().eval()yes_id = tok.encode(" yes", add_special_tokens=False)[-1]no_id = tok.encode(" no", add_special_tokens=False)[-1]prompt = ("query: what is the capital of france " "passage: Paris is the capital of France.\n" "Is the passage relevant to the query?")ids = tok(prompt, return_tensors="pt").to("cuda")with torch.no_grad(): logits = model(**ids).logits[0, -1]print((logits[yes_id] - logits[no_id]).item())If you use this model, please cite the Tevatron toolkit.